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/voicenpx skills add juxt/claude-plugins --skill voicegit 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 | $0.00096 | $0.02969 |
| Opus 5 | $0.00048 | $0.01484 |
| Sonnet 5 | $0.00019 | $0.00594 |
| Haiku 4.5 | $0.00010 | $0.00297 |
Grade A, and why
voice 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chalk Voice — Writing Principles
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
Optimise for the reader, not the writer.
Whatever you're writing, the reader is trying to do one of four things, and Diataxis names them:
| Acquire | Apply | |
|---|---|---|
| Cognition | Explanation | Reference |
| Action | Tutorial | How-to |
Nearly everything in this plugin is explanation, end to end — commit bodies, issue and PR descriptions, chalk comments, code comments. Reference-shaped material inside them (log excerpts, usage examples, commit lists, test plans) is illustration embedded in the explanation, not a section of its own. A docs page is the only artefact that plays all four.
Load alongside this
-
chalk:mindmap— always. The shape of followable content: nested bullets, subject lines, tags, cross-reference IDs, tl;dr placement. It applies in every quadrant. -
chalk:goal-tree— where a node's children accomplish it rather than argue for it. The direction of a piece of work, a Future state or Implementation section. -
references/palette.md— before drafting an issue, PR or chalk comment. The section palette, their ordering, and the annotated-trace technique for sequencing bugs. -
references/docs-quadrants.md— before writing a docs page. How-to, reference and tutorial voice; the three quadrants nothing else here needs. -
chalk:code-comments— before writing or editing any comment. The reader model, the counter-intuition test, and where the rejected material goes instead.
Line format
The destination decides it: paragraph-per-line where the artefact is read rendered, sentence-per-line where it's reviewed as a diff.
- Paragraph-per-line — commit bodies, issue and PR descriptions, chalk comments.
These are read rendered on GitHub, and GitHub renders a single newline as
<br>, so sentence-per-line fragments into staccato. Put each paragraph on one line, separate paragraphs with a blank line, and let the rendering wrap.
What ships with it
2 files 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 · 211 lines · 96 tokens per session scan A 71e1b8a55ecb
voice is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 2,969 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…