lathe: Instructions file for Claude Code

CLAUDE.md

lathe CLAUDE.md is an instructions file for Claude Code from lathe-cli/lathe. It costs 1,447 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for Lathe, a tool that turns API descriptions into command-line programs for humans and AI agents. API descriptions are formal documents that define available operations, inputs, authentication, and outputs.

In plain words
What is it for?
It is for developing Lathe's API-to-CLI generation, repository setup, authentication checks, command discovery, and agent guidance.
Why use it?
It tells the agent which files and specifications are authoritative and explains how generated commands should expose discoverable, machine-readable details.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

This is lathe-cli/lathe's own configuration. It tells Claude Code how to work on lathe itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lathe configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lathe-cli/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.

Copy the file
curl -O https://raw.githubusercontent.com/lathe-cli/lathe/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lathe-cli/lathe

Made for: Claude Code.

Wrote 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.

agentmods badge for lathe CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lathe-cli/lathe/claude-md/github.svg)](https://agentmods.dev/instructions/lathe-cli/lathe/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lathe-cli/lathe/claude-md"><img src="https://agentmods.dev/badge/instructions/lathe-cli/lathe/claude-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.

agentmods 80×15 button for lathe CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lathe-cli/lathe/claude-md"><img src="https://agentmods.dev/badge/instructions/lathe-cli/lathe/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,447 This file is loaded in full into every session.
When invoked 1,447 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01447 $0.01447
Opus 5.5 $0.00579 $0.00579
Sonnet 5.5 $0.00289 $0.00289
Haiku 4.5 $0.00145 $0.00145

Measured 10d ago against content hash 7e08a24db76e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lathe CLAUDE.md 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.

CLAUDE.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lathe agent guide

AGENTS.md links to this file. Read CLAUDE.local.md if present.

Product and sources

Lathe generates inspectable Cobra CLIs and Agent Skills from Swagger 2.0, OpenAPI 3, google.api.http protobuf APIs, and policy-curated GraphQL. lathe init and lathe skill install support this workflow. Keep generic scaffolding, plugin loaders, GUI/TUI, API gateways, and hand-written SDK replacement out of scope.

  • Durable inputs are specs/sources.yaml, cli.yaml, declared specs, and optional overlays and Skill includes. Pinned Git sources are reproducible; local_path follows the referenced working tree, and sync state must record and validate its resolved path.
  • Change inputs or the generator, never hand-edit generated files. Do not commit internal/generated/, .cache/, example build artifacts, or ad-hoc generated skills/<cli-name>/ in this repository. Starter repositories have their own generated-output policy.
  • Follow CONTRIBUTING.md for contribution scope, Go conventions, Conventional Commits, and DCO sign-off. Use live code and Makefile targets to check documentation claims.

Architecture boundaries

See docs/architecture.md for package ownership and request flow.

  • cmd/lathe and internal/lathecmd orchestrate generation; internal/sourceconfig, internal/specsync, internal/codegen/**, and internal/overlay own its pipeline. internal/projectinit owns initialization; internal/latheskill owns the bundled Lathe Skill.
  • Generated runtime.CommandSpec declarations cross into the runtime through generated.Mount, alongside compiled workflows and bundled capabilities. pkg/runtime must not depend on internal/codegen/** or read raw specs, overlays, or sync caches.
  • Overlays are codegen-time inputs that can alter command semantics; compile them into runtime declarations without introducing overlay concepts at runtime.
  • pkg/config, pkg/runtime, pkg/lathe, and pkg/skillbundle are downstream-facing, compatibility-sensitive packages. internal/** is implementation-only.

Read the full file on GitHub · 66 lines

Changes

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.

  1. 10d ago Changed · +1 lines · +37 tokens per session 7e08a24db76e
  2. 25d ago Changed · +19 lines · +345 tokens per session e13bb2662566
  3. 1mo ago Changed · +6 tokens per session d24c99ce2801
  4. 2mo ago Changed · -53 lines · -850 tokens per session 23fd46aecba2
  5. 2mo ago First seen · 99 lines · 1,909 tokens per session scan A 97818165b065

Subscribe to this mod's changes

lathe CLAUDE.md is an instructions file published in the GitHub repository lathe-cli/lathe (87 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,447 tokens to every session, about $0.0058 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 2026-08-30.

Related

lathe CLAUDE.md compared with instructions from other repositories

lathe CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lathe CLAUDE.mdlathe-cli/latheInstructions file87yesterdayApache-2.0A1,447Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode