Borrowing it
Nothing to install: this file belongs to heptafox/mcp-sandbox. 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/heptafox/mcp-sandbox/main/CLAUDE.mdgit clone --depth 1 https://github.com/heptafox/mcp-sandboxWrote 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/heptafox/mcp-sandbox/claude-md)<a href="https://agentmods.dev/instructions/heptafox/mcp-sandbox/claude-md"><img src="https://agentmods.dev/badge/instructions/heptafox/mcp-sandbox/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 | $0.00890 | $0.00890 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
mcp-sandbox 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 — 79 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.
What this is
A public MCP (Model Context Protocol) server of test fixtures for QA and
evals. Each tool returns deliberately distinctive output so a caller can prove a
response originated from this server, not from the model's own training/context.
Live at https://mcp.heptafox.com/mcp on AWS Lightsail (Ubuntu) behind
nginx + Let's Encrypt.
Commands
uv sync # install deps into .venv
uv run server.py # run server: guide at :8000/ , MCP at :8000/mcp
uv add <pkg> # add a dependency
There is no test framework — the tools are constant returns. To smoke-test a
tool in-memory (no network), use the FastMCP Client against the mcp object:
uv run python -c "
import asyncio; from fastmcp import Client; from server import mcp
async def m():
async with Client(mcp) as c:
print((await c.call_tool('identity', {})).content[0].text)
asyncio.run(m())"
Architecture
Single-process design: one uvicorn serves both the static guide and the MCP
endpoint, from server.py:
@mcp.toolfunctions are the MCP tools, ordered as a learning progression:identity(no auth, no params) →echo(params) →auth_check(Bearer token, fixed dev token inDEV_TOKEN).@mcp.custom_route(...)serves the static files inweb/(guide page, logo, robots.txt, sitemap.xml).mcp.run(transport="http", ...)= FastMCP streamable HTTP transport.
Routes (same port): GET / → guide page, POST /mcp → MCP endpoint.
New tools go in the same server.py as additional @mcp.tool functions — no
new files needed.
Gotchas
- Endpoint is
/mcp, no trailing slash. FastMCP 3.x 307-redirects/mcp/→/mcp, andmcp-remote(the Claude Desktop bridge) drops the POST body across that redirect → 404. Always configure clients with/mcp. - Bind
127.0.0.1only. nginx terminates TLS and proxies in; the app port is never exposed publicly.deploy/nginx.confproxies bothlocation /mcp(matches/mcpand the redirect) andlocation /(the guide), with buffering off and long read timeouts on/mcpfor streaming responses. - Reading the Authorization header needs
get_http_headers(include_all=True). FastMCP stripsauthorizationfrom the default header set — plainget_http_headers()will never see it (seeauth_check). web/index.htmlfills in the live URL via JS (location.origin), so the Claude config snippets show the real deployed URL with no hardcoding.
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 · 79 lines · 890 tokens per session scan A eb31034f536d
mcp-sandbox CLAUDE.md is an instructions file published in the GitHub repository heptafox/mcp-sandbox (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 890 tokens to every session, about $0.0044 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.
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.