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-importernpx skills add GaosCode/PlanWeave --skill plan-importergit 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 | $0.00048 | $0.02412 |
| Opus 5 | $0.00024 | $0.01206 |
| Sonnet 5 | $0.00010 | $0.00482 |
| Haiku 4.5 | $0.00005 | $0.00241 |
Grade A, and why
plan-importer 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Importer
Use this skill to turn existing project planning material into a PlanWeave Plan Package.
Command Entry
Resolve the command before writing files:
- Use a user-provided command if given.
- Else try global
planweave. - In the PlanWeave repo, prefer
pnpm --filter @planweave-ai/cli planweave. - If the repo defines another local script, use that exact entry and show it in the report.
Write examples as <pw> ..., where <pw> is the resolved command.
Use the CLI to resolve the target workspace before writing files:
<pw> init --json
<pw> paths --json
<pw> validate --json
Use the CLI for command discovery, workspace/path resolution, and validation in this workflow. Materialize imports by writing package files directly into the CLI-returned PlanWeave workspace paths.
Workspace
- Run
<pw>from the target project root, not from the PlanWeave repo unless PlanWeave itself is the target project. - Do not create or write
./.planweaveinside the target project by hand. - PlanWeave stores project plans under
PLANWEAVE_HOMEwhen set; otherwise defaults to:- macOS:
~/.planweave - Linux:
~/.planweave - Windows:
%USERPROFILE%\.planweave
- macOS:
- Read exact workspace paths from
<pw> init --jsonand<pw> paths --json. - Write only inside CLI-returned PlanWeave workspace paths, such as
workspaceRoot,projectGraphPath, and package directories under that workspace. - For a single-canvas import with an explicit existing target canvas, write only inside that canvas package directory.
- For a single-canvas import without an explicit target canvas, do not overwrite the existing default/current canvas. Create a new formal canvas entry in
project-graph.json, allocate a collision-free canvas id, and write the imported package under that canvas package directory. - For formal multi-canvas plans, write
project-graph.jsonat the returned project/workspace root and write each canvas package only under the package directories named by that project graph. - Treat CLI-returned project/workspace and package directories as the only writable PlanWeave locations.
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 · 144 lines · 48 tokens per session scan A 38a5f0acdfdd
plan-importer is a skill published in the GitHub repository GaosCode/PlanWeave (364 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 2,412 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…