61a98573d7
Strip the disable-model-invocation frontmatter key from all 19 editable skills. Absent = default = model invocation enabled. 8 were 'true' and blocked the model AND orchestrators from self-routing (status, plugin-check, analyze, onboard, refactor, init-project, pdf-translate, ship-feature) — contradicting the CLAUDE.md skill-routing rules. The other 11 were 'false', a no-op noise line. The setting is binary (no per-caller granularity), so enabling orchestrator chaining also enables model auto-fire — accepted. Genuinely destructive operations remain guarded by the careful/guard hooks, independent of this flag. Capitalized: BDR-019 (decision), LRN-026 (learning), journal 2026-06-09. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
799 B
799 B
| name | description | argument-hint | allowed-tools | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| bugfix | Structured bug fix with root cause investigation. For bugs where the cause isn't immediately obvious, spans multiple files, or requires careful analysis before fixing. Includes hypothesis-driven investigation and a fix plan. Trigger: "bugfix", "debug this", "fix this bug", "pourquoi ca marche pas", "investigate and fix", "find and fix", "root cause + fix". For obvious 1-2 file fixes → use /hotfix instead. For bugs that need investigation only (no fix) → use /analyze. | <bug description, error message, or stack trace> |
|
Load and follow strictly:
- $HOME/.claude/agents/bugfixer.md
Execute the BUGFIXER agent on the following target:
$ARGUMENTS