production-readiness-review Skill

Codex compatibility note:

Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.

Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.

User-question prompts mean to ask the user directly in Codex.

Ignore Claude-specific mode-switch instructions when they appear.

Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.

Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.

Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.

For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.

If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex uses static project-reference loading instead of runtime-injected project docs. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.

Situation-based docs:

Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra): project-structure-reference.md
Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md
Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
Spec authoring, docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
Behavior/public-contract changes or spec-test-code sync: workflow-spec-test-code-cycle-reference.md plus the spec docs above
Derived spec indexes/ERDs/reimplementation guides: spec-system-reference.md and source Feature Specs under docs/specs/
Integration test implementation/review: integration-test-reference.md
E2E test implementation/review: e2e-test-reference.md
Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval. [BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.

Quick Summary

Goal: Ensure service/API changes are production-ready for observability, reliability, data integrity, and database performance — scoring each of these dimensions on service-layer and API changes.

Summary:

Main steps (in order): (1) Resolve scope — args else git diff --name-only uncommitted; backend service/API files only, skip frontend/tests/docs/config-only. (2) Score 12 criteria 0-2 across the 4 dimensions (/24). (3) Extended SRE Readiness gate — 8 pass/fail deploy-time + operate-time items; an unaccepted CRITICAL/HIGH fail blocks PASS regardless of the /24 score. Gating, NOT scored — does not change the /24 math. (4) Map score + gate → verdict. (5) Structural Impact Analysis — graph gate (blast-radius, tests_for, downstream trace) when graph.db exists. (6) Validated Fix + Full Re-Review loop on any finding. (7) Emit the SRE Review Results report — file:line evidence per score and per gate item. Execute in order; NEVER skip/merge a step — why: untracked steps get silently merged and gaps reach production.
Score 12 criteria 0-2 across four dimensions (Observability/8, Reliability/8, Data Integrity/4, DB Performance/4) for a /24 PASS (19-24) / NEEDS WORK (13-18) / NOT READY (0-12) verdict — every score needs file:line evidence or it is 0.
The DB Performance Protocol is MANDATORY and non-advisory: ALL list queries must paginate (no unbounded GetAll/ToList) and ALL filter fields, foreign keys, and sort columns must have matching indexes.
VERDICT is advisory only; the graph gate, validated-fix full re-review, and DB Performance Protocol are NEVER skippable regardless of change size — and when batched (≥10 files), re-score all 12 criteria holistically from combined cross-batch evidence, never by averaging per-batch scores.
After applying any fix, validate findings first, then rerun the FULL review (fresh sub-agent with zero prior-round memory); a clean pass ENDS the loop.

When to use: After implementing backend service or API changes, before committing. Frontend-only changes exempt.

Why: Working code that can't be debugged, monitored, or rolled back is technical debt in disguise.

Deployment context: Read docs/project-config.json → infrastructure section:

containerization → check Dockerfiles, docker-compose
orchestration → check K8s manifests, Helm charts
cicd.tool → check pipeline configs

Your Mission

<task> $ARGUMENTS </task>

Review Mindset (NON-NEGOTIABLE)

Be skeptical. Every claim needs traced proof, confidence >80%.

NEVER accept operational readiness at face value — verify by reading implementations
Every score MUST have file:line evidence — unprovable score = 0
Question: "Is this really handled?" → trace error/retry/timeout path to confirm
Challenge: "Are ALL failure modes covered?" → check behavior when dependencies fail
Verify: "Can we debug this in production?" → check logging, correlation, metrics

Scope Resolution

Arguments specify files/directories → review those
Else → review uncommitted changes (git diff --name-only)
Focus: backend source files under service root (per the project's structure reference / docs/project-config.json), API controllers, service classes
Skip: frontend files, test files, documentation, config-only changes

Production Readiness Scoring

Score each criterion 0-2: 0 = not addressed, 1 = partially, 2 = fully.

MANDATORY when batched (≥10 files, SYNC:systematic-review-batching active): score the 12 criteria holistically across the FULL cross-batch scope, NOT by merging or averaging per-batch scores. Several criteria are cross-file — e.g. "all query filter fields have indexes" can have the query in one batch, the migration in another; a per-batch score sees only its ≤8 files and false-flags 0 when the satisfying file lives in a different batch. The synthesis/reduce tier MUST therefore RE-SCORE each of the 12 criteria from combined cross-batch evidence (batch agents surface evidence per criterion; reducer assigns the score). If holistic re-score is infeasible, do NOT batch production-readiness-review — fall back to whole-scope serial scoring.

Observability (max 8)

Think: If this service errors at 3am, can on-call engineer diagnose root cause from logs alone — without reproducing?

| # | Criterion | What to Check | | --- | ---------------------- | ------------------------------------------------------------------------------------------------------------- | | 1 | Structured Logging | External API calls and critical operations log errors with context (request ID, user, parameters) | | 2 | Error Context | Exceptions include enough context to diagnose without reproducing (entity IDs, operation type, input summary) | | 3 | Metrics Awareness | Operations >100ms consider tracking duration. New endpoints consider latency monitoring | | 4 | Correlation | Cross-service calls include or propagate correlation IDs for distributed tracing |

Reliability (max 8)

Think: If the downstream dependency is down or slow, does this service degrade gracefully or cascade-fail?

| # | Criterion | What to Check | | --- | ------------------------- | --------------------------------------------------------------------------------------------------------- | | 5 | Retry Strategy | Transient failures (HTTP, DB timeouts) have retry logic or documented reason for not retrying | | 6 | Timeout Configuration | HTTP clients and external calls have explicit timeout (not relying on defaults) | | 7 | Error Handling | Errors handled gracefully — no swallowed exceptions, no generic catch-all without logging | | 8 | Fallback Behavior | Critical paths define behavior when dependencies fail (degraded mode, cached response, user-facing error) |

Data Integrity (max 4)

Think: If database wiped and reseeded from scratch, does system still reach a valid state?

| # | Criterion | What to Check | | --- | ---------------------- | ------------------------------------------------------------------------------------------------------------- | | 9 | Seed vs Migration | Seed data (default records, system config) lives in startup data seeders, NOT in one-time migration executors | | 10 | Seeder Idempotency | Data seeders use check-then-create pattern (query before insert) — safe for repeated runs on any environment |

Decision test: "If the database is reset, does this data still need to exist?" Yes → must be in seeder. No → migration acceptable.

Database Performance (max 4)

Think: At 10x current data volume, do these queries still complete in <1s?

Database Performance Protocol (MANDATORY):

Paging Required — ALL list/collection queries use pagination. NEVER load all records into memory. Verify: no unbounded GetAll(), ToList(), or Find() without Skip/Take or cursor-based paging.

Index Required — ALL query filter fields, foreign keys, and sort columns have database indexes configured. Verify: entity expressions match index field order, database collections have index management methods, migrations include indexes for WHERE/JOIN/ORDER BY columns.

| # | Criterion | What to Check | | --- | -------------------- | ---------------------------------------------------------------------------------------------------------------------- | | 11 | Pagination | List/collection queries use pagination (Skip/Take, cursor). No unbounded GetAll/ToList loading all records into memory | | 12 | Database Indexes | Query filter fields, foreign keys, and sort columns have matching database indexes. Migrations include index creation |

Spec-Loop Discipline for changed core logic (MANDATORY — gates the verdict, not a scored criterion):

Mutation bar, not coverage % — for changed service/API core logic the bar is the MUTATION-SCORE gate: a surviving mutant on a changed line is a release blocker (it proves an invariant the tests do not assert), NEVER a line-coverage-% question. A green coverage number over un-asserted behavior does not clear this gate.

Dual feedback — every production-readiness finding that changes behavior feeds BOTH the spec (NAME the contract/invariant in Section 8) AND a guarding test; a code-only fix is INCOMPLETE. A surviving mutant → add the killing test AND record the invariant it protects in the spec.

Extended SRE Readiness Gate (step-by-step, pass/fail — gating, NOT scored)

Runs as main step 3, after scoring, before verdict mapping. Deploy-time and operate-time SRE aspects the 12-criteria /24 model does NOT score. Check each item step by step; record pass / partial / fail with file:line evidence or explicit N/A — reason. Gate does not change /24 math — it overlays it: an unaccepted CRITICAL/HIGH fail blocks a PASS verdict regardless of score (per Severity Rubric — CRITICAL/HIGH must be resolved or owner-accepted before PASS). Read deployment context from docs/project-config.json → infrastructure (referenced above) to decide which items are N/A (e.g. no orchestration → readiness/liveness probes N/A with stated reason).

| # | Gate Item | What to Check | Status | Evidence | | --- | ------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------- | ----------------------------- | | G1 | Rollout & Rollback | Deploy is staged/canary-able; a documented, fast rollback path exists (feature flag, versioned + reversible migration). No irreversible one-way change without a stated recovery plan. | pass/partial/fail | file:line or N/A — reason | | G2 | Health Checks | Readiness + liveness endpoints/probes exist and reflect real dependency health (not an always-200 stub). | pass/partial/fail | ... | | G3 | Alerting & Runbook | New failure modes have an actionable alert (signal, not noise) and a runbook / escalation note. | pass/partial/fail | ... | | G4 | SLO / Error-Budget | Change respects an SLO or names the latency/availability target it affects; no silent new failure mode against the budget. | pass/partial/fail | ... | | G5 | Capacity & Resource Limits | Load ceilings, resource limits, autoscaling/back-pressure considered; no unbounded fan-out or unbounded in-memory growth. | pass/partial/fail | ... | | G6 | Config & Secrets | Required config present in all envs and fails fast if missing; no secrets committed in the diff. | pass/partial/fail | ... | | G7 | Graceful Shutdown/Startup | In-flight work drains on shutdown; startup waits for / degrades gracefully on unready dependencies. | pass/partial/fail | ... | | G8 | Concurrency & Idempotency | Operations are safe under retry / at-least-once delivery; no race on shared state; idempotency keys where needed. | pass/partial/fail | ... |

Gate verdict: {n}/8 pass. Any CRITICAL/HIGH fail not explicitly owner-accepted ⇒ overall verdict cannot be PASS even at a 19-24 score.

Technique Applicability (advisory — NON-SCORING, NON-GATING)

Invoke SYNC:scale-technique-gate: derive the system's scale tier from evidence (users/RPS, SLO, data volume, tenancy, topology — cite file:line/config/infra + confidence), then emit the Technique Applicability Matrix (technique | tier-warranted? | present? | verdict | advice | evidence) across the 10 concern groups. Surface warranted-but-missing reliability/scale techniques (rate limiting, backups, DR, failover, graceful degradation) as advice; flag OVER-ENGINEERED techniques the tier does not warrant.

Advisory only — this matrix does NOT add a gate item, does NOT change the {n}/8 gate result, the /24 score, or the verdict. A MISSING-WARRANTED technique is guidance to consider at this tier, NOT a gate fail. N/A-by-scale for small systems is expected, never a failure. Full catalog → .claude/docs/scale-technique-catalog.md.

Scoring

| Score | Verdict | Recommendation | | ----- | -------------- | ----------------------------------------------------------------------------------------- | | 19-24 | PASS | Production-ready. Proceed to commit. | | 13-18 | NEEDS WORK | Address gaps before deploying to production. OK for dev/staging. | | 0-12 | NOT READY | Significant operational gaps. Review Operational Readiness rules in code-review-rules.md. |

Run python .claude/scripts/code_graph connections <file> --json on service boundary files for cross-service impact.

