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/AGENTS.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/instructions/devenjarvis/lathe/agents-md)<a href="https://agentmods.dev/instructions/devenjarvis/lathe/agents-md"><img src="https://agentmods.dev/badge/instructions/devenjarvis/lathe/agents-md/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/instructions/devenjarvis/lathe/agents-md"><img src="https://agentmods.dev/badge/instructions/devenjarvis/lathe/agents-md.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 | $0.06104 | $0.06104 |
| Opus 5.5 | $0.02442 | $0.02442 |
| Sonnet 5.5 | $0.01221 | $0.01221 |
| Haiku 4.5 | $0.00610 | $0.00610 |
Grade C, and why
lathe AGENTS.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/HEAD/install.sh | sh -s -- -b "$(go env GOPATH)/bin" v2.12.2 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/HEAD/install.sh | sh -s -- -b "$(go env GOPATH)/bin" v2.12.2 How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Orientation for AI coding agents working in this repo.
What this is
Lathe is a Go CLI plus a set of coding-agent skills (the SKILL.md format is now a cross-tool standard — Claude Code, Cursor, Codex, Gemini CLI, opencode, Cline, Windsurf) that together generate, store, serve, verify, and extend hands-on technical tutorials. See README.md for user-facing docs.
The boundary is strict: skills generate content; the CLI owns durable state. All model work — generating, verifying, extending, answering reader questions, and authoring voices — runs in the user's interactive coding-agent session via user-invoked skills (/lathe, /lathe-verify, /lathe-extend, /lathe-ask, /lathe-tag, /lathe-voice, /lathe-work). The Go binary never drives a model itself — it spawns no claude/agent subprocess (which also keeps Lathe off metered headless runs like claude -p, metered as of 2026-06-15; interactive sessions are not). Don't move generation logic into Go, and don't have skills write to ~/.lathe/ directly — they call lathe commands (lathe store, lathe verify-result, lathe extend-start/extend-commit, lathe voice add) instead. The one skill→CLI read path is lathe voice show (the active voice spec) — still consistent with the boundary: the CLI stays the sole owner of the voice files and config; the skill only asks for text.
The web buttons close the copy-paste gap without crossing that boundary. When a /lathe-work worker session is connected (it long-polls GET /-/work, so internal/queue knows it's live), Ask/Verify/Extend enqueue a job the worker claims and runs in its interactive session; with no worker they fall back to the same paste-able handoff as before. The model still only ever runs in the interactive session — the queue is just an in-memory bridge between the browser and that session. MCP, if ever added, would be only an alternate transport for this same queue, not a way to run a model inside Go.
Layout
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.
- 2mo ago First seen · 118 lines · 6,104 tokens per session scan C 9af00bc4cfba
lathe AGENTS.md is an instructions file published in the GitHub repository devenjarvis/lathe (1,714 stars, last pushed 19d ago), licensed MIT. It adds 6,104 tokens to every session, about $0.0244 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
lathe AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lathe AGENTS.mddevenjarvis/lathe | Instructions file | 1.7k | 19d ago | MIT | C | 6,104 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |