task-track

Codex compatibility note:

• Invoke $skill-name: load the registered .agents/skills/<name>/SKILL.md and execute it with Codex tools; no separate Skill tool or Claude mode switch is needed. 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_agent subagent(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

Choose by the invocation, never by the presence of a tracker folder, root pointer or configured engine. When both exist, explicit guide uses project instructions; an old mode still uses the engine protocol. Project prohibitions and unsupported engine capabilities remain binding; never switch routes to bypass a refusal. Guide mode does not initialize, enroll or migrate a tracker, and does not require portable-engine configuration.

Honor the active host's Run/Skip and disabled-selection controls. This skill remains manual-only; a named authorized invocation remains usable. Invocation supplies guidance, not permission for assignment, acceptance, publication or other actions beyond the user's request.

Project customization

For engine command recipes, read manual operations when the selected engine route needs exact requests, placement or refusal recovery. Read the integration guide when recording an actual saved producer checkpoint or interpreting exact linked concerns. These are engine references; project-guide mode keeps the selected project's own guide and mechanism.

Read the selected checkout's root instructions (CLAUDE.md or AGENTS.md) when resolving its work-tracking guide. The project owns its guide path, storage, lifecycle, placement, evidence, acceptance and checks. Change those at the project owner; keep them out of this portable skill. Additive project overlays may add steps, but cannot replace either route's requirements or waive an authority or verification gate.

Closing reminders

Select the route explicitly; read its reference before acting; preserve project rules and actual human authority. Report only checks and outcomes observed.