What is lean-md CLAUDE.md?

Project instructions for lean-md, a Rust project with strict rules for reading, editing, testing, and running commands. They require the project's specific tools and test command.

Use them when modifying or testing the lean-md repository.

They prevent common workflow mistakes, such as using the wrong test runner, editing method, command format, or formatting step.

How dasTholo/lean-md configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dasTholo/lean-md. 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/dasTholo/lean-md/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dasTholo/lean-md

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dastholo/lean-md/claude-md/github.svg)](https://agentmods.dev/instructions/dastholo/lean-md/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dastholo/lean-md/claude-md"><img src="https://agentmods.dev/badge/instructions/dastholo/lean-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dastholo/lean-md/claude-md"><img src="https://agentmods.dev/badge/instructions/dastholo/lean-md/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,142 This file is loaded in full into every session.

When invoked 1,142 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.

Model	Per session	Once invoked
Fable 5.1	$0.01142	$0.01142
Opus 5.5	$0.00457	$0.00457
Sonnet 5.5	$0.00228	$0.00228
Haiku 4.5	$0.00114	$0.00114

Measured 2mo ago against content hash 5afa2e2a2bb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lean-md 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 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.

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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Startup

@AGENTS.md

Project Hard Rules

lean-ctx tool-discipline (ctx_read/ctx_shell/ctx_search/ctx_tree mapping, read modes, CEP, dense output) is loaded globally via ~/.claude/CLAUDE.md. Full project rules: AGENTS.md + the vendored addon contract docs/CONTRACT.md. Not repeated here — only project deltas below.

Tests: always cargo nextest run, never cargo test
Edits: Non-symbol → ctx_read(mode=anchored) → ctx_patch (anchored, patch by LINE:HASH, never re-emit old text). ctx_edit only tiny-span/replace-all; symbol rename/move → ctx_refactor. Anchored is the default even over native Edit.
Shell — no &&/||/; chaining: every command is its own invocation. Replace cd <dir> && cargo … with cargo … --manifest-path <dir>/Cargo.toml; resolve conditional gates into separate steps with an explicit "Expected:" check.
Deferred-tool reflex: see ~/.claude/CLAUDE.md Hard Rules — always ToolSearch(query="select:...") before any Bash workaround.
Before git add (per changed file): cargo fmt (this is a standalone crate; Cargo.toml + src/ live at the repo root).
No worktrees — work directly on the current branch
No Brief-/Report-Files: ctx_session
Rendering lmd-skills (this dev-repo): die SKILL.md-Stubs zeigen auf das MCP-Tool ctx_md_render. Es liegt im Gateway-Katalog (dorthin delegiert ctx_read), steht dem Agenten aber nicht als direktes Tool zur Verfügung. Rendere Phasen deshalb direkt über die CLI; probiere nicht vorher MCP / ctx_call: cargo run -q --bin lean-md -- render --skill <skill> --phase <phase> --consumer=ai (Companion statt Phase: --companion <name>). Kein Release-Build — cargo run genügt (nach dem ersten Compile gecached).
.lmd.md lesen: ctx_read liefert Roh-Source wie bei jeder anderen Datei; Rendern ist explizit und opt-in (CLI oben bzw. ctx_md_render).
PATH-lean-md ist ein Shim aufs released Addon-Binary: ~/.local/bin/lean-md löst das lean-ctx-managed Binary auf (…/addons/bin/lean-md/<version>/…) und folgt addon update automatisch — kein cargo-Drift. Es spiegelt daher nur den veröffentlichten Stand, nicht deine ungecommitteten src/**-/Seed-Änderungen. Sobald du am Binary etwas änderst, gilt für JEDE Verifikation (render / skill / source / check) das lokale cargo-Target — cargo run -q --bin lean-md -- … bzw. ./target/… —, nie das PATH-lean-md. Shim = Consumer-/Released-Pfad, cargo-Target = Dev-Pfad. (Ein cargo install gehört bewusst NICHT auf den PATH: es würde still altern und genau den Versions-Skew erzeugen, den der Shim vermeidet.)

Read the full file on GitHub · 69 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.

2mo ago First seen · 69 lines · 1,142 tokens per session scan A 5afa2e2a2bb9

Subscribe to this mod's changes

lean-md CLAUDE.md is an instructions file published in the GitHub repository dasTholo/lean-md (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,142 tokens to every session, about $0.0046 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.

lean-md CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
lean-md CLAUDE.mddasTholo/lean-md	Instructions file	5	1mo ago	Apache-2.0	A	1,142	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

lean-md: Instructions file for Claude Code