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/issuenpx skills add juxt/claude-plugins --skill issuegit 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 | $0.00134 | $0.01876 |
| Opus 5 | $0.00067 | $0.00938 |
| Sonnet 5 | $0.00027 | $0.00375 |
| Haiku 4.5 | $0.00013 | $0.00188 |
Grade A, and why
issue 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
The user MAY provide a title as an argument (e.g. /chalk:issue flaky expression_test under load).
If no title is provided, draft one from the conversation.
This skill owns the issue description — drafting it, creating the issue, and keeping the description accurate later.
It does not track a session against the issue: "open an issue for this so we don't lose it" is this skill on its own.
Filing and picking it up is chalk new, which runs this skill to produce the issue and then starts tracking.
Before you draft
An issue description is an explanation artefact, and it MUST be drafted against the chalk voice. Load these first (via the Skill tool):
chalk:voice, and itsreferences/palette.md— the principles, the section palette, the line-format rule.chalk:mindmap— the shape of the content inside each section.chalk:goal-tree— wherever a section's children accomplish their parent rather than argue for it.
Structure the body into sections drawn from the palette, choosing the ones this issue needs, and write each section as a mindmap — a short tl;dr opening it, then the tree. A wall of undifferentiated prose is the wrong shape; if you've written one, you skipped this step.
The body MUST open with a tl;dr at the top, per chalk:mindmap.
That makes a separate Summary section largely redundant — drop it, or hold it to the one or two sentences the palette asks for.
Your audience is whoever is scanning a backlog, deciding whether to pick this card up this sprint. Write for that decision: a summary of the session's work doesn't serve it.
Your responsibilities
-
Establish the why and the why now.
An issue MUST NOT be filed without a why — if the motivation isn't recoverable, ask rather than guessing. The rule is a universal principle in
chalk:voice.What's specific to an issue: why now is the line most often missing from a filed card, and its absence is what makes it un-triageable. It MUST be traceable to something the user said, a commit or a file you can name. There is no diff here to fall back on, and a motivation you assembled yourself reads exactly like one you were told.
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 · 122 lines · 134 tokens per session scan A 5d5d33feb92f
issue is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed 4d ago), licensed MIT. It adds 134 tokens to every session and 1,876 once invoked, about $0.0007 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…