Borrowing it
Nothing to install: this file belongs to b34nst4lk/vestibule. 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/b34nst4lk/vestibule/main/CLAUDE.mdgit clone --depth 1 https://github.com/b34nst4lk/vestibuleWrote 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/b34nst4lk/vestibule/claude-md)<a href="https://agentmods.dev/instructions/b34nst4lk/vestibule/claude-md"><img src="https://agentmods.dev/badge/instructions/b34nst4lk/vestibule/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.
<a href="https://agentmods.dev/instructions/b34nst4lk/vestibule/claude-md"><img src="https://agentmods.dev/badge/instructions/b34nst4lk/vestibule/claude-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 | $0.01504 | $0.01504 |
| Opus 5 | $0.00752 | $0.00752 |
| Sonnet 5 | $0.00301 | $0.00301 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
vestibule 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 8d 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 — 138 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.
Project Overview
vestibule is a new Python 3.13 project using uv for package management. The project is in its initial scaffold stage.
Commands
# Run the application
uv run python main.py
# Add a dependency
uv add <package-name>
# Add a dev dependency
uv add --dev <package-name>
# Run a command in the project environment
uv run <command>
Architecture
- Entry point:
main.py— currently a minimal scaffold printing a greeting - Configuration:
pyproject.toml— defines project metadata and dependencies (PEP 621) - Python version: 3.13 (specified in
.python-version)
Notes
- The project uses
uv— preferuv run,uv addoverpipandpythondirectly README.mdis populated — keep it in sync as features are added
FastMCP integration notes
These are hard-won facts about the mcp library (FastMCP). Read the public API
surface and source before touching library internals — do not reach into
_private attributes.
- Version:
mcp>=1.28.1(seepyproject.toml). Re-validate these notes when bumping the dependency. - Upstream docs: https://github.com/modelcontextprotocol/python-sdk
Public API surface (use these, not private attrs)
list_tools()— returns registered tools (use for existence checks)call_tool(name, arguments)— invoke a tooladd_tool()/remove_tool()/tool()— register/unregisterlist_prompts(),list_resources(),read_resource(),get_prompt()
Error-wrapping behavior (critical)
- FastMCP wraps all tool exceptions — pydantic argument-validation errors
AND
TypeError— intoToolError("Error executing tool {name}: ..."). - Consequence: argument-validation errors are not
INVALID_PARAMS; they surface asToolError. ATypeErrorbranch in a handler is only reachable via a non-FastMCP fallback path (e.g. callingtool.handler(**args)directly). - To distinguish protocol errors from business errors, pre-check tool existence
(via
list_tools()) and raiseToolErrorfor unknown tools so the transport maps it tomethod_not_found.
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.
- 8d ago First seen · 138 lines · 1,504 tokens per session scan A fcecf6d86a7b
vestibule CLAUDE.md is an instructions file published in the GitHub repository b34nst4lk/vestibule (0 stars, last pushed 24d ago), licensed MIT. It adds 1,504 tokens to every session, about $0.0075 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.
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.
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.