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/commitnpx skills add juxt/claude-plugins --skill commitgit 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 | $0.00098 | $0.01462 |
| Opus 5 | $0.00049 | $0.00731 |
| Sonnet 5 | $0.00020 | $0.00292 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
commit 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 yesterday.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contextual Git Commit
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
The user will provide the commit headline as an argument (e.g. /chalk:commit fix: boolean logic error in expression.clj).
Before you draft
A commit body is an explanation artefact and MUST be drafted in the chalk voice, not your own default prose habits.
chalk:commit pulls in nothing on its own, so load these first (via the Skill tool):
chalk:voice— the principles, the explanation quadrant, the line-format rule.chalk:mindmap— a commit body is a lead-in line then a tree, not prose. See "Commit bodies" there.chalk:code-comments— the body is where a comment's design rationale belongs, so this is the moment the misfiled ones surface.
The body MUST NOT contain headings — needing them is a signal the commit is too big, or that you're writing the PR description in the wrong place. A tl;dr is optional; the subject line normally serves as one.
Your responsibilities
-
Stage relevant changes.
Each commit MUST be an atomic, cohesive unit of change — a transition from one valid state to another — and unrelated changes MUST NOT be staged together.
- If two changes don't make sense independently, they're one commit; if they're distinct, they're two.
- Keep unrelated bugfixes separate.
- Where reasonable, separate behaviour-preserving changes (refactorings) from behaviour-advancing ones.
-
Weed the staged comments.
Delegate to the
weed-commentsagent, passing the paths of the staged files and nothing else.- You MUST NOT tell it what the change is for. Not the issue, not the problem, not what you decided. It stands in for a reader who has none of that, and briefing it makes it a second opinion from your own context rather than a first opinion from the reader's.
- Its deletions apply. They land in the working tree and you stage them; you do not review them back into place. The user sees them in the commit diff, which is the human review point.
- Its Misfiled list is input to Draft the body — a comment deleted for being design rationale is rationale the body now has to carry.
- Where a comment survives, its Kept line names the misunderstanding it prevents; that belongs in neither the body nor the code.
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.
- yesterday First seen · 98 lines · 98 tokens per session scan A 90632d3a3d74
commit is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 1,462 once invoked, about $0.0005 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…