Lathe is a tool that uses language models to create hands-on, multi-part technical tutorials and lets people study them in a local interface. It is intended for learners who want to follow tutorials themselves, while coding agents can generate, verify, extend, and manage those tutorials through its skills and command-line tool.
Borrowing it
Nothing to install: this file belongs to devenjarvis/lathe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/devenjarvis/lathe/main/.claude/skills/lathe-voice/SKILL.mdgit clone --depth 1 https://github.com/devenjarvis/latheWrote 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/devenjarvis/lathe/lathe-voice)<a href="https://agentmods.dev/skills/devenjarvis/lathe/lathe-voice"><img src="https://agentmods.dev/badge/skills/devenjarvis/lathe/lathe-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/devenjarvis/lathe/lathe-voice"><img src="https://agentmods.dev/badge/skills/devenjarvis/lathe/lathe-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 42 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00064 | $0.01292 |
| Opus 5 | $0.00032 | $0.00646 |
| Sonnet 5 | $0.00013 | $0.00258 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
lathe-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 12d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lathe — Author a Voice
Help the user craft a custom writing voice — a tone/register preset that
/lathe and /lathe-extend can generate tutorials in — then persist it through
the CLI. Triggered by /lathe-voice [name].
A voice controls tone and register only. It never changes accuracy,
research, citation, verification, substance, pedagogy, or structure — those are
fixed invariants in the lathe skill, and every voice is wrapped at read time
with a preamble that says so. You are authoring how the prose sounds, nothing
more.
What a voice is (and what it is not)
Look at the built-ins for the exact shape before you draft — they are the template:
lathe voice show plainspoken # the honest, non-anthropomorphic default
lathe voice show companion # the warm, first-person original
lathe voice list # everything currently available
A voice spec is a small markdown file with name:/description: frontmatter and
three working sections:
- Stance and register — persona, point of view, sentence rhythm, how the reader is addressed, the first-person policy, humor.
- Avoid — the tonal anti-patterns this voice rejects.
- Calibration — before / after — two or three ❌/✅ pairs showing the voice's
tone (not pedagogy; the pedagogy before/afters live in the
latheskill).
Refuse to author these (deception guardrail)
Decline, and explain why, if the request is to make a voice that:
- Impersonates a real, named person ("write exactly like <specific living author/engineer>", or as a named public figure) or implies their endorsement. A register inspired by a tradition is fine ("plain, in the spirit of good systems writing"); writing as a specific real person is not.
- Fabricates credentials or authority — a voice that claims real-world
experience, institutions, or qualifications the author doesn't have, or that
presents invented anecdotes as things that actually happened. (A voice may use
first person as a stance, like
companion, but it must not manufacture a fake résumé.) - Denies LLM authorship or is built to pass the tutorial off as human-written.
- Is coercive or deceptive — manipulative urgency, dark patterns, dishonesty toward the reader.
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.
- 12d ago First seen · 105 lines · 64 tokens per session scan A 4ca3b4989167
lathe-voice is a skill published in the GitHub repository devenjarvis/lathe (1,664 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,292 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…