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/chalknpx skills add juxt/claude-plugins --skill chalkgit 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 | $0.00031 | $0.02370 |
| Opus 5 | $0.00015 | $0.01185 |
| Sonnet 5 | $0.00006 | $0.00474 |
| Haiku 4.5 | $0.00003 | $0.00237 |
Grade A, and why
chalk 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chalk — GitHub Issue Tracking
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
Track work against a GitHub Issue. The issue description is the source of truth, and it MUST be kept accurate as facts change. Comments are the append-only session log: what was tried, decided and learned.
Before you draft anything GitHub-bound
Every chalk comment and Progress section MUST be drafted in the chalk voice and shaped per chalk:mindmap.
Load these first (via the Skill tool):
chalk:voice, and itsreferences/palette.md.chalk:mindmap.chalk:goal-tree— when the artefact carries the direction of the work rather than its history.
Two artefacts have their own skill — load it instead of drafting from here:
the issue description is chalk:issue's, and the PR description is chalk:pr's.
Your audience is the next session on this issue — a teammate, or you, or an agent starting cold with only the issue in front of it.
"Name your audience" (chalk:voice): a comment written for whoever already sat through this session helps nobody, because they've gone.
Issue relationships
Parent/child and blocked-by carry structure the description can't — use them liberally.
chalk:issue covers what each is for.
- Wire relationships in the same session they emerge A dependency discovered mid-implementation ("this is blocked by #45") gets linked as soon as you find it. Deferring it usually means the link never gets made.
The github agent has GraphQL recipes for reading and mutating these (addSubIssue, addBlockedBy, and the neighbourhood query).
Commands
chalk #N— track this session against issue Nchalk new— create a new issue and track against itchalk status— report the issue number and current Progress summarychalk off— finalize the current comment (if one is in progress) via the agent, then stop tracking
Activation: chalk #N
- Use the agent to read the issue, its recent comments, and its one-hop neighbourhood (parent, sub-issues, blocked-by, blocking).
- Internalize the issue context without repeating the entire issue to the user.
- If no
## Progresssection exists in the description, ask the agent to add one. - If the change is non-trivial and the why or why now isn't obvious from the issue or its neighbours, ask the user before starting.
Per "Establish the why and the why now" (
chalk:voice), a why now you can't trace to something the user said, a commit or a file you can name is one you don't have. - Tell the user you're tracking against #N.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 195 lines · 31 tokens per session scan A a08d716c4a0e
chalk is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 2,370 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 2026-08-31.
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…