leerie: Instructions file for Claude Code

CLAUDE.md

leerie CLAUDE.md is an instructions file for Claude Code from enricai/leerie. It costs 7,385 tokens per session, scanned A, original, MIT.

Repository instructions for Leerie, a Python tool that coordinates parallel Claude Code workers in isolated Git worktrees and containers. They describe its architecture and the documents agents must read before changing it.

In plain words
What is it for?
Use them when changing Leerie’s orchestration, worktree isolation, container execution, dependencies, or implementation documents.
Why use it?
They explain the safety boundaries and runtime setup needed to modify an orchestrator that runs multiple workers.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is enricai/leerie's own configuration. It tells Claude Code how to work on leerie 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 leerie configures →

Reuse

Borrowing it

Nothing to install: this file belongs to enricai/leerie. 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/enricai/leerie/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/enricai/leerie

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 leerie CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/enricai/leerie/claude-md"><img src="https://agentmods.dev/badge/instructions/enricai/leerie/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,385 This file is loaded in full into every session.
When invoked 7,385 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 $0.07385 $0.07385
Opus 5 $0.03692 $0.03692
Sonnet 5 $0.01477 $0.01477
Haiku 4.5 $0.00739 $0.00739

Measured 9d ago against content hash bccdbd395e65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

leerie 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 9d 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 · 514 lines

How it starts

The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working in this repository. Read docs/DESIGN.md before touching architecture; read docs/IMPLEMENTATION.md before touching code surface; read this file first.

Tech stack

Python 3.10+, stdlib-preferred orchestrator (runtime deps pinned in requirements.txt and listed in docs/IMPLEMENTATION.md §0). The orchestrator shells out to claude -p (Claude Code CLI, on the user's subscription — no API key) and uses git worktrees for parallel implementer isolation. pytest is the only dev dependency.

Leerie runs inside a container. The leerie launcher shells out to nerdctl run to start a container per run (DESIGN §6 Worker subtree termination). The orchestrator runs as PID 1 inside; every worker (and every Bash tool call those workers make) lives in the same PID namespace. On Ctrl-C / SIGTERM / SIGKILL / crash, the kernel reaps the namespace — the abnormal-exit cleanup guarantee is the container boundary, not Python signal handling.

Runtime: containerd + nerdctl. On Linux, native. On macOS, via Colima (a Lima-managed Linux VM). See docs/INSTALL.md for per-OS install steps.

Python is provisioned inside the container by the image (Python 3 from Debian 13). The launcher itself is a portable bash script; it no longer needs uv or a host Python. See docs/IMPLEMENTATION.md §0 (install surface) and §0.5 (container shape).

All control flow lives in one file: orchestrator/leerie.py. The launcher (a portable bash script) and the Dockerfile are the only other moving parts on the orchestrator side. The orchestrator is deliberately kept as a single module rather than split across packages — the design goal is that you can read the whole control flow top-to-bottom in one sitting. Stdlib-preferred on the Python side — runtime deps are pinned in requirements.txt and listed in docs/IMPLEMENTATION.md §0; pytest is the sole dev dependency.

The three-layer rule (load-bearing — read first)

This repo deliberately separates theory, mechanism, and code, and the layers are top-down canonical: each layer derives from and conforms to the one above it.

Read the full file on GitHub · 514 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. 9d ago First seen · 514 lines · 7,385 tokens per session scan A bccdbd395e65

Subscribe to this mod's changes

leerie CLAUDE.md is an instructions file published in the GitHub repository enricai/leerie (10 stars, last pushed 6d ago), licensed MIT. It adds 7,385 tokens to every session, about $0.0369 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens