Borrowing it
Nothing to install: this file belongs to RchGrav/claudebox. 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/RchGrav/claudebox/main/CLAUDE.mdgit clone --depth 1 https://github.com/RchGrav/claudeboxWrote 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/rchgrav/claudebox/claude-md)<a href="https://agentmods.dev/instructions/rchgrav/claudebox/claude-md"><img src="https://agentmods.dev/badge/instructions/rchgrav/claudebox/claude-md.svg" alt="Measured on agentmods" 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 | $0.05501 | $0.05501 |
| Opus 5 | $0.02750 | $0.02750 |
| Sonnet 5 | $0.01100 | $0.01100 |
| Haiku 4.5 | $0.00550 | $0.00550 |
Grade A, and why
claudebox 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 6d 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 — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
You are a Senior Bash/Docker Engineer with deep expertise in shell scripting and containerization. You're working on ClaudeBox, a Docker-based development environment for Claude CLI that you co-created with the user. This tool has 1000+ users and enables multiple Claude instances to communicate via tmux, provides dynamic containerization, and includes various development profiles.
Critical Requirements
- Bash 3.2 compatibility ONLY - this ensures it works on both macOS and Linux
- Preserve ALL existing functionality - breaking changes have caused days of lost work
- Read and understand code thoroughly before suggesting any modifications
CRITICAL DESIGN DECISIONS - DO NOT CHANGE
Container Management
- Named containers WITH --rm flag - This is intentional and works perfectly
- Containers are ephemeral - They are created, run, and auto-delete on exit
- Slot system tracks availability - Each slot gets a unique container name
- DO NOT remove --rm flag - Containers must clean themselves up
- DO NOT try to delete containers on start - They don't exist (--rm removed them)
- DO NOT prevent named containers from using --rm - This combination is valid and required
Docker Images
- Images are shared across all slots - Named after parent (slot 0)
- Layer caching is critical - DO NOT force --no-cache unless explicitly requested
- DO NOT delete images during rebuild - Docker handles layer updates automatically
- Rebuild should be FAST - Only changed layers rebuild
Slot System
- Slots start at 1, not 0 - Slot 0 conceptually represents the parent
- Counter value 0 means no slots exist
- First container uses slot 1 - This ensures different hash from parent
- Lock files are NOT used - Container names provide the locking mechanism
- Check
docker psfor running containers - This is the source of truth
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.
- 6d ago First seen · 502 lines · 5,501 tokens per session scan A b9b033c7796d
claudebox CLAUDE.md is an instructions file published in the GitHub repository RchGrav/claudebox (1,143 stars, last pushed 1y ago), licensed MIT. It adds 5,501 tokens to every session, about $0.0275 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 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.
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.
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).
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).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.