Structural Impact Analysis (MANDATORY when graph.db exists)

python .claude/scripts/code_graph graph-blast-radius --json → blast radius >20 nodes = high-risk deployment
python .claude/scripts/code_graph query tests_for <function_name> --json → verify test coverage on changed functions
python .claude/scripts/code_graph trace <service-file> --direction downstream --json → verify all downstream event handlers, bus consumers, cross-service calls have error handling

Why-Review Findings Validation Gate (MANDATORY when findings exist)

Purpose: Adversarial validation of own findings BEFORE any fix. Catches over-flagged criteria, false positives, and severity/score inflation at the source rather than letting them drive fixes or ship downstream.

Trigger: Any finding produced (any severity). Skip ONLY when the verdict is unconditional PASS with literally zero findings.

Protocol:

Read own finalized report from plans/reports/{skill}-{date}-{slug}.md
Invoke $why-review --validate-findings plans/reports/{skill}-{date}-{slug}.md — verify each finding has file:line proof, steel-man each rejected interpretation, and stress-test every severity/score classification (each finding must clear why-review's finding-survival bar to be kept)
Read the CLEAN / HAS-ISSUES verdict returned by why-review
If why-review demotes/removes any finding: UPDATE own report with revised severities, remove false positives, and add a ## Why-Review Validation Notes section citing what changed and why
If why-review confirms all findings: append a ## Why-Review Validation line stating "All N findings re-validated against actual code; no severity changes."

Skip conditions (record explicit reason if skipping): unconditional PASS with zero findings; why-review is itself the active context (avoid recursion).

Why this exists: SRE sub-agent reports inherit confirmation bias — the orchestrator absorbs severity claims as ground truth. Validate findings BEFORE the fix so no fix is ever driven by an inflated or false finding; this gate feeds the "Validated Fix + Full Re-Review" loop below.

Validated Fix + Full Re-Review (MANDATORY when fixes are applied)

When a review pass finds issues, validate findings before any fix. Do NOT spawn a fresh sub-agent only to re-review the same finding set before validation/fix. After validated SRE fixes applied, rerun the full SRE review. If that restarted review uses a sub-agent, spawn it with ZERO prior-round memory. A clean review pass ENDS the review.

When a fresh sub-agent is part of the restarted review, spawn via canonical template in SYNC:review-protocol-injection:

agent_type: code-reviewer
Task: "SRE production readiness review after validated fixes — score all 12 criteria (0-2) for {files reviewed in the current full scope}"
Review mode: "Fresh full re-review after validated fixes. Zero memory of prior rounds. Re-read ALL target files from scratch."
Reference Docs: docs/project-reference/code-review-rules.md
Target Files: same files from Scope Resolution
Integrate sub-agent report findings — DO NOT filter or override

Fresh re-review focus (what prior rounds typically miss):

Operational concerns spanning multiple services
Subtle reliability gaps (retry, circuit breakers, timeout handling)
Missing observability (structured logging, correlation IDs, metrics)
Data-integrity edge cases under concurrent load

Final verdict = every review pass that actually ran, combined.

Output Format

## SRE Review Results

**Scope:** {files reviewed}
**Date:** {date}
**Score:** {X}/24
**Verdict:** PASS / NEEDS WORK / NOT READY

### Observability ({X}/8)

| #   | Criterion          | Score | Evidence                   |
| --- | ------------------ | ----- | -------------------------- |
| 1   | Structured Logging | 0/1/2 | {file:line or "not found"} |
| 2   | Error Context      | 0/1/2 | ...                        |
| 3   | Metrics Awareness  | 0/1/2 | ...                        |
| 4   | Correlation        | 0/1/2 | ...                        |

### Reliability ({X}/8)

| #   | Criterion         | Score | Evidence |
| --- | ----------------- | ----- | -------- |
| 5   | Retry Strategy    | 0/1/2 | ...      |
| 6   | Timeout Config    | 0/1/2 | ...      |
| 7   | Error Handling    | 0/1/2 | ...      |
| 8   | Fallback Behavior | 0/1/2 | ...      |

### Data Integrity ({X}/4)

| #   | Criterion          | Score | Evidence |
| --- | ------------------ | ----- | -------- |
| 9   | Seed vs Migration  | 0/1/2 | ...      |
| 10  | Seeder Idempotency | 0/1/2 | ...      |

### Database Performance ({X}/4)

| #   | Criterion        | Score | Evidence |
| --- | ---------------- | ----- | -------- |
| 11  | Pagination       | 0/1/2 | ...      |
| 12  | Database Indexes | 0/1/2 | ...      |

### Extended SRE Readiness ({n}/8 gate — pass/fail, does not change /24)

| #   | Gate Item                  | Status            | Evidence          |
| --- | -------------------------- | ----------------- | ----------------- |
| G1  | Rollout & Rollback         | pass/partial/fail | `file:line` / N/A |
| G2  | Health Checks              | pass/partial/fail | ...               |
| G3  | Alerting & Runbook         | pass/partial/fail | ...               |
| G4  | SLO / Error-Budget         | pass/partial/fail | ...               |
| G5  | Capacity & Resource Limits | pass/partial/fail | ...               |
| G6  | Config & Secrets           | pass/partial/fail | ...               |
| G7  | Graceful Shutdown/Startup  | pass/partial/fail | ...               |
| G8  | Concurrency & Idempotency  | pass/partial/fail | ...               |

_Any unaccepted CRITICAL/HIGH `fail` above blocks a PASS verdict regardless of the /24 score._

### Gaps to Address

- {specific actionable item}

### Recommendation

{Proceed / Address gaps first}

Important Notes

Advisory (final VERDICT only) — score/verdict inform team but don't block commits; MANDATORY process steps (graph gate, validated-fix full re-review, Database Performance Protocol) are NEVER advisory
Evidence-based — cite file:line for every score; unprovable score = 0
Proportional — small bug fixes need less rigor than new endpoints (applies to VERDICT interpretation, NOT to skipping MANDATORY steps)
Extended SRE Readiness gate is pass/fail, NOT scored — does not change /24 math; but an unaccepted CRITICAL/HIGH gate fail blocks a PASS verdict (Severity Rubric). Use docs/project-config.json → infrastructure to mark items N/A with stated reason
Check framework patterns — background-job base handlers, base-controller error handling

Workflow Recommendation

MANDATORY — NO EXCEPTIONS: If NOT already in workflow, use ask the user directly to ask user:

Activate workflow-feature workflow (Recommended) — scout → investigate → plan → feature-implement → review → production-readiness-review → test → docs

Execute $production-readiness-review directly — run standalone

Next Steps

MANDATORY — NO EXCEPTIONS — after completing, use ask the user directly:

"$watzup (Recommended)" — wrap up + check doc staleness
"$test" — run tests before wrapping up
"Skip, continue manually" — user decides

Combined audit: For a whole-project architecture + compliance + production-readiness audit in one pass, run $architecture-review-full (or $start-workflow workflow-architecture-audit) — fans out this skill, architecture-review, architecture-scalability-review as parallel sub-agents and synthesizes one consolidated report.

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting. For simple tasks, AI MUST ask user whether to skip.

docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models)

Critical Purpose: Ensure quality — no flaws, no bugs, no missing updates, no stale content. Verify code AND documentation.

External Memory: Complex/lengthy work → write intermediate findings + final results to plans/reports/ — prevents context loss, serves as deliverable.

Evidence Gate: MANDATORY — every claim, finding, recommendation requires file:line proof or traced evidence with confidence percentage (>80% to act, <80% verify first).

Graph-Assisted Investigation — MANDATORY when .code-graph/graph.db exists.

HARD-GATE: MUST ATTENTION run at least ONE graph command on key files before concluding any investigation.

Pattern: Grep finds files → trace --direction both reveals full system flow → Grep verifies details

| Task | Minimum Graph Action | | ------------------- | -------------------------------------------- | | Investigation/Scout | trace --direction both on 2-3 entry files | | Fix/Debug | callers_of on buggy function + tests_for | | Feature/Enhancement | connections on files to be modified | | Code Review | tests_for on changed functions | | Blast Radius | trace --direction downstream |

CLI: python .claude/scripts/code_graph {command} --json. Use --node-mode file first (10-30x less noise), then --node-mode function for detail.

Sub-Agent Return Contract — When this skill spawns a sub-agent, the sub-agent MUST return ONLY this structure. Main agent reads only this summary — NEVER requests full sub-agent output inline.
## Sub-Agent Result: [skill-name]

Status: ✅ PASS | ⚠️ PARTIAL | ❌ FAIL
Confidence: [0-100]%

### Findings (Critical/High only — max 10 bullets)

- [severity] [file:line] [finding]

### Actions Taken

- [file changed] [what changed]

### Blockers (if any)

- [blocker description]

Full report: plans/reports/[skill-name]-[date]-[slug].md
Main agent reads Full report file ONLY when: (a) resolving a specific blocker, or (b) building a fix plan. Sub-agent writes full report incrementally (per SYNC:incremental-persistence) — not held in memory.

Context budget — the return payload is a SUMMARY, not a transcript: ≤10 finding bullets, no raw file contents / full diffs / verbatim logs inline, no re-pasted source. Everything beyond the summary lives in the Full report on disk. A sub-agent that would exceed the summary shape MUST write the detail to its report and return only the pointer — the orchestrator's context is the scarce resource the whole map-reduce protects.

Nested Task Expansion Contract — For workflow-step invocation, the [Workflow] ... row is only a parent container; the child skill still creates visible phase tasks.

Call the current task list first. If a matching active parent workflow row exists, set nested=true and record parentTaskId; otherwise run standalone.

Create one task per declared phase before phase work. When nested, prefix subjects [N.M] $skill-name — phase.

When nested, link the parent with TaskUpdate(parentTaskId, addBlockedBy: [childIds]).

Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.

Mark exactly one child in_progress before work and completed immediately after evidence is written.

Complete the parent only after all child tasks are completed or explicitly cancelled with reason.

Blocked until: the current task list done, child phases created, parent linked when nested, first child marked in_progress.

Project Reference Docs Gate — Run after task-tracking bootstrap and before target/source file reads, grep, edits, or analysis. Project docs override generic framework assumptions.

Identify scope: file types, domain area, and operation.

Read docs/project-config.json first — the project's machine-readable map. It is the single source of truth for THIS repo (modules/paths, framework + search keywords, test/E2E/integration run-commands, design system, architecture rules, workflow patterns); ground exact paths, run-commands, and conventions on it before investigating, planning, or coding — never assume framework defaults (CLAUDE.md + reference docs are derived from it). If it — or the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any required reference doc — is missing or stale, auto-run $project-init or the narrow route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) first; if Codex mirrors or AGENTS.md are stale, ask the user to run $sync-codex (never auto-run it).

Required docs by trigger: always docs/project-reference/lessons.md; doc lookup docs-index-reference.md; review code-review-rules.md; backend/CQRS/API backend-patterns-reference.md; domain/entity domain-entities-reference.md; frontend/UI frontend-patterns-reference.md; styles/design scss-styling-guide.md + design-system/design-system-canonical.md; integration tests integration-test-reference.md; E2E e2e-test-reference.md; feature docs/specs feature-spec-reference.md + spec-system-reference.md + spec-principles.md; behavior/public-contract/spec-test-code sync workflow-spec-test-code-cycle-reference.md; derived spec index/ERD/reimplementation guides spec-system-reference.md + source Feature Specs under docs/specs/; architecture/new area project-structure-reference.md.

Read every required doc, then before target work state: Reference docs read: ... | Not applicable: ....

Ready when: scope evaluated, docs/project-config.json consulted, required docs checked/read or setup route completed, lessons.md confirmed, citation emitted.

Task Tracking & External Report Persistence — Bootstrap this before execution; then run project-reference doc prefetch before target/source work.

