investigate
Installation
SKILL.md
Codex compatibility note:
- Invoke
$skill-name: load the registered.agents/skills/<name>/SKILL.mdand execute it with Codex tools; no separateSkilltool or Claude mode switch is needed. When a workflow step or another skill names a skill, read that file in full yourself (every line, with no line limit; in parts only when output is cut off): a skill whose implicit invocation is off is never loaded for you. Author.claude/**; mirrors are generated.- Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
- Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required
spawn_agentsubagent(s) for that task.- Preserve protocol order unless the user approves a deviation. Workflows use
$start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence. [BLOCKING] Mode routing — detect FIRST. Explicit--mode=debugor--mode=explainselects that mode; no mode is the default read-only code-flow investigation (everything below, unchanged).$investigate --mode=debug <bug>is the former/debug-investigate(root-cause investigation of a bug).
[BLOCKING] Execute phases in declared order. NEVER skip, reorder, or merge without explicit user approval. [BLOCKING] Before each phase or skill call, update todo tracking; mark
in_progressat start andcompletedafter evidence. [BLOCKING] Record evidence for each completed/skipped phase; if task tools are unavailable, maintain an equivalent tracker. [BLOCKING] Investigation stays READ-ONLY; report findings, never patch source.
Quick Summary
Goal: Explain existing code through READ-ONLY, evidence-backed exploration so every finding maps to file:line (or "inferred"), system flow is verified, and follow-up decisions rest on evidence without changing source.