Debug reproduced
User confirms the bug was reproduced. Analyze logs and iterate on hypotheses.From its SKILL.md
npx -y skills add mikecfisher/agent-debug-mode --skill debug-reproducedAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.5 KB, as published. Nobody here has run it
Debug Reproduced
User has reproduced the bug. Analyze log evidence and iterate.
User Notes
$ARGUMENTS
Workflow
Step 1: Analyze Logs
Run the analyzer:
bun ./scripts/analyze-logs.mjs
Or read raw logs:
cat .debug/debug.log
Step 2: Evaluate Hypotheses
For each hypothesis, assign one verdict:
- CONFIRMED: Log evidence proves this is the cause
- REJECTED: Log evidence rules this out
- INCONCLUSIVE: Need more instrumentation
Always cite specific log entries as evidence:
Hypothesis A: CONFIRMED
- Log at 14:32:05.123 shows
itemsisundefinedat function entry- Log at 14:32:05.156 shows error "Cannot read property 'length' of undefined"
- Root cause:
order.itemsnot provided by callerHypothesis B: REJECTED
- Logs show
loadUsercompleted at 14:32:05.100renderProfilestarted at 14:32:05.200- Order is correct, no race condition
Step 3: Take Action
If hypothesis CONFIRMED:
- Implement the fix
- Keep instrumentation in place (do NOT remove logs yet)
- Provide new reproduction steps to verify fix
- After user reproduces, compare before/after logs — cite specific entries showing the fix worked
If INCONCLUSIVE:
- Add more instrumentation to narrow down
- Provide new reproduction steps
If ALL hypotheses REJECTED:
- Generate NEW hypotheses from different subsystems
- Add instrumentation for new hypotheses
- Provide new reproduction steps
Step 4: Next Iteration
Provide exact reproduction steps:
<reproduction_steps>
- [Step 1]
- [Step 2] ... </reproduction_steps>
End with:
Follow these steps, then run
/debug-reproducedwhen done, or/debug-fixedif the issue is resolved.
Critical Rules
- NEVER fix without 100% confidence with log proof
- NEVER remove instrumentation before verified fix
- ALWAYS cite specific log entries — "Log at 14:32:05 shows X was null"
- Iteration is expected — Failed fixes mean new hypotheses, not giving up
- 3 failed fixes = step back — Reconsider assumptions, look at different subsystems
- Taking longer is better — Thorough debugging beats quick guesses
Note on Log Accumulation
Logs accumulate across iterations (not auto-cleared). This allows comparing behavior across reproduction cycles. Run bun ./scripts/clear-logs.mjs if you need a fresh start.