Create a small task breakdown before target file reads, grep, edits, or analysis. On context loss, inspect the current task list first.

Mark one task in_progress before work and completed immediately after evidence; never batch transitions.

For plan/review work, create plans/reports/{skill}-{YYMMDD}-{HHmm}-{slug}.md before first finding.

Append findings after each file/section/decision and synthesize from the report file at the end.

Final output cites Full report: plans/reports/{filename}.

Blocked until: task breakdown exists, report path declared for plan/review work, first finding persisted before the next finding.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

Evidence-Based Reasoning — Speculation is FORBIDDEN. Every claim needs proof.

Cite file:line, grep results, or framework docs for EVERY claim

Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend

Cross-service validation required for architectural changes

"I don't have enough evidence" is valid and expected output

BLOCKED until: - [ ] Evidence file path (file:line) - [ ] Grep search performed - [ ] 3+ similar patterns found - [ ] Confidence level stated

Forbidden without proof: "obviously", "I think", "should be", "probably", "this is because" If incomplete → output: "Insufficient evidence. Verified: [...]. Not verified: [...]."

Validated-Finding Fix + Full Re-Review Loop — Re-review is triggered by a validated finding fix cycle, not by a round number. Review purpose: review → validate findings → fix validated findings → full re-review until a complete review pass clears the round's exit bar (see Severity floor below). A clean review ENDS the loop — no further rounds required.

aka Self-Review Convergence Loop. The name is historical — there is NO 2-round cap; "double-round-trip" only means a validated-finding fix cycle forces at least one fresh re-review. It runs until a clean pass, bounded by the 3-round ceiling below.

Round cap — 3 rounds MAX (a ceiling, NEVER a target). A clean pass ENDS the loop immediately at ANY round — round 1 included; the cap never obliges you to keep spinning. Hitting round 3 with blocking findings still open (severity floor applied) → STOP and escalate by asking the user directly with the still-open findings listed; NEVER emit a silent "good enough" PASS on cap exhaustion, and NEVER let the cap substitute for the clean-review requirement. The 2-repeated-no-progress blocker rule stays an EARLIER exit — escalate at whichever trips first.

Severity floor — from round 3, LOW stops blocking. The exit bar tightens by round, so the loop converges on consequence instead of spinning on polish:

Define one predicate everywhere: blocking_findings(round, findings) returns all validated findings in rounds 1–2 and only validated CRITICAL/HIGH/MEDIUM findings in round 3+. A binary gate (test-green, security must-fix, required artifact) is exempt only when its owning invariant explicitly says so.

| Round | Exit bar — loop ENDS when the fresh full review has… | Must be fixed to continue | | ----- | ------------------------------------------------------------------------- | ------------------------------ | | 1-2 | zero validated findings at ANY severity | CRITICAL · HIGH · MEDIUM · LOW | | 3+ | zero validated CRITICAL / HIGH / MEDIUM findings — LOW-only is a PASS | CRITICAL · HIGH · MEDIUM only |

From round 3 onward LOW findings are NOT required to be fixed: a round whose validated findings are ALL LOW ENDS the loop immediately — do not open another round for them. Severity tiers are SYNC:severity-rubric (CRITICAL block-merge · HIGH must-fix · MEDIUM should-fix · LOW nice-to-fix); rounds 1-2 are unchanged, so an easy LOW still gets fixed early when it is cheap.

Severity-floor rules:

Never silently drop a deferred LOW. Every unfixed LOW is listed in the final report under ## Deferred LOW Findings (severity floor, round ≥3) with file, line, and description, so the owner can schedule it. Dropping it from the report is a protocol violation, not a clean pass.

Never re-tier a finding to trigger the exit. Downgrading a real CRITICAL/HIGH/MEDIUM to LOW so the loop can end is a FALSE PASS. Severity is set by consequence per SYNC:severity-rubric before the round bar is applied — never after, and never with the exit in view. — why: a floor that can be reached by relabeling is not a floor.

The floor bounds the loop, not the standard. It ends iteration; it never authorizes shipping a known CRITICAL/HIGH/MEDIUM, and it never lowers the finding-survival bar that admits a finding in the first place.

The floor never applies to a hard gate. Test-green gates (a suite must actually pass), security must-fix gates, and any gate whose criterion is binary rather than severity-rated are unaffected — a failing test is a failure, not a LOW finding.

Universal scope (any new output/judgment): any newly produced output or judgment gets ≥1 self-review; any new judgment gets ≥1 $why-review --validate-findings pass; anything flagged to re-check is re-checked ≥1 time — before that output is treated as final. This loop is the default convergence contract for ANY work-producing skill, not review skills only.

Routing invariant (author-facing): a skill that validates findings MUST route them through $why-review --validate-findings (the terminal validator) — NEVER fork an inline finding-validation. Routing through why-review is what makes the finding-survival bar and this loop apply; the verify-review-validate-coverage sensor enforces this exact route mechanically.

Round 1: Main-session review. Read target files, build understanding, note issues. Output findings + verdict (PASS / FAIL).

Decision after Round 1:

No issues found (PASS, zero findings) → review ENDS. Do NOT spawn a fresh sub-agent for confirmation.

blocking_findings(round, findings) is non-empty → run the active review skill's findings-validation gate first; for review skills the default gate is $why-review --validate-findings <report-path>. Fix only validated findings, then restart the full review protocol from the beginning with a fresh task breakdown.

Fresh full re-review after every fix cycle: Re-run the whole review protocol over the current full target. When sub-agents are part of that protocol, spawn NEW spawn_agent calls — never reuse prior agents. Reviewers re-read ALL files from scratch with ZERO memory of prior rounds. See SYNC:fresh-context-review for the spawn mechanism and SYNC:review-protocol-injection for the canonical Agent prompt template. Each fresh full review must catch:

Cross-cutting concerns missed in the prior round

Interaction bugs between changed files

Convention drift (new code vs existing patterns)

Missing pieces that should exist but don't

Subtle edge cases the prior round rationalized away

Regressions introduced by the fixes themselves

Loop termination: After each full re-review, repeat the same decision against that round's exit bar: bar cleared → END; blocking findings remain → validate findings → fix → restart from the first review phase. Rounds 1-2 clear on zero findings at any severity; from round 3 the bar is zero CRITICAL/HIGH/MEDIUM, so a LOW-only round ENDS the loop (deferred LOWs go in the report). Capped at 3 rounds. Escalate by asking the user directly at whichever comes first: the same validated finding repeats for 2 full invocations with no progress · a fix requires product/owner input · round 3 completes with CRITICAL/HIGH/MEDIUM still open. NEVER loop past 3 rounds, and NEVER convert cap exhaustion into a PASS.

Rules:

A clean Round 1 ENDS the review — no mandatory Round 2

From round 3 on, a round whose validated findings are ALL LOW ENDS the loop — never open round N+1 to fix LOW alone; list those LOWs as deferred instead

NEVER re-tier a CRITICAL/HIGH/MEDIUM down to LOW to reach the round-3 exit — severity is assigned by consequence before the bar is applied

NEVER fix unvalidated findings; validate first using the caller's validation gate

Every surviving finding must additionally clear the finding-survival bar defined in why-review's Findings Validation Routine (a deliberately higher bar than the generic act-gate — "keep this finding?" is a stricter question than "act on this evidence?"); a finding below the bar is demoted or dropped, not kept

NEVER skip the full re-review after a fix cycle (every fix invalidates the prior verdict)

NEVER reuse a sub-agent across rounds — every iteration that uses sub-agents spawns NEW Agent calls

Main agent READS sub-agent reports but MUST NOT filter, reinterpret, or override findings

The 3-round cap NEVER replaces the clean-review requirement — it bounds runaway looping, it does not authorize shipping an un-clean review; a clean pass ends the loop early at any round, and cap exhaustion escalates rather than passes

Enforce the round cap of 3 alongside the 2 repeated-no-progress blocker rule; both are escalation triggers, neither is a completion criterion

Track recursive invocation count and repeated blockers in conversation context (session-scoped)

Final verdict must incorporate ALL rounds executed

Report must include ## Round N Findings (Fresh Sub-Agent) for every round N≥2 that was executed, plus ## Deferred LOW Findings (severity floor, round ≥3) whenever the loop ended on the round-3+ bar with LOWs still open.

Fresh Context Re-Review — Eliminate orchestrator confirmation bias after fixes by restarting the full review with isolated sub-agents where applicable.

Why: The main agent knows what it (or $feature-implement) just fixed and rationalizes findings accordingly. A fresh sub-agent has ZERO memory, re-reads from scratch, and catches what the main agent dismissed. Sub-agent bias is mitigated by (1) fresh context, (2) verbatim protocol injection, (3) main agent not filtering the report.

When: ONLY after a validated-finding fix cycle. A review round that finds zero issues ENDS the loop — do NOT spawn a confirmation sub-agent. A review round that finds issues triggers: validate findings → fix → full review restart from the first phase.

How:

Start a NEW full review invocation/task breakdown; when that protocol calls for agents, spawn NEW spawn_agent tool calls — use code-reviewer agent_type for code reviews, general-purpose for plan/doc/artifact reviews

Inject ALL required review protocols VERBATIM into the prompt — see SYNC:review-protocol-injection for the full list and template. Never reference protocols by file path; AI compliance drops behind file-read indirection (see SYNC:shared-protocol-duplication-policy)

Sub-agent re-reads ALL target files from scratch via its own tool calls — never pass file contents inline in the prompt

Sub-agent writes structured report to plans/reports/{review-type}-round{N}-{date}.md

Main agent reads the report, integrates findings into its own report, DOES NOT override or filter

Rules:

SKIP fresh sub-agent when the prior full review found zero issues (no fixes = nothing new to verify)

NEVER skip the full review restart after a fix cycle — every fix invalidates the prior verdict

NEVER reuse a sub-agent across rounds — every fresh round spawns a NEW spawn_agent call

Continue until a complete full review pass clears that round's exit bar per SYNC:double-round-trip-review: rounds 1-2 → zero findings at any severity; round 3+ → zero CRITICAL/HIGH/MEDIUM, so a round whose validated findings are ALL LOW ENDS the loop (list those LOWs as deferred instead of spawning another round). If the same blocker repeats 3 times with no progress, escalate by asking the user directly

Track iteration count and repeated blockers in conversation context (session-scoped, no persistent files)

Review Protocol Injection — Every fresh sub-agent review prompt MUST embed 11 protocol blocks VERBATIM. The template below has ALL 11 bodies already expanded inline. Copy the template wholesale into the Agent call's prompt field at runtime, replacing only the {placeholders} in Task / Round / Reference Docs / Target Files / Output sections with context-specific values. Do NOT touch the embedded protocol sections.

Why inline expansion: Placeholder markers would force file-read indirection at runtime. AI compliance drops significantly behind indirection (see SYNC:shared-protocol-duplication-policy). Therefore the template carries all 11 protocol bodies pre-embedded.

Subagent Type Selection

code-reviewer — for code reviews (reviewing source files, git diffs, implementation)
general-purpose — for plan / doc / artifact reviews (reviewing markdown plans, docs, specs)

Canonical Agent Call Template (Copy Verbatim)

spawn_agent({
  description: "Fresh Round {N} review",
  agent_type: "code-reviewer",
  prompt: `
## Task
{review-specific task — e.g., "Review all uncommitted changes for code quality" | "Review plan files under {plan-dir}" | "Review integration tests in {path}"}

## Round
Round {N}. You have ZERO memory of prior rounds. Re-read all target files from scratch via your own tool calls. Do NOT trust anything from the main agent beyond this prompt.

