Diagnosing Bugs

A discipline for hard bugs. Skip phases only when explicitly justified.

When exploring the codebase, read GLOSSARY.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 in your report instead of guessing.

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.

Spend disproportionate effort here. Be aggressive. Be creative. Refuse to give up.

Ways to construct one, in roughly this order

1. Curl / HTTP script against a running dev server.
2. CLI invocation with a fixture input, diffing stdout against a known-good snapshot.
3. Headless browser script (Playwright / Puppeteer) that drives the UI and asserts on DOM/console/network.
4. Replay a captured trace. Save a real network request / payload / event log to disk; replay it through the code path in isolation.
5. 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.
6. Property / fuzz loop. If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
7. 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.
8. Differential loop. Run the same input through old-version vs new-version (or two configs) and diff outputs.

Build the right feedback loop, and the bug is 90% fixed.

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 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, so keep raising the rate until it's debuggable.

When you genuinely cannot build a loop

Stop and report to whoever dispatched you (the orchestrator, or the user in the main session). List what you tried and what you need: (a) access to whatever environment reproduces it, (b) a redacted captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Do not proceed to hypothesise without a loop.

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 CLI invocation, a curl) that you have already run at least once (show the invocation and its output, redacted), 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).
• Fast: seconds, not minutes.
• Agent-runnable: you can run it unattended, with no human in the loop.

If you catch yourself reading code to build a theory before this command exists, stop: jumping straight to a hypothesis is the exact failure this skill prevents. No red-capable command, no Phase 2.

Phase 2: Reproduce + minimise

Run the loop. Watch it go red as 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, and 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).

Done when every remaining element is load-bearing: removing any one of them makes the loop go green.

Do not proceed until you have reproduced and minimised.

Phase 3: Hypothesise

Generate 3–5 ranked hypotheses before testing any of them. Single-hypothesis generation anchors on the first plausible idea.

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.

Put the ranked list in your report. In the main session, show it to the user before testing: they often have domain knowledge that re-ranks it instantly, or know hypotheses already ruled out. Don't block on it; proceed with your ranking.

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

1. Turn the minimised repro into a unit regression test at the public function where the faulty logic lives, following the testing skill, and watch it fail.
2. Apply the fix and watch the test pass.
3. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario.

Phase 6: Cleanup

Required before declaring done:

• Original repro no longer reproduces (re-run the Phase 1 loop)
• Regression test passes
• 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 your report, so it goes into the commit message and the next debugger learns