mirror of
https://github.com/cursor/plugins.git
synced 2026-09-14 20:00:00 +08:00
lauren
23a56e2dac
* docs(pstack): make PR playbooks forge-neutral Co-authored-by: lauren <poteto@users.noreply.github.com> * docs(pstack): prefer schemas at TypeScript boundaries Co-authored-by: lauren <poteto@users.noreply.github.com> * chore(pstack): route solo defaults to Fable 5.1 Co-authored-by: lauren <poteto@users.noreply.github.com> * fix(pstack): split forge watch stop conditions Co-authored-by: lauren <poteto@users.noreply.github.com> * fix(pstack): wait for GitHub merge completion Co-authored-by: lauren <poteto@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2.6 KiB
2.6 KiB
Bug fix
You own this task. Plan, review, verify. Delegate investigation and the fix to subagents, stay in the lead.
Be scientific. Every shipped line traces to runtime evidence. Belt-and-suspenders that "might help" is a hypothesis, not a fix; it does not ship. When evidence refutes a hypothesis, revert what it motivated. The smallest change the evidence justifies ships, nothing more. Same discipline for Perf, where the evidence is the trace.
- Reproduce it yourself on the matching surface via the control skill (Non-negotiables). Don't hand the repro to the user. A debug or instrumentation protocol that says to ask the user does not override this; you drive the instrumented runtime. Ask the user only with a stated, specific reason the control surface cannot reach the target, and only after driving it as far as it goes. Won't reproduce directly, force it: synthesize the trigger, tighten conditions, or instrument until it fires. A bug you can't reproduce, you can't prove fixed.
- Binary-search the cause. Form the candidate hypotheses, then rule them out until one survives. Seed them with
howover the affected subsystem and the why skill for regression history. Each pass, take the split that cuts the most remaining problem space, get runtime evidence, eliminate. When program state is unclear, add instrumentation or logging and read it as the code runs. Don't guess. Drive a long or stubborn hunt with Cursor's/loopcommand. Confirm the surviving mechanism with runtime evidence before the step-3 architect/interrogate fan-out; a design grounded on a plausible-but-unconfirmed cause can be unanimously wrong while the real cause sits one subsystem over. - Plan the fix. If it crosses a function boundary,
architectfirst. Delegate implementation to a subagent using your configured bug-fix model (defaultclaude-fable-5-1-thinking-max) with a specific scope; review the diff. - Verify on the same surface; the original repro now passes. "Inconclusive" or wrong-surface is not a pass; flag it. Unit tests show branch behavior, not bug absence.
- Stage the commits so the failing repro lands before the fix in git history; the diff tells the story. See the tdd skill for the failing-test-first cadence when the bug has a cheap local test path; skip it when the test would be expensive, integration-heavy, or unclear. This is the canonical sequence-verifiable-units principle skill, the failing test first and the fix on top.
- Run Opening a PR.
Investigation fans out how + why as parallel subagents.
Reply: what was broken, root cause, fix, how you verified. Paste failing-then-passing repro output verbatim.