## Protocols (follow VERBATIM — these are non-negotiable)

### Spec ↔ Tests ↔ Code Triangulation
DO THIS FIRST — before any per-protocol check below. The review target is the WHOLE PACKAGE, not the diff alone: load the behavior's spec (§3 ACs / §4 BRs / §8 TCs), its tests, and the changed code TOGETHER, and reason about their mutual consistency BEFORE judging any one in isolation.
1. Locate all three faces: the Feature Spec section(s) governing the changed behavior, the tests that guard it, and the production code that implements it. A missing face is itself a finding (SPEC-GAP / TEST-GAP / DEAD-SPEC).
2. Triangulate pairwise — every disagreement is a finding; classify which face is wrong:
   - code vs spec: behavior the code does that no §3/§4/§8 rule describes → CODE-EXTRA or SPEC-STALE; a [HARD] §4 rule or §5 invariant with no enforcing code path → CODE-WRONG.
   - tests vs spec: a §8 TC with no test, or a test asserting behavior no TC/rule names → TEST-GAP or SPEC-SILENT.
   - tests vs code: a changed code path with no covering test → TEST-GAP; a test that still passes against a deliberately broken invariant → WEAK-TEST (apply the mutation thinking in Bug Detection).
3. Hidden-rule capture: any invariant the code enforces but the spec never states (SPEC-SILENT) MUST be surfaced as a finding to add into §3/§4/§8 AND guarded with a test — the enrichment loop, never a silent pass.
4. Only after the three faces agree — or every disagreement is logged as a finding — proceed to the per-protocol checks below; when enrichment adds spec/test content, re-review the package against the enriched spec.
NEVER mark review PASS while any spec/test/code face disagrees without a logged finding. The diff is the entry point; the package is the unit of judgment.

### Evidence-Based Reasoning
Speculation is FORBIDDEN. Every claim needs proof.
1. Cite file:line, grep results, or framework docs for EVERY claim
2. Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend
3. Cross-service validation required for architectural changes
4. "I don't have enough evidence" is valid and expected output
BLOCKED until: Evidence file path (file:line) provided; Grep search performed; 3+ similar patterns found; Confidence level stated.
Forbidden without proof: "obviously", "I think", "should be", "probably", "this is because".
If incomplete → output: "Insufficient evidence. Verified: [...]. Not verified: [...]."

### Bug Detection
MUST check categories 1-4 for EVERY review. Never skip.
1. Null Safety: Can params/returns be null? Are they guarded? Optional chaining gaps? .find() returns checked?
2. Boundary Conditions: Off-by-one (< vs <=)? Empty collections handled? Zero/negative values? Max limits?
3. Error Handling: Try-catch scope correct? Silent swallowed exceptions? Error types specific? Cleanup in finally?
4. Resource Management: Connections/streams closed? Subscriptions unsubscribed on destroy? Timers cleared? Memory bounded?
5. Concurrency (if async): Missing await? Race conditions on shared state? Stale closures? Retry storms?
6. Stack-Specific: Check the configured language/runtime pitfalls and framework-specific failure modes discovered from local code.
Classify: CRITICAL (crash/corrupt) → FAIL | HIGH (incorrect behavior) → FAIL | MEDIUM (edge case) → WARN | LOW (defensive) → INFO.

### Design Patterns Quality
Priority checks for every code change:
1. DRY via OOP: Same-suffix classes (*Entity, *Dto, *Service) MUST share base class. 3+ similar patterns → extract to shared abstraction.
2. Right Responsibility: Logic in LOWEST layer (Entity > Domain Service > Application Service > Controller). Never business logic in controllers.
3. SOLID: Single responsibility (one reason to change). Open-closed (extend, don't modify). Liskov (subtypes substitutable). Interface segregation (small interfaces). Dependency inversion (depend on abstractions).
4. After extraction/move/rename: Grep ENTIRE scope for dangling references. Zero tolerance.
5. YAGNI gate: NEVER recommend patterns unless 3+ occurrences exist. Don't extract for hypothetical future use.
Anti-patterns to flag: God Object, Copy-Paste inheritance, Circular Dependency, Leaky Abstraction.

### Logic & Intention Review
Verify WHAT code does matches WHY it was changed.
1. Change Intention Check: Every changed file MUST serve the stated purpose. Flag unrelated changes as scope creep.
2. Happy Path Trace: Walk through one complete success scenario through changed code.
3. Error Path Trace: Walk through one failure/edge case scenario through changed code.
4. Acceptance Mapping: If plan context available, map every acceptance criterion to a code change.
5. Tests Verify Intent: For test/spec changes, verify tests name the protected business rule or invariant and would fail if that intent breaks.
6. Migration Test Exclusion: Do not write tests for migration code. Schema/data migrations are one-time execution paths, not core application logic.
NEVER mark review PASS without completing both traces (happy + error path).

### Test Spec Verification
Map changed code to test specifications.
1. Identify the project's test/spec format from existing docs, test-case files, BDD feature files, or spec folders.
2. Every changed code path MUST map to a corresponding test case/spec (or flag as "needs test case").
3. New functions/endpoints/handlers → flag for test spec creation.
4. Migration files are excluded from test/spec creation; schema/data migrations are one-time execution paths, not core application logic.
5. If spec evidence fields exist, verify they point to actual code (file:line, not stale references).
6. Verify each meaningful test case names the business intent/invariant; flag behavior-only cases that only mirror implementation details.
7. Auth/data changes → verify corresponding authorization and data-state test cases exist.
8. If no specs exist for a changed path → log the gap and recommend the project's test-spec workflow.
NEVER skip test mapping. Untested code paths are the #1 source of production bugs.

### Behavioral Delta Matrix
MANDATORY for any bugfix review. Produce input-state × pre-fix × post-fix × delta table BEFORE writing verdict.
- Minimum 3 rows; include at least one row OUTSIDE the original bug report.
- Any "REGRESSION" delta → review returns FAIL until a preservation test is added.
- Narrative descriptions do NOT substitute for the matrix.
Example rows (external-record sync fix):
| Input                 | Pre-fix | Post-fix                  | Delta      |
| --------------------- | ------- | ------------------------- | ---------- |
| Record exists (valid) | Reused  | Always recreated → orphan | REGRESSION |
| Record missing (404)  | Error   | Recreated                 | Fixed      |

### Fix-Layer Accountability
NEVER fix at the crash site. Trace the full flow, fix at the owning layer. The crash site is a SYMPTOM, not the cause.
MANDATORY before ANY fix:
1. Trace full data flow — Map the complete path from data origin to crash site across ALL layers (storage → backend → API → frontend → UI). Identify where bad state ENTERS, not where it CRASHES.
2. Identify the invariant owner — Which layer's contract guarantees this value is valid? Fix at the LOWEST layer that owns the invariant, not the highest layer that consumes it.
3. One fix, maximum protection — If fix requires touching 3+ files with defensive checks, you are at the wrong layer — go lower.
4. Verify no bypass paths — Confirm all data flows through the fix point. Check for direct construction skipping factories, clone/spread without re-validation, raw data not wrapped in domain models, mutations outside the model layer.
BLOCKED until: Full data flow traced (origin → crash); Invariant owner identified with file:line evidence; All access sites audited (grep count); Fix layer justified (lowest layer that protects most consumers).
Anti-patterns (REJECT): "Fix it where it crashes" (crash site ≠ cause site, trace upstream); "Add defensive checks at every consumer" (scattered defense = wrong layer); "Both fix is safer" (pick ONE authoritative layer).

### Rationalization Prevention
AI skips steps via these evasions. Recognize and reject:
- "Too simple for a plan" → Simple + wrong assumptions = wasted time. Plan anyway.
- "I'll test after" → RED before GREEN. Write/verify test first.
- "Already searched" → Show grep evidence with file:line. No proof = no search.
- "Just do it" → Still need task tracking. Skip depth, never skip tracking.
- "Just a small fix" → Small fix in wrong location cascades. Verify file:line first.
- "Code is self-explanatory" → Future readers need evidence trail. Document anyway.
- "Combine steps to save time" → Combined steps dilute focus. Each step has distinct purpose.

### Graph-Assisted Investigation
MANDATORY when .code-graph/graph.db exists.
HARD-GATE: MUST run at least ONE graph command on key files before concluding any investigation.
Pattern: Grep finds files → trace --direction both reveals full system flow → Grep verifies details.
- Investigation/Scout: trace --direction both on 2-3 entry files
- Fix/Debug: callers_of on buggy function + tests_for
- Feature/Enhancement: connections on files to be modified
- Code Review: tests_for on changed functions
- Blast Radius: trace --direction downstream
CLI: python .claude/scripts/code_graph {command} --json. Use --node-mode file first (10-30x less noise), then --node-mode function for detail.

### Understand Code First
HARD-GATE: Do NOT write, plan, or fix until you READ existing code.
1. Search 3+ similar patterns (grep/glob) — cite file:line evidence.
2. Read existing files in target area — understand structure, base classes, conventions.
3. Run python .claude/scripts/code_graph trace <file> --direction both --json when .code-graph/graph.db exists.
4. Map dependencies via connections or callers_of — know what depends on your target.
5. Write investigation to .ai/workspace/analysis/ for non-trivial tasks (3+ files).
6. Re-read analysis file before implementing — never work from memory alone.
7. NEVER invent new patterns when existing ones work — match exactly or document deviation.
BLOCKED until: Read target files; Grep 3+ patterns; Graph trace (if graph.db exists); Assumptions verified with evidence.

## Reference Docs (READ before reviewing)
- `.claude/docs/development-rules.md` — canonical development rules, code-quality guidelines, and pre-commit checklist
- docs/project-reference/code-review-rules.md
- {skill-specific reference docs — e.g., integration-test-reference.md for integration-test-review; backend-patterns-reference.md for backend reviews; frontend-patterns-reference.md for frontend reviews}

## Target Files
{explicit file list OR "run git diff to see uncommitted changes" OR "read all files under {plan-dir}"}

## Output
Write a structured report to plans/reports/{review-type}-round{N}-{date}.md with sections:
- Status: PASS | FAIL
- Issue Count: {number}
- Critical Issues (with file:line evidence)
- High Priority Issues (with file:line evidence)
- Medium / Low Issues
- Cross-cutting findings

Return the report path and status to the main agent.
Every finding MUST have file:line evidence. Speculation is forbidden.
`
})

Rules

DO copy the template wholesale — including all 11 embedded protocol sections
DO replace only the {placeholders} in Task / Round / Reference Docs / Target Files / Output sections with context-specific content
DO choose code-reviewer agent_type for code reviews and general-purpose for plan / doc / artifact reviews
DO NOT paraphrase, summarize, or skip any protocol section
DO NOT pass file contents inline — the sub-agent reads via its own tool calls so it has a fresh context
DO NOT reference protocols by file path or tag name — the bodies are already embedded above
DO NOT introduce placeholder markers for the protocols — they must stay literally expanded

AI Mistake Prevention — Failure modes to avoid on every task:

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Assert the outcome your system owns, not the intermediate state your infrastructure owns. When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

Systematic Review Batching (map-reduce) — When a changeset is large, do NOT review files one-by-one. Partition into size-capped batches, fire one specialized sub-agent per batch in parallel, then reduce. This bounds EVERY context — each batch agent AND the orchestrator — so coverage stays complete as file count grows.

Trigger ladder (one ordered escalation — not competing thresholds):

< 10 changed files → sequential per-file review (default; no batching).

≥ 10 changed files → switch to systematic parallel mode. Announce: "Detected {N} changed files. Switching to systematic parallel review protocol." Then: categorize → size-capped batches → flat consolidation.

categories > 6 OR files > 40 → additionally insert the hierarchical synthesis tier (below). Everything from rung 2 still applies.

