Debug

Debug

Read enough code, tests, and logs to identify the reported behavior and the smallest useful check.

When exploring the codebase, read CONTEXT.md (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.

Redact

This skill has you show commands, outputs and captured artifacts. Redact every secret first — write <REDACTED> in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal.

If the redacted output is not enough to diagnose the bug, say so and ask the user.

Phase 1 — Build a feedback loop

Build a check that distinguishes the reported failure from correct behavior. Initial code inspection and provisional hypotheses help choose that check; they are not proof of the cause. Prefer an existing focused test over a new harness.

Ways to construct one — try them in roughly this order

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.

Run the check before changing the implementation when the environment permits it.

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

The goal is not a clean repro but a higher reproduction rate. Loop the trigger 100×, parallelise, add stress, narrow timing windows, inject sleeps. A 50%-flake bug is debuggable; 1% is not — keep raising the rate until it's debuggable.

When you genuinely cannot build a loop

State what you tried and what prevents reproduction. Continue useful source or log analysis, but label its conclusions as provisional. Ask for missing access, a redacted artifact, or instrumentation approval only when it blocks the next useful check. Do not claim a verified fix without evidence from the failing path.

Completion criterion — a tight loop that goes red

Runtime reproduction is established when you can name a command you have run (show its output, redacted) 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).
• Fast — seconds, not minutes.
• Agent-runnable — you can run it unattended; a human in the loop only via scripts/hitl-loop.template.sh.

Until then, keep investigation findings separate from reproduction evidence.

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 reducing the reproduction when it isolates a testable cause. Do not spend time removing every input from an already decisive test. If reproduction is unavailable, retain that limitation when proceeding with source analysis.

Phase 3 — Hypothesise

Start with the cause best supported by the evidence. When several causes remain plausible, rank them and choose a check that distinguishes them. One clear cause does not require invented alternatives.

Each hypothesis must be falsifiable — state the prediction it makes, or discard it as a vibe.

Format: "If is the cause, then will make the bug disappear / will make it worse."

Share competing explanations when the user's context could change the next check. Otherwise proceed with the focused test and report what it establishes.

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], so cleanup at the end is a single grep.

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: the codebase architecture is preventing the bug from being locked down. Flag it 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 (re-run the Phase 1 loop)
• 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

Then ask: what would have prevented this bug? If the answer involves architectural change (no good test seam, tangled callers, hidden coupling), hand the specifics to the improve-codebase-architecture skill. Make the recommendation after the fix is in, not before — you have more information now than when you started.