Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/gaoscode/planweave/plan-reviewernpx skills add GaosCode/PlanWeave --skill plan-reviewergit clone --depth 1 https://github.com/GaosCode/PlanWeaveWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00039 | $0.00664 |
| Opus 5 | $0.00019 | $0.00332 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
plan-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Reviewer
Use this skill after the coordinator assigns one review gate. Judge the assigned work; do not implement fixes, claim new work, coordinate the plan, edit Plan Package files, or repair runtime state.
Required Packet
The handoff should include:
- assigned review ref.
- rendered review prompt or prompt path.
- upstream implementation reports.
- changed files or diff summary.
- acceptance criteria and validation evidence.
- expected
review-result.jsonpath or instruction to return the JSON.
If key evidence is missing, ask the coordinator for it instead of guessing.
Review Loop
- Confirm the assigned ref is a review block.
- Do not run
claim-next; claim only the exact review ref if the coordinator explicitly saysclaim required. - Read the review prompt, implementation reports, changed files, referenced source, tests, and acceptance criteria.
- Check only the assigned gate and its upstream implementation work.
- Return
passedorneeds_changes; submit only if the coordinator explicitly asked you to submit.
Review Checks
- Goal and acceptance are satisfied.
- Producer/consumer contracts are consistent for schema, API, CLI, events, files, state, and prompt I/O.
- Runtime use, callers, live paths, and observable outputs exist where required.
- Mock, dry-run, fixture-only, or uncalled paths are not presented as complete live behavior.
- Validation evidence matches the risk of the block.
- Failure paths are covered when the feature or state machine needs reliability.
Verdict
- Use
passedonly when acceptance is met and validation evidence is adequate. - Use
needs_changesfor incomplete, unsafe, unverifiable, out-of-scope, or contract-breaking work. - Use
NEEDS_COORDINATORfor blocked work, divergence, missing evidence, tool failure, stale prompts, invalid acceptance, bad dependencies, or review-gate design defects. - Do not encode Plan Package defects as implementation feedback; report the exact task, block, prompt, edge, or review-gate problem to the coordinator.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 65 lines · 39 tokens per session scan A 3dc66c21ae36
plan-reviewer is a skill published in the GitHub repository GaosCode/PlanWeave (370 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 664 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
dot-ai-prd-create
Create documentation-first PRDs that guide development through user-facing content.
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…
bmad-check-implementation-readiness
Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".