Per-skill prose tightening from the same audit swarm; each finding passed an adversarial second reviewer. No behavioural change. - audit: drop garbled "Conventions require deferred audits to compound" sentence (says the opposite of intent; the preceding line already closes the loophole). - brainstorm: drop forward-pointing meta-comment about the Rationalisations table. - debug: drop third restatement that debugger.md is the single source for the carrier/handoff fields. - docwriter: drop motivational opener; Overview starts at the waste argument. - fieldtest: fold the 2-4-examples rationale into the dispatch sentence instead of restating the count a fourth time. - implement: drop "known platform constraint at the time" aside. - planner: cut the verbose anti-drift paragraph (which restated the very table it claimed not to) down to a cross-reference. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
3.8 KiB
name, description
| name | description |
|---|---|
| debug | Use when a bug surfaces — failing test, segfault, wrong stdout, panic, or any observable misbehaviour. Bug fixes are RED-first TDD; no fix is attempted before the failing test exists in the working tree. Mandatory for any bug, including ones that look trivial. |
debug — RED-first bug diagnoser
Violating the letter of these rules is violating the spirit.
Overview
Bugs are diagnosed and fixed by a two-stage handoff: this
skill produces the RED test and the cause analysis; the
implement skill then drives the fix to GREEN. Skipping the
RED stage — even for "trivial" bugs — produces fixes that don't
stick and tests that don't exist to catch the next regression.
The substantive process — root cause investigation → pattern
analysis → minimal, autonomous RED test → handoff, plus the
Phase 4.5 architecture-question trigger after three failed
hypotheses — lives in agents/debugger.md. The RED stage is
not "any failing test": Phase 3 reduces the reproducer to the
smallest autonomous trigger before the test counts. That file is the single source of truth
for the discipline; this skill file only governs trigger,
dispatch, and handoff.
When to Use / Skipping
Trigger this skill on:
- a failing run of the project's test command (configured under
commands.testin the profile) - wrong stdout from running a project artefact
- a segfault from a built binary
- a panic / unhandled exception in the toolchain
- a structured diagnostic from
bencherorarchitectthat names a concrete misbehaviour
Never skipped. A bug without a regression test is a code change, not a fix. Ad-hoc judgement that a bug is "too small for TDD" is the exact failure mode this skill exists to prevent.
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
NO FIX WITHOUT A FAILING TEST FIRST
Both clauses are non-negotiable.
Dispatch
Dispatch the debugger agent with the carrier fields it defines
under Carrier contract in agents/debugger.md — symptom,
repro_known, recent_iter. That table is the authoritative
definition of those fields; it is deliberately not restated here,
so the two files cannot drift.
The agent writes the RED test to the working tree (uncommitted)
and reports the handoff carrier for implement mini-mode. The
agent does NOT commit anything, and does NOT write the fix —
splitting RED (this skill) and GREEN (implement mini-mode)
across two dispatches keeps the diagnosis honest. The
orchestrator decides whether to commit the RED test as a
separate audit-trail commit before dispatching implement
mini-mode, or to hand the dirty working tree directly to
mini-mode (the mini-mode orchestrator's Phase-0 clean-tree
check will refuse the latter — so for an audit-trail-preserving
flow the orchestrator commits the RED test first; for a
streamlined-fix flow the orchestrator commits the combined
RED+GREEN at the end of mini-mode).
Handoff Contract
debug produces, for implement mini-mode, the handoff carrier
the agent defines under Output format in agents/debugger.md
— red_test_path, cause_summary, constraint. That list is
the authoritative definition of those fields; it is deliberately
not restated here, so the two files cannot drift.
Anything else (broader refactor, doc rewrite, new feature) is OUT of scope for the bug-fix iteration and gets queued for a separate one.
Cross-references
- Agent dispatched:
agents/debugger.md— carries the four-phase process, the Phase 4.5 escalation rule, the Common Rationalisations table, and the Red Flags list. The orchestrator does not execute these phases directly. - Hand-off target:
../implement/SKILL.md— runs the GREEN side after the orchestrator has decided whether to commit the RED test separately or as part of the final fix commit.