work-item
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
$start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence. [BLOCKING] Mode routing — detect FIRST. An explicit--mode=refine,--mode=story,--mode=mockup,--mode=challenge,--mode=reviewor--mode=dorselects that mode. With no mode, show the Mode Dispatch table and stop: ask nothing, guess nothing, run nothing. Formerly/refine,/story,/pbi-mockup,/pbi-challenge,/artifact-review,/dor-gate: those slash commands no longer exist, and each mode works called directly with no workflow. Read the mode file in full before anything else.
Renamed: formerly
/pbi— now$work-item. The old name no longer resolves as a slash command. Modes are unchanged; the record this skill writes is a task, and--type=pbiis now--type=task.
Work tracking: Keep the project's tracked work current in the same change, as its root instructions (
CLAUDE.mdorAGENTS.md) say. When the project uses the portable tracker (taskTracking.modeisobserveorlinked), read the linked work integration guide at capture, start, saved-work, verification, handoff and close-out checkpoints. Inspect exact selected owners and declared spec/task/subtask dependencies before refinement/story decisions and after their actual successful save. Retain all selected-mode interview, validation and readiness gates; diagnostic concerns never approve readiness or acceptance. Only the primary saving owner records one checkpoint with the actual inherited producer/context. Read-only review and failed saves supply no saved observation. Continue untracked; disclose partial/unavailable concerns and secondary pending reasons.Work record shape: Task and story files are work records owned by
$task-track. Read Records another skill authors before a mode writes or edits one:status: drafton generation, no assignee, integerpriority, labels inpriority_label, and tracker-owned fields of a tracked record change only through$task-track.
Quick Summary
For UI-bearing artifact reviews, read references/review-type-design.md → Shared UI protocol bodies at the review mode's UI gate; its Design-only UI/UX principles apply only to --type=design. Non-UI reviews keep their own rubric without loading UI depth.
Review modes: For review/audit work, standalone defaults to
--review-only(--report-onlyalias);--fix-loopenables review → validate → authorized fix → fresh re-review, default cap 3.--fix-loop --loop-owner=callerreturns a read-only pass to the caller that owns fixes/re-review. Create triage, review, validation and re-review todo tasks first; apply the carriedreview-policycontract for LOW deferral and user-approved bounded extensions. Non-review modes and terminal findings validation keep their own dispatch.