task-track
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.
Quick Summary
Goal: Support the selected project's tracker conventions or the portable work engine through one
explicit entry point. Read only the selected route's reference before acting. These modes are
skill purposes, not CLI flags; never pass --mode=guide to the engine command.
| Invocation | Read and follow |
|---|---|
--mode=guide |
Project guide: discover the selected checkout's root-linked work-tracking instruction and use its documented mechanism |
Bare invocation, or --mode=inspect|maintain|link|lifecycle|verify|accept|report|serve |
Engine protocol: preserve the bare inspect default and existing operation safeguards |
| Any other mode | Refuse without an operation |