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/juxt/claude-plugins/weed-docsnpx skills add juxt/claude-plugins --skill weed-docsgit clone --depth 1 https://github.com/juxt/claude-pluginsWhat 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 | $0.00080 | $0.01297 |
| Opus 5 | $0.00040 | $0.00648 |
| Sonnet 5 | $0.00016 | $0.00259 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade A, and why
weed-docs 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weed — Documentation Drift Audit
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
Given a code change, identify the user-facing docs pages that probably need updating.
Mirror of allium:weed for prose.
This skill MUST NOT edit docs pages — it reports, the user acts, and resolving the drift is a separate step (usually chalk:tend-docs).
The audit MUST be scoped to user-facing docs.
Internal READMEs, code comments and developer notes are out of scope unless the user asks otherwise.
Your Responsibilities
-
Determine the audit scope.
Default: the current branch's diff against its base branch. If the user provides a commit, commit range, or path, use that instead.
If the diff is empty, say so and stop — don't produce a fake empty punch list.
-
Enumerate the code surfaces that changed.
Walk the diff and extract the things a docs page could mention:
- Renames — classes, functions, modules, config keys, CLI flags, environment variables.
- Signature changes — added/removed/renamed parameters, changed return types, changed error types.
- Behavioural changes — changed defaults, new required fields, relaxed or tightened constraints.
- New public surfaces — new commands, endpoints, config keys, public APIs. These have no existing docs, so the audit must flag them as coverage gaps.
- Removed surfaces — deleted commands, endpoints, config keys. Docs that still reference them are stale.
- Error messages and log lines — if a docs page quotes them, they need updating.
- Examples in the code — if docstrings or README snippets changed, paired docs examples may need syncing.
Internal refactors that don't change observable behaviour don't need docs updates.
-
Cross-reference the issue-graph neighbourhood.
If chalk is active (or the diff references an issue or PR), cast one hop out — the tracked chalk issue and its comments, related issues (parent, sub-issues, blocked-by, blocks), and the PR description and review discussion.
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 · 105 lines · 80 tokens per session scan A 3a11f5f03682
weed-docs is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed 4d ago), licensed MIT. It adds 80 tokens to every session and 1,297 once invoked, about $0.0004 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 2026-08-31.
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…