Agent Skills: dart-ultrawork

dart-ultrawork

Use this skill in Codex to run the DART dart-ultrawork workflow. The editable workflow source currently lives in .claude/commands/, and this generated Codex skill is a first-class Codex entrypoint.

Invocation

• Claude Code/OpenCode: /dart-ultrawork <arguments>
• Codex: $dart-ultrawork <arguments>

Treat the text after the skill name as $ARGUMENTS. When the workflow references $1, $2, etc., map those to the positional values supplied by the user.

Command Body

Start a team-scale or autonomous DART task: $ARGUMENTS

Required Reading

@AGENTS.md @docs/ai/principles.md @docs/ai/north-star.md @docs/ai/orchestration.md @docs/ai/sessions.md @docs/ai/verification.md @docs/dev_tasks/README.md

Arguments

$ARGUMENTS is a task brief plus optional mode flags:

• mode=interview: ask one up-front batch of critical questions.
• mode=brief: treat provided context as sufficient unless escalation applies.
• mode=resume: start from the existing docs/dev_tasks/<task>/ project home and run the session-start protocol before changing files.
• interview=skip: skip maintainer questions only when the brief already answers all consequential decisions.

The brief may be prose or a structured TASK / CONTEXT block. Extract north star, deliverable, acceptance criteria, constraints, risks, references, paths, issues/PRs/branches, commands, and first step when present.

Workflow

Own understanding, decomposition, sequencing, review, and honest evidence for the whole task. Delegate only when the user explicitly requested it and the current surface permits it; otherwise execute packets serially. Use dart-new-task for bounded single-session work unless the user asked for the autonomous project-home loop.

A work packet is the unit of handoff: one packet = one branch = one verification story, with an objective, scope, non-goals, acceptance evidence, and gates named before execution starts. An executor who finds the real scope materially different stops and reports back.

