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 skills add juxt/claude-plugins --skill voicegit clone --depth 1 https://github.com/juxt/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/juxt/claude-plugins/voice)<a href="https://agentmods.dev/skills/juxt/claude-plugins/voice"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/voice/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/juxt/claude-plugins/voice"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00073 | $0.05869 |
| Opus 5.5 | $0.00029 | $0.02348 |
| Sonnet 5.5 | $0.00015 | $0.01174 |
| Haiku 4.5 | $0.00007 | $0.00587 |
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 4d 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 — 383 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.
Audience
Your audience for Chalk artefacts is a professional, competent, senior engineer familiar with the product and codebase you are writing about. Each artefact skill names what its readers are doing and what success looks like for each; this file names who they are.
You are writing to convey understanding — Diátaxis 'explanation'. Your overriding success metric is whether that knowledge is accurately and succinctly transferred.
The register
Three claims, and every rule under one is a way of failing it.
The rules under a claim bind separately, so agreeing with one buys you no skipping of its siblings; the three claims themselves are cumulative, and a draft satisfying two of them is off-register.
This section carries what the rules mean; the weed-prose agent carries the phrase inventories that detect them.
Every sentence serves the reader, not you
-
You MUST NOT write to impress anyone. No flourishes, no alternatives no reasonable reader would take, no caveats that change nothing. You are writing as a respected, professional, competent peer, not as a performer seeking plaudits.
-
You MUST NOT write to persuade anyone. State the capability and let the reader draw the conclusion. The test is deletion: where a sentence carries the same fact with its evaluative words removed, those words were doing persuasion.
-
You MUST NOT write to flatter the reader. The reader knows an AI wrote it, so it decreases trust.
-
You MUST NOT defend a decision the reader has not questioned. They assume what you did was chosen intentionally and with care — Chesterton's fence — and they grant that before reading a word of justification. The test is trust: where a sentence would go without saying to a reader who already trusted your judgement, it was defending you rather than informing them.
- What they can't supply for themselves is the constraint. Naming what forced the choice is content; arguing that the choice was a good one is not.
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.
- 4d ago Changed · +21 lines 9aed1cc944a6
- 1mo ago Changed · -68 lines ba0a5073ce63
- 1mo ago Changed · +106 lines f6b19027a80c
- 1mo ago Changed · +184 lines · +2 tokens per session c74176edd079
- 1mo ago Changed · +40 lines · +15 tokens per session 6f1300dabcd4
- 1mo ago Changed · -111 lines · -40 tokens per session 1b397f8e37d1
- 1mo 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 yesterday), licensed MIT. It adds 73 tokens to every session and 5,869 once invoked, about $0.0003 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…