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-runnernpx skills add GaosCode/PlanWeave --skill plan-runnergit 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 | $0.00042 | $0.00584 |
| Opus 5 | $0.00021 | $0.00292 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
plan-runner 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Runner
Use this skill after the coordinator assigns one implementation block. Focus on completing that block precisely; do not schedule, discover, repair PlanWeave state, or reconcile the Plan Package.
Required Packet
The handoff should include:
- assigned block ref.
- rendered prompt or prompt path.
- claim ownership: usually
already claimed. - scope boundaries and files not to touch.
- expected report/result artifact.
- validation commands or observable completion criteria.
If any required item is missing, ask the coordinator for it instead of claiming other work.
Execution Loop
- Confirm the assigned ref is implementation work.
- If ownership is
already claimed, do not runclaimorclaim-next. - If ownership is
claim required, claim only the exact assigned ref/task and stop if a different ref is returned. - Read the rendered prompt and referenced files.
- Search nearby producers, consumers, schemas, tests, fixtures, and docs that affect this block.
- Make the smallest scoped change that satisfies the prompt.
- Run the assigned or directly relevant validation.
- Write the requested report and return it, or submit only if the coordinator explicitly asked you to submit.
Quality Gate
- Do not treat mock, dry-run, fixture-only tests, or uncalled APIs as live completion unless the prompt explicitly scopes the block that way.
- Keep schema/type/API/CLI/file/prompt contracts aligned between producers and consumers.
- Preserve unrelated files and behavior.
- If the prompt is empty, contradictory, stale, blocked, diverged, or points at missing source files, stop and return
NEEDS_COORDINATOR. - If the assigned block cannot be completed because the plan has bad dependencies, missing prompts, invalid acceptance, wrong review gate design, or stale task scope, stop and return
NEEDS_COORDINATORwith the exact plan defect.
Report
Include:
- assigned ref.
- changed files.
- behavior changed and behavior kept.
- validation run and result.
- remaining risks or
none. - any coordinator/recovery issue.
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 · 60 lines · 42 tokens per session scan A f2129e948d8d
plan-runner is a skill published in the GitHub repository GaosCode/PlanWeave (364 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 584 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…