Step 1 — Categorize. Group changed files into logical categories derived from the project's actual structure (not forced). Category is the concern axis; orient with these examples, derive what fits the repository:

| Category Type | Example Groupings | | ------------------- | --------------------------------------------------------------------- | | Agent/Tooling | AI scripts, hooks, skill definitions, workflow configs, linting rules | | Root config/docs | Root README, project config, CI/CD pipeline configs | | Reference docs | Architecture docs, patterns references, setup guides | | Feature/domain docs | Business feature documentation, spec files, ADRs | | Backend logic | Service/handler/controller source (infer from project structure) | | Frontend logic | UI component/state/API source (infer from project structure) | | Data/Schema | Migrations, schema files, seed data | | Tests | Unit, integration, E2E test files | | Infrastructure | Docker, k8s, CI/CD, cloud manifests |

Step 2 — Size-capped batches. One sub-agent per batch of ≤8 files OR ≤2000 diff-lines, whichever hits first. Category stays the concern axis, but any category exceeding a cap splits into multiple size-capped batches (30 backend files → 4 batches). Size caps — not category caps — make "many files" safe: a category cap alone lets one giant category blow a single agent's context.

Step 2a — Sub-agent type per batch (match the batch's dominant concern):

Code logic (any stack) → code-reviewer

Security-sensitive changes → security-auditor

Performance-critical paths → performance-optimizer

Docs, plans, specs, configs, infra → general-purpose

Each batch sub-agent receives: its full file list; SYNC:category-review-thinking as its primary thinking model — derive each category's concerns from first principles, NOT a fixed checklist (if the consuming skill does not carry that block, apply category-first thinking directly); project reference docs relevant to its concern (discover via *patterns*, *conventions*, *style-guide*); cross-reference verification instructions (counts, tables, links). All batch agents run in parallel and write findings to plans/reports/ (per SYNC:task-tracking-external-report); reducers read from disk, never from memory.

Step 3 — Reduce.

Flat reduction (rung 2, ≤6 categories AND ≤40 files): the orchestrator collects each batch report, cross-references counts/tables/contracts ACROSS batches, detects gaps visible only across categories (feature in code but missing from docs; new API endpoint with no client call), and consolidates into one categorized holistic report.

Hierarchical reduction (rung 3, > 6 categories OR > 40 files): insert a mid-tier — each concern gets ONE synthesizer agent that reads only its own batch reports and emits a single concern-synthesis. The orchestrator reads the concern-syntheses (~5), never the raw batch reports — keeping the reducer's context O(#concerns), not O(#files).

Cross-concern interaction pass (mandatory at rung 3 — closes the synthesis-tier blind spot): concern-siloed synthesis can drop an interaction spanning two concerns AND two batches (tainted source in data-layer/batch 7 → sink in api/batch 3). So: (a) each concern-synthesizer MUST emit an explicit "cross-concern interaction candidates" list — entities/symbols/contracts it touched that plausibly bind to another concern (shared DTOs, event names, table/collection names, exported symbols); (b) the orchestrator MUST run the Step-3 cross-reference/gap step over those candidate lists across all concern-syntheses, not only within a batch, before concluding. Without this pass the tier trades completeness for context-bounding on exactly the large diffs it targets.

Step 4 — Holistic assessment. With all findings combined, judge: overall coherence as a unified intent; cross-category sync (docs match code? contracts match callers?); risk areas where categories interact; missing doc/spec updates for changed artifacts.

No silent truncation. If any cap forces sampling or a batch is dropped for budget, ANNOUNCE the dropped/sampled scope explicitly — bounded coverage must never read as complete coverage.

Severity Rubric — Classify every finding by consequence, not by how easy it is to fix. One scale across all reviews so a "High" means the same thing everywhere.

| Severity | Action | Definition | | -------- | ----------- | ------------------------------------------------------------------------- | | CRITICAL | Block merge | Silent runtime failure, data corruption, validation bypass, security hole | | HIGH | Must fix | Incorrect behavior, invariant gap, architectural violation | | MEDIUM | Should fix | Design debt, maintainability, likely future bug | | LOW | Nice to fix | Convention, documentation, minor clarity |

Score-based skills map their numeric scale onto these tiers — do not invent a parallel vocabulary:

0-2 criterion scoring (e.g. production-readiness-review): 0 = CRITICAL/HIGH (criterion unmet, blocks production readiness), 1 = MEDIUM (partial, should fix), 2 = pass (no finding).

Two-axis scoring (e.g. performance-review, impact × likelihood): map the resulting cell to the nearest tier — high-impact + high-likelihood → CRITICAL/HIGH; low-impact OR low-likelihood → MEDIUM/LOW.

A finding's tier drives the gate: CRITICAL/HIGH must be resolved or explicitly accepted by the owner before PASS; MEDIUM/LOW may ship with a tracked follow-up.

Category Review Thinking — A thinking framework for reviewing any category of changed files. NOT a fixed checklist — derive concerns from domain knowledge; the examples are starting points only. Your knowledge of the category exceeds any list here — trust it.

Step 1 — Understand the category's role. What is this category responsible for in the overall system? What invariants must it uphold? What are its consumer contracts (who depends on it, what do they expect)?

Step 2 — Read project conventions for this category. Search for reference docs, style guides, ADRs, or READMEs specific to this area. Grep 3+ existing similar files — extract naming conventions, structural patterns, shared base classes. If no docs exist, derive conventions empirically from existing code.

Step 3 — Derive concerns from first principles. Apply all that are relevant; expand beyond this list based on the actual category:

Correctness: Does the logic match the intent? Trace happy path AND error path.

Boundary contracts: Are interfaces/APIs/events/protocols honored? No implicit coupling introduced?

Project conventions: Does new code follow the patterns found in Step 2? Evidence-confirmed, not assumed.

Security: Auth enforced at every entry point? Input validated at boundaries? No secrets in the diff?

Performance: Unbounded operations? N+1 patterns? Blocking calls in async context? Unindexed queries?

Maintainability: DRY? Single responsibility? Complexity within reason? Names reveal intent?

Test coverage: Are the changed paths covered by tests? Are existing tests still valid after the change?

Documentation: Do related docs, specs, or READMEs reflect the changes?

Step 4 — Create sub-tasks and execute. For each identified concern: create a task tracking sub-task, work through it with file:line evidence, mark done. No findings without proof.

Illustrative concern examples by category type (not exhaustive — trust your knowledge beyond this):

Server-side logic: handler/service structure conventions, validation layer placement, side-effect isolation, cross-service boundary enforcement, data-access layer separation, error propagation strategy

Client-side logic: component lifecycle management, resource cleanup (subscriptions, listeners, timers), state management patterns, API integration layer separation, reactive stream composition

Data/Schema: migration reversibility (rollback script), lock impact on table volume, backfill idempotency, index coverage for query patterns, deployment ordering

Configuration: present in ALL environments? No secrets in diff? App fails fast if config missing (not silently null)? Documented in setup guide?

Infrastructure: dev/prod parity? No hardcoded dev values (localhost, debug flags)? Pinned image/dependency versions? CI/CD secret requirements documented?

Styles/Assets: follows project naming conventions? Uses design variables/tokens (no hardcoded magic values)? Correct scope (no global side effects from component styles)?

Documentation: accurate? Links valid? Examples still match current code/behavior? Covers new scenarios?

Tests: assertions verify specific outcomes (not just "no exception")? Idempotent (repeatable N times)? Covers edge cases, not just happy path?

Security artifacts: all code paths reach the gate? Negative tests exist (unauthorized denied)? Both enforcement AND display control updated?

Build/Tooling: rule changes apply consistently? No exceptions that silently swallow violations? Impact on CI runtime documented?

Scalability & Production-Readiness Technique Gate — CONDITIONAL, evidence-gated, scale-tiered. Judge which system-design techniques a system warrants at its scale — flag warranted-but-missing gaps AND advise AGAINST unwarranted heavyweight ones. ADVICE-ONLY: emit the matrix as guidance; NEVER mutate any score, verdict band, or gate pass/fail.

Derive the scale tier FIRST — from evidence, never assumed. Read users/RPS, SLO/latency targets, data volume, tenancy, topology from config/infra/specs; cite file:line + confidence. Tiers: T0 internal/single-instance · T1 small SaaS (<10k users) · T2 high-scale (10k–1M) · T3 massive/multi-region (millions+). Unknown tier → state assumption, do NOT default to T3.

Judge each concern group only at/above its warranting tier (member techniques → owning review skill for depth):

Traffic & Edge — Rate Limiting, Load Balancing, Reverse Proxy, API Gateway, CDN, Edge Caching, WAF, DDoS (T1+; CDN/WAF T2+) → security-review owns WAF/DDoS

Caching & Data Access — Caching, Cache Invalidation, DB Indexing, Query Optimization, N+1, Connection Pooling (T1+) → performance-review owns depth

Data Scaling & Consistency — Read Replicas, Sharding, Partitioning, Replication, CAP, Eventual Consistency, Locks, Leader Election (T2+; sharding/multi-region T3) → performance-review

Async & Messaging — Message Queues, Pub/Sub, Event-Driven, Saga, DLQ, Distributed Transactions, Backpressure, Webhooks, WebSockets/SSE (T2+)

Resilience — Circuit Breakers, Timeouts, Retries, Backoff, Idempotency, Health Checks, Liveness/Readiness, Failover, Graceful Degradation (T1+) → production-readiness-review

Scaling & Compute — Autoscaling, Horizontal/Vertical Scaling, Serverless Limits, Cold Starts, Cron Jobs, Thread Safety, GC/Memory Leaks (T1+; autoscaling T2+)

Deployment & Release — CI/CD, Docker, Kubernetes, Blue-Green/Canary/Rolling, Rollbacks, Feature Flags, IaC/Terraform/Helm, Build Caching (CI/CD T0+; K8s/canary T2+)

Observability — Monitoring, Logging, Distributed Tracing, Metrics, Alerting, SLOs/SLIs, Error Budgets (T1+; tracing/error-budgets T2+) → production-readiness-review

Security & Compliance — Secrets Management, IAM, OAuth, JWT Rotation, TLS, Encryption at Rest/Transit, CORS, CSRF, SQLi, XSS, SSRF (T0+) → security-review owns

DR & Infra — Backups, Disaster Recovery, Multi-Region, Chaos Engineering, Schema Versioning, DB Migrations, Cost Optimization (backups T1+; DR/multi-region/chaos T3) → production-readiness-review

Assign one of 4 verdicts per warranted technique: PRESENT · MISSING-WARRANTED (→ advise only — guidance, NOT a score/gate lever) · N/A-by-scale (below warranting tier) · OVER-ENGINEERED (present but unwarranted at this tier → advise AGAINST).

Anti-over-engineering guard (first-class): do NOT recommend K8s, sharding, multi-region, service mesh, event sourcing, or distributed transactions below their warranting tier. A correctly-lean small system is a PASS, never a gap.

Output — Technique Applicability Matrix: technique | tier-warranted? | present? | verdict | advice | evidence (file:line/config/infra). Full grouped catalog + per-tier baseline → .claude/docs/scale-technique-catalog.md. Hosting reviews surface this matrix WITHOUT changing any /20, /24, verdict band, or PASS/FAIL (per user decision 2026-07-06). Drift-guard: tier thresholds & per-technique warranting tiers are AUTHORITATIVE in .claude/docs/scale-technique-catalog.md — the inline tier summary above is a condensed pointer; on any tier/technique change, update the catalog FIRST, then re-run .claude/scripts/inject_scale_technique_gate.py to re-propagate this block.

