plan-coordinator

A coordination guide for running a complete PlanWeave plan, including assigning work to other agents, sending items for review, handling feedback, and recovering from execution problems. PlanWeave organizes a project as linked work blocks.

In plain words
What is it for?
Use it to inspect status, choose the next work item, give a worker its exact assignment and expected artifact, and route review or recovery work.
Why use it?
It keeps execution moving while preserving separate responsibilities for implementation, review, feedback fixes, and recovery.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gaoscode/planweave/plan-coordinator
Any agent
npx skills add GaosCode/PlanWeave --skill plan-coordinator
Clone the repo
git clone --depth 1 https://github.com/GaosCode/PlanWeave

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,624 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00063 $0.02624
Opus 5 $0.00032 $0.01312
Sonnet 5 $0.00013 $0.00525
Haiku 4.5 $0.00006 $0.00262

Measured 2d ago against content hash f2312d0aeb82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-coordinator 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.

skills/plan-coordinator/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Coordinator

Use this skill as the main agent/controller for a PlanWeave package. The coordinator thread is a dispatcher only: it must not implement blocks, review gates, feedback fixes, edit target source files, edit Plan Package files, or write implementation/review artifacts itself.

plan-runner, plan-reviewer, and plan-recovery are role instructions for worker subagents. They are not permission for the coordinator to switch roles inside the same thread. If current-agent or manual work cannot be handed to a native subagent mechanism, stop and report NEEDS_COORDINATOR unless the user explicitly authorizes coordinator fallback.

Quick Start

  1. Resolve the CLI entry. Use <pw> help work, <pw> help submit, and <pw> help recovery for command syntax.
  2. Run preflight: confirm PLANWEAVE_HOME, project id, project graph path when present, package/canvas paths, source prompt paths, current refs, and active feedback.
  3. Decide whether to assign implementation work, review work, feedback work, or recovery work.
  4. Give each worker subagent exactly one work item, claim ownership, rendered prompt path/content, expected artifact, submit command, and validation expectations.
  5. Collect reports/results, submit or verify submission, then re-check status.
  6. Continue until the plan is complete, genuinely blocked, or diverged and needs user/plan reconciliation.

Preflight

  • Read <pw> paths --json before dispatching and record project id, package dir, state path, and results dir.
  • Identify the active canvas/package scope and where cross-canvas dependencies are expressed.
  • For formal multi-canvas projects, treat project-graph.json as the authority for canvas-level dependencies and explicit cross-task blockers.
  • Do not infer runnable canvas order from prompt prose when a formal project graph exists.
  • Confirm source of truth for global, project, task, and block prompts; rendered prompts are derived output.
  • Produce a prompt source summary when prompts look empty, inherited, or surprising.
  • Surface inherited prompt sources before dispatching work, including global prompt, project/canvas prompt, task node prompt, block prompt, and any higher-level flow requirements.
  • Do not inject other projects' skills, bootstrap rules, or agent instructions into prompts unless the target repository explicitly requires them.

Read the full file on GitHub · 135 lines

Changes

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.

  1. 2d ago First seen · 135 lines · 63 tokens per session scan A f2312d0aeb82

Subscribe to this mod's changes

plan-coordinator is a skill published in the GitHub repository GaosCode/PlanWeave (364 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 2,624 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens