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-work/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-work)<a href="https://agentmods.dev/skills/devenjarvis/lathe/lathe-work"><img src="https://agentmods.dev/badge/skills/devenjarvis/lathe/lathe-work/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-work"><img src="https://agentmods.dev/badge/skills/devenjarvis/lathe/lathe-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01633 |
| Opus 5 | $0.00034 | $0.00816 |
| Sonnet 5 | $0.00014 | $0.00327 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
lathe-work 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 10d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lathe — Worker Loop
Start a long-running loop that lets the lathe serve web UI drive Ask, Verify, and Add-a-part directly in this session. With this loop running, the browser buttons enqueue a job and you pick it up here — no copy-paste of a /lathe-* command. Triggered by /lathe-work.
This is just long-poll → do the model work → report → repeat, so it works in any supported coding agent. The strict boundary still holds: the binary never drives a model. All model work runs here, in your normal interactive session — never via -p / headless. Verify runs the tutorial's code under exactly the same trust model as /lathe-verify does today (a fresh mktemp -d, your normal permissions).
When this loop is not running, the buttons fall back to today's copy-paste handoff — so starting it is purely additive.
Prerequisite
lathe serve must be running (the loop talks to it via ~/.lathe/serve.json). If lathe work next reports "no lathe server is running", tell the user to start lathe serve in another terminal, then start the loop.
The loop
Repeat until the user stops you (Ctrl-C, "stop the worker", or closing the session):
-
Claim the next job:
lathe work nextThis long-polls (~50s) and prints either
no taskor a single JSON object like:{"id":"7","type":"verify","slug":"digital-synth-zig","part":"part-02.md","question":"…","guidance":"…","state":"claimed"}- If it prints
no task, loop back to step 1 immediately — that's just an idle long-poll, not an error. - Otherwise parse the JSON and note
id,type,slug, and (depending on type)part/question/guidance.
- If it prints
-
Dispatch on
type, applying the existing protocol as the source of truth — don't duplicate or paraphrase it, apply it:verify→ apply the/lathe-verifyprotocol againstslugexactly as written (it marks the tutorialverifying, follows it in a fresh scratch dir, and records the outcome vialathe verify-result). When it finishes, close the job:lathe work done <id>
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.
- 10d ago First seen · 71 lines · 68 tokens per session scan A dfba3de95857
lathe-work is a skill published in the GitHub repository devenjarvis/lathe (1,662 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,633 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…