BLOCKED until: - [ ] tier derived from evidence (not assumed) - [ ] matrix emitted - [ ] over-engineering guard applied - [ ] advisory-only (no score/verdict mutation) confirmed

Scenario Stress & Resilience Evaluation — CONDITIONAL, evidence-gated, business-criticality-aware. The top-down companion to SYNC:scale-technique-gate: instead of "is technique X present?", put the system UNDER concrete failure/load scenarios and judge whether it SURVIVES, SELF-HEALS, and whether its BUSINESS needs it to. ADVICE-ONLY: emit the Scenario Stress Matrix as guidance; NEVER mutate any score, verdict band, or gate pass/fail.

Reuse the scale tier derived by SYNC:scale-technique-gate (or derive it identically from evidence); also derive business-criticality B0–B3 from specs/SLA/product docs + the domain, cite file:line + confidence. B0 best-effort · B1 important · B2 business-critical · B3 mission-critical/regulated. Unknown → state the assumption, do NOT default to B3/T3. Criticality-signal floor (both-directions safety): regulated / PII / financial / health data, money movement, auth/identity, or legal-compliance scope raises B to at least B2 even absent SLA/SLO docs; anti-over-engineering lowers hardening ONLY when NO such signal is present. B (blast if it fails) and T (scale of load/data) are independent — a low-traffic payroll run is low-T, high-B.

Select in-scope scenarios — only those the system's B/T combination warrants (a B0 internal PoC skips region-loss/DR entirely; a B3/T0 regulated service still needs backups + DR by BUSINESS, not scale).

Walk each in-scope scenario: simulate the stimulus → trace the break path → name the failure signature → answer the self-heal/recovery question (auto-recover? MTTR? manual runbook?) → name the trade-off it forces. Families: traffic spike · sustained growth · data-volume growth · write/ingest burst · dependency down/slow · instance/node loss · zone/region loss · data loss/corruption · poison-message/retry-storm · cascading failure/backpressure · cold-start/deploy-blip · clock-skew/duplicate-delivery.

Assign one verdict per scenario: WITHSTANDS · DEGRADES-GRACEFULLY · FAILS-HARD (→ advise only) · N/A-by-business (not warranted → skip, not a gap) · OVER-HARDENED (resilience beyond business need → advise AGAINST, cite carrying cost).

Anti-over-engineering guard (first-class): a lean system whose business does not need HA/DR is a PASS; OVER-HARDENED flags resilience the business does not warrant. This guard is symmetric with the criticality-signal floor above — never under-harden a B2+ system just because its traffic is low.

Output — Scenario Stress Matrix: scenario | in-scope (B/T)? | verdict | self-heal | trade-off | evidence (file:line/config/infra). Full catalog + Business×Scale in-scope baseline + verdict/tier tables → .claude/docs/scenario-stress-catalog.md. ADVISORY-ONLY: NEVER mutate any /20, /24, verdict band, or gate pass/fail. Drift-guard: scenarios/verdicts/business-tiers are AUTHORITATIVE in the catalog — update it FIRST, then re-run .claude/scripts/inject_scenario_stress_gate.py. Scale tier stays single-sourced in scale-technique-catalog.md.

BLOCKED until: - [ ] scale tier + business-criticality (with criticality-signal floor) derived from evidence - [ ] in-scope scenarios selected - [ ] matrix emitted - [ ] over-hardening guard applied - [ ] advisory-only (no score/verdict mutation) confirmed

Goal Contract Satisfaction Loop — Persist the user goal in an external file, execute against it, and loop review/fix until every saved required criterion passes or a blocker escalates. Bounded closed loop — NEVER open-ended autonomous exploration.

Resolve the active goal (in order): active plan goal.md → plans/goals/{YYMMDD-HHmm}-{slug}/goal.md → create a new Goal Contract from the current user request (template: .claude/templates/goal-contract-template.md).

Required sections: Original Request, Purpose, Success Criteria (checkboxes; mark required vs optional), Constraints, Evidence Required, Iteration Log, Goal Satisfaction matrix.

Before work: read the active goal and map planned work to saved success criteria — execution serves the saved criteria, never chat memory alone.

After execution/verification: append an Iteration Log entry — result, evidence references (file:line, command output, report path), remaining gaps.

Review gate: emit a Goal Satisfaction matrix — | Success Criterion | Evidence | Status | with PASS/FAIL/BLOCKED. Overall PASS requires every required criterion PASS.

Loop rule (retry): required criterion FAIL → validate the gap is real → fix → re-review only the affected criteria. Stop cleanly when all required criteria PASS.

Escalation rule (stop): two consecutive iterations with no criterion progressing, or a blocker needing user input → mark the criterion BLOCKED with a user-facing reason and escalate. NEVER loop indefinitely.

Skip rule: tiny conversational tasks may skip the goal file ONLY with a recorded one-line reason. User-accepted gate skips are recorded in the goal file with reason and scope.

Security: NEVER store secrets, tokens, credentials, or private customer data in goal files — store evidence references and redact sensitive values.

Blocked until: active goal resolved (or skip reason recorded) · saved success criteria read before edits · iteration evidence appended after execution · Goal Satisfaction matrix emitted before any PASS verdict.

Trade-Off Interrogation Gate — ALWAYS ask these THREE questions before ANY verdict, score, finding, or recommendation — about the thing under review AND about every recommendation YOU make. — why: naming a benefit without its price is an endorsement, not a review; the costliest trade-offs are the ones nobody wrote down.

Is there any trade-off? Name what it SACRIFICES. "None" / "pure win" is an unfinished analysis, NOT an answer — to claim none, state which dimensions you checked and why each is unaffected: future change cost · complexity · performance/latency · memory/cost · coupling · reversibility · migration burden · operational load · blast radius · security posture · testability · team skill/ramp · delivery time · UX.

Is it worth it? Weigh gain against sacrifice EXPLICITLY — what is gained (with a metric) · what it costs · WHO pays · WHEN it comes due — then emit WORTH IT / NOT WORTH IT / UNCLEAR. "Better" with no metric and no cost FAILS this question. NOT WORTH IT → withdraw or replace the recommendation, never keep it as-is.

Is the trade-off material enough to CONFIRM WITH THE USER? A material trade-off is the user's call, never yours. MATERIAL when ANY holds: irreversible / one-way door (data migration, public contract, storage format, vendor lock-in) · cost shifted onto someone else (another team, ops/on-call, future maintainer, end user) · one quality attribute traded for another (correctness↔speed, security↔convenience, latency↔cost, simplicity↔flexibility) · a boundary crossed (client↔server tier, service contract, event contract, shared library) · a high-consequence path (auth, money, data integrity, breaking change, High/Medium residual risk) · the worth-it verdict is UNCLEAR.

MATERIAL → STOP and confirm by asking the user directly BEFORE the verdict stands — state the trade-off, both options, what each sacrifices, and your recommendation. NOT material → record it inline with a one-line justification and proceed.

Non-asking execution contexts — ESCALATE BY HANDOFF, never by silence. ask the user directly reaches only the main interactive agent: a sub-agent cannot ask the user, and a terminal/verdict-only mode asks nothing by design. When you are running in such a context, the obligation is redirected, never waived — do ALL of: (a) complete questions 1 and 2 normally; (b) decide materiality and record it in the Trade-Off Assessment row with confirmed? = NO — cannot ask from this context; (c) name the unconfirmed MATERIAL trade-off explicitly in your returned summary/verdict so the CALLER (or parent orchestrator) escalates it by asking the user directly on your behalf — a material trade-off mentioned only inside a report file on disk is NOT a handoff; (d) do not emit an unqualified PASS — mark the verdict as carrying an unconfirmed material trade-off, so the caller's gate stays closed until the user answers. The caller inherits the escalation duty the moment it reads your return.

This carve-out is about reachability, not convenience: it applies ONLY where the tool genuinely cannot reach the user (spawned sub-agent, terminal validate/verdict-only mode, non-interactive/headless run). It is NEVER a licence to skip the question, to self-approve a one-way door, or to downgrade materiality because asking is inconvenient — if you CAN ask, you MUST ask.

Emit a Trade-Off Assessment row per reviewed decision and per recommendation: | decision | sacrifices | gain (metric) | who pays, when | WORTH IT/NOT/UNCLEAR | material? | confirmed? |.

BLOCKED until: trade-off named (or dimensions-checked justification given) · worth-it verdict emitted · materiality decided · every MATERIAL trade-off either confirmed with the user OR — in a non-asking context — handed off in the returned verdict for the caller to confirm. A MATERIAL trade-off that is neither confirmed nor handed off can NEVER be PASS, and NEVER gets buried as a Low-severity note.

NEVER answer "no trade-off" without checking · decide a material trade-off silently on the user's behalf · let convergence/delivery pressure authorize walking through a one-way door · bundle several material trade-offs into one vague "proceed?".

MANDATORY IMPORTANT MUST ATTENTION execute the review loop (aka Self-Review Convergence Loop): review → validate findings → fix validated findings → full re-review. A complete review pass with zero findings ENDS the review. Any newly produced output/judgment gets ≥1 self-review; any new judgment gets ≥1 $why-review --validate-findings pass before it is treated as final.
MANDATORY apply the severity floor: rounds 1-2 exit on zero findings at any severity; from round 3 the bar is zero CRITICAL/HIGH/MEDIUM — LOW findings are no longer required to be fixed, so a LOW-only round ENDS the loop. List every deferred LOW in the report; NEVER re-tier a real CRITICAL/HIGH/MEDIUM down to LOW to reach the exit, and NEVER apply the floor to a binary gate (test-green, security must-fix).
MANDATORY enforce the round cap of 3 — a ceiling, NEVER a target: a clean pass ends the loop immediately at any round (round 1 included), and round 3 completing with CRITICAL/HIGH/MEDIUM still open → STOP & escalate by asking the user directly, never a silent PASS. The 2-repeated-no-progress blocker rule is an earlier exit — escalate at whichever trips first. NEVER loop open-ended.

IMPORTANT MUST ATTENTION run at least ONE graph command on key files before concluding (when graph.db exists).

IMPORTANT MUST ATTENTION cite file:line evidence for every claim. Confidence >80% to act, <60% do NOT recommend.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

MANDATORY Bootstrap task tracking before target work; transition one task at a time.
MANDATORY Persist plan/review findings to plans/reports/ incrementally and synthesize from disk.

MANDATORY Before investigating, planning, or coding, read docs/project-config.json (the project map: modules/paths, run-commands, conventions, architecture/workflow rules) + the required project-reference docs, and cite Reference docs read: ....
MANDATORY Always include lessons.md; project config + conventions override generic framework defaults.
MANDATORY If project config, root instruction files, or any required reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

MANDATORY Parent workflow rows do not replace child phase tracking; expand phases and link the parent when nested.
MANDATORY Orchestrators pre-expand child skill phases before invocation; use [N.M] $skill-name — phase prefixes and one-in_progress discipline.

MANDATORY Large changeset → batch by size cap (≤8 files OR ≤2000 diff-lines), one parallel sub-agent per batch; never review many files one-by-one.
MANDATORY > 6 categories OR > 40 files → add the hierarchical synthesis tier; each concern-synthesizer emits cross-concern interaction candidates and the orchestrator runs the cross-concern pass before concluding.

MANDATORY Classify findings Critical/High/Medium/Low by consequence; Critical/High block PASS until fixed or owner-accepted.
MANDATORY Score-based skills (sre 0-2, perf two-axis) map onto the same four tiers — no parallel severity vocabulary.

