Agent Skills: Diagnosing Bugs

Diagnosing Bugs

Build a reliable symptom check, then use evidence to isolate and fix the cause. Adapt the investigation to the failure; keep the reproduction and verification requirements.

Use relevant sections of CONTEXT.md and nearby ADRs when module boundaries or past decisions affect the investigation.

Phase 1 — Build a feedback loop

This is the skill. Everything else is mechanical. If you have a tight pass/fail signal for the bug — one that goes red on this bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.

Prioritize a check that distinguishes the reported symptom from setup errors.

Choose a loop that reaches the symptom

1. Failing test at whatever seam reaches the bug — unit, integration, e2e.
2. Curl / HTTP script against a running dev server.
3. CLI invocation with a fixture input, diffing stdout against a known-good snapshot.
4. Headless browser script (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network.
5. Replay a captured trace. Save a real network request / payload / event log to disk; replay it through the code path in isolation.
6. Throwaway harness. Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.
7. Property / fuzz loop. If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
8. Bisection harness. If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can git bisect run it.
9. Differential loop. Run the same input through old-version vs new-version (or two configs) and diff outputs.
10. HITL bash script. Last resort. If a human must click, drive them with scripts/hitl-loop.template.sh so the loop is still structured. Captured output feeds back to you.

Prefer the smallest loop that exercises the actual failure path.

Tighten the loop

Treat the loop as a product. Once you have a loop, tighten it:

• Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.)
• Can I make the signal sharper? (Assert on the specific symptom, not "didn't crash".)
• Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.)

A 30-second flaky loop is barely better than no loop; a 2-second deterministic one is tight — a debugging superpower.

Non-deterministic bugs

For intermittent bugs, record trial counts, failure rates, and timing conditions. Use stress or repeated trials when they improve the signal; choose enough trials to compare baseline and fix rather than imposing a fixed failure-rate threshold.

When you genuinely cannot build a loop

Stop and say so explicitly. List what you tried. Ask the user for: (a) access to whatever environment reproduces it, (b) a captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Continue useful code or artifact inspection while collecting missing evidence; label hypotheses as unverified and do not claim a fix without an adequate check.

Completion criterion — a tight loop that goes red

Phase 1 is done when the loop is tight and red-capable: you can name one command — a script path, a test invocation, a curl — that you have already run at least once (paste the invocation and its output), and that is:

• [ ] Red-capable — it drives the actual bug code path and asserts the user's exact symptom, so it can go red on this bug and green once fixed. Not "runs without erroring" — it must be able to catch this specific bug.
• [ ] Deterministic — same verdict every run (flaky bugs: a pinned, high reproduction rate, per above).
• [ ] Focused — avoids unrelated setup where practical; slower end-to-end checks are valid when the symptom requires them.
• [ ] Agent-runnable — you can run it unattended; a human in the loop only via scripts/hitl-loop.template.sh.

Read the relevant code when needed to construct the loop. Use the loop to test theories before committing to a fix.

Phase 2 — Reproduce + minimise

Run the loop. Watch it go red — the bug appears.

Confirm:

• [ ] The loop produces the failure mode the user described — not a different failure that happens to be nearby. Wrong bug = wrong fix.
• [ ] The failure is reproducible across multiple runs (or, for non-deterministic bugs, reproducible at a high enough rate to debug against).
• [ ] You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix actually addresses it.

Minimise

Once it's red, shrink the repro to the smallest scenario that still goes red. Cut inputs, callers, config, data, and steps one at a time, re-running the loop after each cut — keep only what's load-bearing for the failure.

Why bother: a minimal repro shrinks the hypothesis space in Phase 3 (fewer moving parts left to suspect) and becomes the clean regression test in Phase 5.

Stop minimizing when the repro is small enough to discriminate causes reliably; proving every remaining element indispensable is unnecessary.

Phase 3 — Hypothesise

State evidence-backed hypotheses and their predictions. Compare alternatives when evidence is ambiguous; do not manufacture a fixed number when the cause is already constrained.

Each hypothesis must be falsifiable: state the prediction it makes.

Format: "If <X> is the cause, then <changing Y> will make the bug disappear / <changing Z> will make it worse."

If you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it.

Show the ranked list to the user before testing. They often have domain knowledge that re-ranks instantly ("we just deployed a change to #3"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it — proceed with your ranking if the user is AFK.

Phase 4 — Instrument

Each probe must map to a specific prediction from Phase 3. Change one variable at a time.

Tool preference:

1. Debugger / REPL inspection if the env supports it. One breakpoint beats ten logs.
2. Targeted logs at the boundaries that distinguish hypotheses.
3. Never "log everything and grep".

Tag every debug log with a unique prefix, e.g. [DEBUG-a4f2]. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die.

Perf branch. For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, performance.now(), profiler, query plan), then bisect. Measure first, fix second.

Phase 5 — Fix + regression test

Write the regression test before the fix — but only if there is a correct seam for it.

A correct seam is one where the test exercises the real bug pattern as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence.

If no correct seam exists, that itself is the finding. Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase.

If a correct seam exists:

1. Turn the minimised repro into a failing test at that seam.
2. Watch it fail.
3. Apply the fix.
4. Watch it pass.
5. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario.

Phase 6 — Cleanup + post-mortem

Required before declaring done:

• [ ] Original repro no longer reproduces (reuse the Phase 5 result if nothing relevant changed)
• [ ] Regression test passes (or absence of seam is documented)
• [ ] All [DEBUG-...] instrumentation removed (grep the prefix)
• [ ] Throwaway prototypes deleted (or moved to a clearly-marked debug location)
• [ ] The hypothesis that turned out correct is stated in the commit / PR message — so the next debugger learns

Report unresolved architectural limits when they affect confidence. Do not automatically start a separate architecture audit after the requested fix is verified.