Audit work tracking
Reusable Codex skills and agent workflows
npx -y skills add LandonTomaine/LT-Agents --skill audit-work-trackingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Audit repository backlog, issue-tracker, PRD, workflow-state, implementation-plan, and artifact tracking for unclear ownership, stale status, oversized items, mixed status vocabularies, missing routing, or token-heavy agent workflows. Use when Codex is asked to review, tighten, migrate, or design how a repo tracks work.
SKILL.md
2.4 KB, 459 tokens by cl100k_base, as published. Nobody here has run it
Audit Work Tracking
Primary lens: Review.
Goal: review the work-tracking system, not the whole repo. Return findings first; make edits only when the user asks for fixes.
Scope
Start with the smallest relevant entrypoints:
- repo agent guide or contributor guide
- tracker/workflow docs
- backlog or issue indexes
- representative active item, plan, workflow state, and result artifact
- repo-local skills that select, plan, implement, or update work
Do not read every backlog item unless the audit explicitly needs coverage sampling.
Checklist
- Source of truth: work item ownership is clear between tracker, PRD, backlog, plan, workflow state, and chat.
- Lanes: active, done, deferred, bugs/incidents, enhancements, and tech-debt lanes are explicit when file-based tracking is used.
- Status vocabularies: backlog, workflow queue, bug/incident, PR, and process-improvement states are distinct and documented.
- Granularity: executable items are small enough to plan, validate, review, and close independently.
- Routing: intake, selection, planning, implementation, review, and closeout have clear handoffs.
- Artifacts: screenshots, logs, validation, result notes, and residual risks live beside the owning work item or in a named tracker location.
- Token cost: agents can find the next action without loading broad PRDs, old plans, large artifacts, or every historical item.
- Closure: done/deferred items are archived or indexed without staying in active queues.
Output
Return:
Scope reviewed- findings ordered by impact
Why it mattersSuggested fixSkill or docs impact, if anyVerdict:Pass,Pass with gaps, orFail
Prefer one or two concrete fixes over a new workflow system. Recommend a new skill only when the workflow is repeated, narrow, repo-specific, and docs alone are insufficient.
Do Not
- Do not invent a file-based backlog for repos that use an external tracker.
- Do not merge intake, selection, planning, implementation, and review into one skill by default.
- Do not turn the audit into broad product planning or code review.
What ships with it: 1 file
204 B alongside SKILL.md
agents/
- openai.yaml204 B