MANDATORY Derive review categories from file language + directory semantics + change nature; create a sub-task per category.
MANDATORY Derive each category's concerns from first principles with file:line evidence — never a fixed checklist.

IMPORTANT MUST ATTENTION scale-technique gate: derive the scale tier from evidence FIRST (T0 internal · T1 <10k · T2 10k–1M · T3 millions+), then judge each warranted technique PRESENT/MISSING-WARRANTED/N/A-by-scale/OVER-ENGINEERED. Advise on warranted-but-missing gaps AND advise AGAINST unwarranted heavyweight techniques (anti-over-engineering). ADVICE-ONLY — emit the Technique Applicability Matrix as guidance; NEVER mutate any score, verdict band, or gate pass/fail. Full catalog → .claude/docs/scale-technique-catalog.md (authoritative for tier thresholds & per-technique warranting tiers — on any change update the catalog FIRST, then re-run inject_scale_technique_gate.py).

IMPORTANT MUST ATTENTION scenario-stress gate: reuse the scale tier T0–T3 AND derive business-criticality B0–B3 from evidence first — apply the criticality-signal floor (regulated/PII/financial/health data · money movement · auth/identity · legal-compliance → at least B2 even absent SLA docs; do NOT default to B3). Select only the scenarios the B/T combination warrants, then walk each (simulate → trace → failure signature → self-heal/MTTR → trade-off) and assign WITHSTANDS/DEGRADES-GRACEFULLY/FAILS-HARD/N/A-by-business/OVER-HARDENED. Anti-over-engineering is first-class (a lean system that needs no HA/DR is a PASS) AND symmetric (never under-harden a B2+ system for low traffic). ADVICE-ONLY — emit the Scenario Stress Matrix as guidance; NEVER mutate any score, verdict band, or gate pass/fail. Full catalog → .claude/docs/scenario-stress-catalog.md (authoritative for scenarios/verdicts/business-tiers — on any change update the catalog FIRST, then re-run inject_scenario_stress_gate.py; scale tier stays single-sourced in scale-technique-catalog.md).

Prompt-Enhance Closing Anchors

IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval IMPORTANT MUST ATTENTION for every step/sub-skill call: set in_progress before execution, set completed after execution IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses

MANDATORY Resolve the active Goal Contract BEFORE work (active plan goal.md → plans/goals/{YYMMDD-HHmm}-{slug}/goal.md → create from current request) and read saved success criteria before editing.
MANDATORY Append iteration evidence after execution; emit a Goal Satisfaction matrix (PASS/FAIL/BLOCKED) before reporting PASS; loop on validated FAIL; escalate repeated no-progress or blockers. NEVER store secrets in goal files.

MANDATORY MUST ATTENTION ALWAYS ASK THE 3 TRADE-OFF QUESTIONS — on the thing under review AND on every recommendation you make: (1) is there any trade-off? name what it SACRIFICES (change cost · complexity · perf · coupling · reversibility · migration · ops load · blast radius · security · testability · delivery time · UX) — "none"/"pure win" is an unfinished analysis, so state the dimensions checked; (2) is it worth it? gain (with a metric) vs cost, WHO pays, WHEN → emit WORTH IT / NOT WORTH IT / UNCLEAR; NOT WORTH IT → withdraw or replace it; (3) is it material enough to confirm with the user? irreversible/one-way door · cost shifted onto another team/ops/maintainer/user · one quality attribute traded for another · a tier/service/event/library boundary crossed · auth/money/data-integrity/breaking-change/High-or-Medium-risk path · verdict UNCLEAR → STOP and confirm by asking the user directly BEFORE the verdict.
MANDATORY A MATERIAL trade-off with no user confirmation can NEVER be PASS; NEVER bury one as a Low-severity note, NEVER decide it silently, and NEVER let delivery or convergence pressure authorize a one-way door. — why: an un-walked-back one-way door is the user's call to make, not the reviewer's.
MANDATORY — non-asking contexts escalate BY HANDOFF, never by silence. ask the user directly reaches only the main interactive agent: a sub-agent cannot ask the user, and a terminal/verdict-only mode asks nothing by design. There the duty is REDIRECTED, not waived — still name the trade-off, still decide materiality, record confirmed? = NO — cannot ask from this context, state the unconfirmed MATERIAL trade-off in your RETURNED verdict/summary so the CALLER escalates it (a note only in an on-disk report is not a handoff), and never emit an unqualified PASS. Applies ONLY where the user is genuinely unreachable (spawned sub-agent, terminal validate mode, headless run) — if you CAN ask, you MUST ask.

Parallel Sub-Agent Dispatch — Plan parallelism the moment a task breakdown exists, BEFORE executing it — running provably independent tasks sequentially wastes wall-clock. Applies to every multi-step job: workflow steps, planning, batch updates, investigation, research, scans, reviews, doc sync. Plan execution is metadata-gated, NEVER default-parallel — fan-out follows ONLY what the plan declares (PAR/SEQ tags + per-phase write set); an untagged plan runs sequentially — why: a derived write set cannot see cascade or generated writes.

Tag every task PAR or SEQ. PAR = inputs exclude every pending task's output AND write set disjoint from every other PAR. Else SEQ — MUST ATTENTION name the dependency forcing it.

Group PAR into waves. No edge between members. Two writers of one file NEVER share a wave. Read-only work (search, investigation, review, research) parallelizes freely.

Declare before dispatch: Parallel plan: wave 1 = [...] · wave 2 = [...] · SEQ = [...] (reason).

Spawn each wave in ONE message — every spawn_agent call in one response, NEVER dripped per turn. Route each task to its specialist (.claude/skills/shared/sub-agent-selection-guide.md); NEVER code-reviewer as catch-all.

Brief each sub-agent self-contained: goal · scope + owned files · reference docs · return contract (summary + Full report: path, per SYNC:subagent-return-contract) · incremental persistence to plans/reports/ (per SYNC:incremental-persistence).

Barrier per wave. Advance ONLY after EVERY member returns (a skipped conditional counts as returned). Merge, mark each task completed/skipped, THEN dispatch the next wave. Mutating steps wait for the barrier.

One level deep. A dispatched sub-agent executes its own brief; further fan-out stays the orchestrator's job unless that agent's .claude/agents/*.md definition authorizes it.

NEVER parallelize: tasks sharing a write target · a task consuming a pending task's output · trivial single-file work (dispatch overhead > gain) · an order a skill or workflow explicitly fixes · gates awaiting user approval.

Blocked until: MUST ATTENTION every task tagged PAR/SEQ with a named reason per SEQ · waves declared + write-set disjointness checked · each wave spawned in ONE message · barrier honored before the next wave.

MANDATORY After planning tasks, tag each PAR/SEQ and spawn every PAR wave as parallel sub-agents in ONE message — default parallel for workflows, batch updates, investigation, research, reviews; plan execution fans out ONLY on what the plan declares.
MANDATORY Disjoint write sets per wave · all-return barrier before the next wave · specialist routing · sub-agents NEVER fan out further unless their own agent definition authorizes it.

Project Protocol Overlay — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the Target column of the project's skill-protocol index (docs/project-reference/skill-protocols-reference.md by default; a referenceDocs entry in docs/project-config.json overrides the path), taking the most specific matching tier ONLY — exact name > glob > *. That precedence orders overlays against EACH OTHER, never against this skill. Read ONLY the matched bodies, resolved as <protocols-dir>/<Name>.md; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: .claude/skills/project-skill-protocol/references/registry.md.

Overlays are ADDITIVE ONLY: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently.

MUST ATTENTION resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > *, which ranks overlays against each other, NEVER against this skill), read only matched bodies at <protocols-dir>/<Name>.md; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user.

Closing Reminders

IMPORTANT MUST ATTENTION Goal: Ensure service/API changes are production-ready for observability, reliability, data integrity, and database performance — score each dimension on service/API changes so working code that can be debugged, monitored, and rolled back ships, and operational technical debt does not.

IMPORTANT MUST ATTENTION — Main steps (execute in order, NEVER skip/merge): (1) Resolve scope (args else uncommitted git diff; backend service/API only, skip frontend/tests/docs/config-only) → (2) Score the 12 criteria 0-2 across the 4 dimensions (/24) → (3) Extended SRE Readiness gate — 8 pass/fail deploy/operate items; unaccepted CRITICAL/HIGH fail blocks PASS (gating, not scored, does not change /24) → (4) Map score + gate → verdict → (5) Structural Impact Analysis graph gate when graph.db exists → (6) Validated Fix + Full Re-Review loop on any finding → (7) Emit the SRE Review Results report with file:line evidence per score and per gate item — why: AI repeatedly forgets the graph gate and the re-review loop and stops at scoring.

IMPORTANT MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries; each is a signpost — the canonical body above governs, NEVER skip one):

Graph-Assisted Investigation: Run one graph command on key files before concluding.
Sub-Agent Return Contract: Sub-agents return only the summary; full report on disk.
Nested Task Creation: Child skills still create visible phase tasks under the parent.
Project Reference Docs Guide: Read required project docs first; lessons.md always.
Task Tracking & External Report: Bootstrap tasks; persist review findings to plans/reports/.
Critical Thinking Mindset: Apply critical + sequential thinking; no guess as fact.
Evidence-Based Reasoning: Cite file:line for every claim; confidence >80% to act.
Double Round-Trip Review: Review → validate → fix → full re-review; clean pass ends.
Fresh Context Review: Spawn fresh zero-memory sub-agent after fixes; never reuse.
Review Protocol Injection: Embed all 11 protocol bodies verbatim in sub-agent prompts.
AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
Systematic Batching: ≥10 files → size-capped parallel batches, then reduce.
Severity Rubric: Classify Critical/High/Medium/Low by consequence; map 0-2 scores onto it.
Category Review Thinking: Derive each category's concerns from first principles, not a checklist.
Scale-Technique Gate (advisory): Derive scale tier from evidence, emit the Technique Applicability Matrix as guidance — NEVER mutate the /24, the {n}/8 gate, or the verdict.
Parallel Sub-Agent Dispatch: Tag tasks PAR/SEQ, group PAR into disjoint-write-set waves, spawn each wave in ONE message, barrier before advancing.

IMPORTANT MUST ATTENTION every score requires file:line evidence — unprovable score = 0; assume the worst without proof — why: an unverified "looks fine" is how silent operational gaps reach production. IMPORTANT MUST ATTENTION the DB Performance Protocol, graph gate, and validated-fix full re-review are NEVER skippable regardless of change size — VERDICT is advisory, these process steps are not — why: small changes are exactly where unbounded queries and missing re-reviews slip through. IMPORTANT MUST ATTENTION validate findings BEFORE any fix, then rerun the FULL review (fresh sub-agent, zero prior-round memory) before declaring PASS — a clean pass ENDS the loop — why: every fix invalidates the prior verdict.

The following are all MANDATORY:

MANDATORY break work into small todo tasks via task tracking BEFORE starting; mark one in_progress, complete it immediately after evidence — why: untracked review steps get silently merged or skipped.
MANDATORY read required project-reference docs first (code-review-rules.md, backend-patterns-reference.md, domain-entities-reference.md, always lessons.md) and cite Reference docs read: ... — why: project conventions override generic SRE assumptions.
MANDATORY grep 3+ existing patterns for the changed area (base handlers, base-controller error handling, paging/index helpers) and verify pattern fit before scoring — why: closest example ≠ matching preconditions; a paging helper may not apply to this query's lifetime/scope.
MANDATORY every score, finding, and recommendation carries file:line proof + confidence (>80% to act, <80% verify first) — NEVER score from inference — why: scoring without trace is the #1 false-PASS source.
MANDATORY ALL list queries MUST paginate (no unbounded GetAll/ToList/Find without Skip/Take or cursor); ALL filter fields, foreign keys, and sort columns MUST have matching indexes — score 0 until each is proven.
MANDATORY run at least ONE graph command on key files before concluding when .code-graph/graph.db exists (blast-radius, tests_for, downstream trace) — why: the HARD-GATE catches cross-service consumers grep alone misses.
MANDATORY when batched (≥10 files), RE-SCORE all 12 criteria holistically from combined cross-batch evidence — NEVER average per-batch scores — why: a cross-file criterion (query in one batch, migration in another) false-flags 0 per-batch.
MANDATORY changed core logic clears the MUTATION-SCORE gate, not a coverage %; every behavior-changing finding feeds BOTH the spec (name the contract/invariant in §8) AND a guarding test — a code-only fix is INCOMPLETE.
MANDATORY validate decisions with the user by asking the user directly for workflow/next-step routing — never auto-decide.