1. Session start and current reality - Locate the project home. For DART 6 autonomous projects this is docs/dev_tasks/<task>/, not a parallel project directory. If it exists, read its README.md, RESUME.md, and any autonomous sidecars such as decisions.md, verification.md, or progress-log.md; then verify checkout state, current branch, and any branch/PR evidence named by the docs. If the docs are stale, update the handoff/current-reality note before relying on them. If no project home exists and the task is multi-session, team-scale, design-heavy, risky, or explicitly autonomous, create docs/dev_tasks/<task>/ before implementation. If prior work exists elsewhere, first absorb or summarize it into the project home.
2. Understand and scout - Restate the north star, final deliverable, acceptance criteria, quality bar, non-goals, constraints, and risks. Scout the territory first with named docs/code, read-only searches, a dart-analyze pass, or a focused read-only scout (dart_scout when running in Codex). Load docs/plans/dashboard.md for roadmap routing, docs/information-architecture.md for durable placement, and the relevant onboarding owner docs only when those phases apply. Draft a candidate decomposition privately before asking anything.
3. Interview decisions; self-resolve uncertainties - Ask at most one up-front batch of critical questions. Escalate before destructive operations, history rewrites, irreversible migrations, meaningful cost, security/credential/secret handling, legal or privacy-sensitive decisions, major product-direction choices not covered by the brief, conflicts with stated constraints, or any assumption whose wrong answer could cause significant harm. If input is unavailable, choose the safest reversible path, document the assumption, and continue only with non-blocked work. Then split consequential unknowns:
   • Maintainer decisions: preference, scope, public API, release, quality-bar, or roadmap calls that evidence cannot settle. Ask the human now in one batched interview (focused questions with 2-4 concrete options each, recommendation first). Do not start large work while a consequential decision is open. Skip this discretionary interview when mode=brief; also skip when interview=skip and the prompt already answers everything consequential. In both cases, still follow the escalation rules above.
   • Evidence-resolvable uncertainties: anything a focused A/B test, benchmark, throwaway spike, reference lookup, or blind-spot review can settle. Do not ask the human; schedule these as spike/research packets and record the method and result as evidence.
4. Create or refresh the tracking surface - Populate the project home with value, north star, deliverable, scope, non-goals, assumptions, risks, acceptance evidence, gates, dependencies, milestone, next actions, and blockers. Claim-dependent physics/simulation, collision/contact, model, OSG, and visual-example work routes through dart-verify-sim: require a text oracle plus assessed visual/debug evidence, or a justified replacement. Keep RESUME.md as the handoff; add decisions.md, verification.md, and progress-log.md sidecars when they improve resumability or evidence.
5. Set the goal contract - Express done-when as verifiable outcomes (files, tests, gates, artifacts). When the session supports a goal or stop-hook mode (for example /goal in Claude Code), set it to this contract so orchestration cannot stop early or loop forever. Stop once the acceptance criteria are satisfied, verification is recorded, docs are current, known gaps are documented, and unnecessary work has been removed or deferred. Every delegated packet gets its own contract: GOAL (one sentence), DONE WHEN (verifiable), EVIDENCE (what to record), RISKS, and NEXT STEP.
6. Decompose and route - Cut work packets per the contract above and execute serially by default. When the user explicitly requested delegation, use the read-only dart_scout for bounded discovery, dart_reviewer for current-state review, and dart_release_auditor for reference comparison. Assign the same contracts to role-separated sessions in other clients. Implementation stays with the parent or a scoped executor. Use parallel writers only with explicit, disjoint ownership.
7. Run the autonomous work/review cycle - For each meaningful chunk: plan, execute, verify, then run an independent/specialized review lane. Treat review findings as hypotheses: investigate, fix or record no-fix evidence, clean up, re-verify, and re-review. A packet is not done until the current post-fix state has at least two clean review passes recorded.
8. Supervise and steer - Monitor progress; unblock, reassign, or re-cut packets on scope mismatch. Workers return Task, Summary, Files changed, Evidence/tests, Risks, and Recommended next step. Use Codex from Claude, Claude from Codex, subagents, or specialist reviewers when available; fall back to role-separated local review only when unavailable. Root-cause failures and fold newly discovered unknowns back into step 3.
9. Update docs at each stopping point - Every meaningful cycle updates the project home: README.md for status/plan/risks, RESUME.md for the next fresh-session handoff, decisions.md if decisions changed, verification.md if checks ran or gaps were found, and progress-log.md for completed chunks when that sidecar exists. Keep docs current enough for a zero-context session to resume without hidden chat memory.
10. Version-control and closeout - Keep commits and PRs coherent: separate feature work, bug fixes, refactors, docs, experiments, and AI-infra changes when practical; review the diff, remove unrelated changes, make the changelog decision, and run pixi run lint before commits. Run task-specific gates from docs/ai/verification.md, record evidence per packet, and complete the principle audit. Load docs/onboarding/contributing.md, docs/onboarding/changelog.md, and docs/onboarding/ai-tools.md for version-control or external closeout. A project is complete only when the north star and acceptance criteria are met, verification evidence is recorded, docs are current, known gaps are documented, unnecessary work is removed or deferred, and final state is summarized in RESUME.md or a durable owner. Promote durable artifacts out of docs/dev_tasks/<task>/ and remove the folder in the completing PR. GitHub mutations only with explicit maintainer/user approval.

Prompt Shape

Use an outcome-first brief. Do not repeat this workflow's logistics or required reading in the task prompt; the capability loads them.

TASK: <one-sentence objective>

Done when:
- <verifiable outcome: a file, test, gate, benchmark, or artifact>
- <verifiable outcome>

Constraints/evidence:
- <task-specific must/never rules and owner references>
- <known risks, branch/PR facts, or required comparison>

Put this brief after /dart-ultrawork or $dart-ultrawork. When goal mode is available, make the same Done when list the goal contract.

Output

• Interview record, uncertainty-resolution evidence, and project-home path
• Packet list, routing, goal contracts, gates, and review-loop status
• Per-packet evidence, GUI/demo artifacts when relevant, and updated docs
• Principle audit, cleanup status, and approved external mutations