Anti-Rationalization:

| Evasion | Rebuttal | | --------------------------------------------- | -------------------------------------------------------------------------------------------- | | "Fix was small, skip re-review" | NEVER — fixes changed the target; validate findings, then rerun the FULL review before PASS | | "Small change, skip graph gate" | HARD-GATE applies regardless of size — run one graph command before concluding | | "No explicit paging but it looks fine" | Score 0 until proven with file:line. Assume worst without evidence | | "Already checked observability" | Show file:line proof. No proof = no check | | "VERDICT is advisory so skip MANDATORY steps" | Advisory = VERDICT only. Graph gate, validated-fix re-review, DB Protocol are NEVER advisory | | "Score it from what I remember of the code" | Re-read and cite file:line; inference is not evidence — unprovable = 0 | | "Batched, so average the per-batch scores" | Re-score all 12 holistically from combined evidence; per-batch sees ≤8 files and false-flags | | "Tests pass, mutation gate is covered" | Green coverage over un-asserted behavior fails the gate; a surviving mutant is a blocker |

IMPORTANT MUST ATTENTION every score needs file:line evidence or it is 0; assume worst without proof. IMPORTANT MUST ATTENTION DB Performance Protocol + graph gate + validated-fix full re-review are NEVER skippable regardless of change size. IMPORTANT MUST ATTENTION validate findings before fixing, then rerun the FULL review before PASS — a clean pass ENDS the loop.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/.ck.json + .claude/skills/shared/sync-inline-versions.md (:full blocks) + .claude/scripts/lib/hookless-prompt-protocol.cjs

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there. For spec, test-case, behavior-change, public-contract, or docs/specs/ work, route through the local spec docs named by the docs index: feature-spec-reference.md, spec-system-reference.md, spec-principles.md, and workflow-spec-test-code-cycle-reference.md when specs/tests/code must stay synchronized. If either file or a required reference doc is missing or stale, auto-run $project-init (or the narrow lower-level route such as $project-config, $docs-init, $scan-all, or $scan --target=<key>) before ordinary project-specific work. Any supported AI tool may execute when this shared context and local docs are available.

DETECT: If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
ACTIVATE: For a selected workflow, call $start-workflow <workflowId>; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
PARALLELIZE: Before executing the task list, tag each task PAR (independent inputs + write set disjoint from every other PAR task) or SEQ (name the blocking dependency), group PAR tasks into waves, declare the wave plan, and spawn each wave's sub-agents in ONE message — all-return barrier per wave, fan-out one level deep unless a sub-agent's own definition authorizes further fan-out. Sequential-by-default is a defect when tasks are independent; do not parallelize shared write targets, output-consuming tasks, trivial single-file work, ordering a skill or workflow explicitly fixes, or user-approval gates.
EXECUTE: Advance per the Workflow Step Advancement & Parallel Phases rule in your context instructions — model-driven; a sub-agent completion advances a step identically to an inline call; a parallel-phase group is an all-return barrier (advance only after ALL members return, never serialize it)

Shared AI-SDD Protocol Markers

Source: .claude/skills/shared/sync-inline-versions.md

SYNC:ai-sdd-artifact-contract

AI-SDD Artifact Contract — Shared spec-driven development rules stay portable and source-owned.

Keep reusable AI-SDD principles in .claude; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.

Preserve cycle: spec -> plan -> tasks -> implement -> verify -> update spec/docs.

Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.

Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.

Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.

Update .claude source first, then sync generated mirrors; do not manually edit .agents, .codex, or AGENTS.md. — why: mirrors are generated artifacts; hand-edits are overwritten on the next sync

If docs/project-config.json, root instruction files, or a required project-reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

Active reference: shared/sdd-artifact-contract.md in the active skills root.

SYNC:ai-sdd-artifact-contract:reminder

MANDATORY Apply shared/sdd-artifact-contract.md; keep reusable AI-SDD in .claude and local rules in project docs.
MANDATORY Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
MANDATORY Update .claude source before syncing generated mirrors; do not manually edit .agents, .codex, or AGENTS.md.
MANDATORY Missing or stale project config, root instruction files, or required reference docs route project-specific work through $project-init or the narrow setup route automatically. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
Auto-fix gate: "Could $code-review/$code-simplifier/$security-review/$lint catch this?" — Yes → improve review skill instead.
BOTH gates pass → ask user to run $learn. [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

Common AI Mistake Prevention (System Lessons)

Re-read files after context compaction. Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
Grep for old terms after bulk replacements. AI over-trusts find/replace completeness. Grep full repo after bulk edits for missed refs in docs/configs/catalogs.
Check downstream references before deleting. Deletions cascade doc/code staleness. Map referencing files before removal.
After memory loss, check existing state before creating new. Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
Verify AI-generated content against actual code. AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
Trace full dependency chain after edits. Changing a definition misses downstream consumers. Trace the full chain.
When renaming, grep ALL consumer file types. Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
Trace ALL code paths when verifying correctness. Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
Update docs that embed canonical data when source changes. Docs inlining derived data (workflows, schemas, configs) go stale silently. Update all embedding docs alongside source.
Verify sub-agent results after context recovery. Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
Cross-check full target list against sub-agent assignments. Parallel sub-agents by category miss boundary items. Reconcile union of assignments against target list before proceeding.
Sub-agents inherit knowledge only from their agent .md definition — use custom agent types, not built-in Explore. Tool adoption = permission + knowledge + enforcement (numbered workflow step).
Persist sub-agent findings incrementally, not as a final batch. Long sub-agents hit cutoffs before final write — findings lost. Instruct append-per-section to report file.
When debugging, ask "whose responsibility?" before fixing. Trace caller (wrong data) vs callee (wrong handling). Fix at responsible layer — never patch symptom site.
Test failure → record a provisional verdict before trace/edit, then investigate. Use the full five-way taxonomy: SOURCE-WRONG (production violates intent), TEST-WRONG (assertion/setup is stale), TEST-NOT-OPTIMAL (valid but fragile or low-signal test), ENVIRONMENT-BLOCKED (external state prevents a verdict), or AMBIGUOUS (intent/evidence cannot choose safely). Then trace root cause and triangulate against the governing spec (docs/specs/** if one exists) AND source. NEVER weaken an assertion, add a skip, relax a timeout, or change source merely to force green.
Grep ALL removed names after extraction/refactoring. Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Pattern-matching as "wrong" skips context. Before changing or reporting any constant/limit/flag/cutoff: read comments, git blame, the CALLER's ordering (the guarantee that makes the value correct usually lives in code running immediately BEFORE the cited line), and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard — and in a validation pass, an accurate file:line citation proves the transcription, never the defect.
Verify ALL affected outputs, not just the first. One build green ≠ all green. Multi-stack changes (backend/frontend/tests/docs) require verifying EVERY output.
Evaluate fit before copying a nearby pattern. Closest example ≠ matching preconditions — verify the new context shares the same constraints, base classes, scope, lifetime.
Holistic-first debugging — resist nearest-attention trap. Don't dive into first plausible cause. List EVERY precondition (config, env vars, paths, DB, endpoints, creds, versions, DI, data). Verify each against evidence (grep/query — not reasoning). Ask "what would falsify this?" — if nothing, it's not a hypothesis. Most expensive failure: going deeper in "obvious" layer while bug sits in layer never questioned.
Surgical changes — apply the diff test (context-aware). Two modes: (1) Bug fix → every line traces to the bug; no restyling; orphan cleanup only for imports YOUR changes made unused. (2) Review/enhancement → implement improvements AND announce as "Enhancement beyond main request: [what]". Never silently scope-creep. Diff test: "Would this line exist if I wasn't asked to do X?" — if no, delete or announce.
Surface ambiguity before coding — don't pick silently. Multiple valid interpretations → present each with effort: "[Request] could mean (1) [N h], (2) [N h]. Which matters?" List scope/format/volume/constraints assumptions first. If simpler path exists, say so. Never silently pick.
[MANDATORY FIRST ACTION] ALWAYS activate a suitable skill or workflow BEFORE responding. Match task against workflow catalog + skill list; invoke via skill invocation or $start-workflow <workflowId>. NEVER answer or write code before checking. Skip = protocol violation.
Why-Review adversarial mindset — apply when reviewing any plan, decision, or design. Default SKEPTIC not VALIDATOR: steel-man a rejected alternative, invert each stated reason ("what does it sacrifice?"), stress-test top 2-3 assumptions, run pre-mortem ("ships, fails in 3 months — what breaks?"), surface 1-2 alternatives author missed. Section presence ≠ quality; quality = causal reasoning + concrete mitigations + evidence, not "it's better" or "monitor closely".
Front-load report-write in sub-agent prompts for large reviews. Many-file sub-agents hit budget before final write — findings lost. Design prompts so: (1) report-write is first explicit deliverable, (2) append per-file/section (not batched), (3) scope bounded so reads don't exhaust budget. Truncated mid-sentence with no report file → spawn narrower scope, don't retry same prompt.
After context compaction, re-verify all prior phase outcomes before continuing. Summaries describe intent, not environment state (git index, filesystem, processes). On resume, FIRST audit: git status, re-read modified files, verify filesystem. Every "completed" claim is an untested hypothesis until evidence confirms.
OOM/memory: check row count before row size. Triage: (1) Unbounded query — no DB filter for trigger? Push filter to DB; eliminates OOM. (2) Large rows? Projection reduces proportionally. Row reduction > projection in ROI.
Assert the outcome your system OWNS, never the intermediate state your INFRASTRUCTURE owns. When testing anything asynchronous (queue/broker delivery, retries, background jobs, caches, replication), assert the final business/entity state. NEVER assert the delivery bookkeeping — consume/send status, attempt counts, last-error, row existence or counts in a broker, scheduler, or outbox/inbox table. That bookkeeping lives in shared infrastructure that ANY co-running process (a peer worker, a second replica, a leftover local container) can write, usually under a deterministic shared key, so the assertion silently tests the developer's environment instead of the system: green when run alone, flaky the instant anything else shares that broker + database. Gate question for every assertion: "would this hold no matter WHICH process did the work?" — if no, assert the converged data state instead. Corollary: process-local fault injection and in-process telemetry cannot gate work any process may perform — use them as stress amplifiers (arm → bounded window → disarm → assert convergence), never as preconditions.
Keep domain concepts out of generic/shared/infrastructure layers. Reusable layer (shared library, framework, infra module) must reference NO consumer-specific domain concept — tenant/customer/product IDs, business entities, feature rules. Leak compiles + runs → passes review silently while coupling the "reusable" layer to one consumer. Keep shared type domain-free; push domain fields/logic down into the consumer via subclass/composition. — why: a layer coupled to one consumer's domain is no longer reusable.

Agent Skills: production-readiness-review

Install this agent skill to your local

Skill Files