Borrowing it
Nothing to install: this file belongs to bird/sandbox-mcp. 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/bird/sandbox-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/bird/sandbox-mcpWrote 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/bird/sandbox-mcp/claude-md)<a href="https://agentmods.dev/instructions/bird/sandbox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bird/sandbox-mcp/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/bird/sandbox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bird/sandbox-mcp/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 | $0.00355 | $0.00355 |
| Opus 5.5 | $0.00142 | $0.00142 |
| Sonnet 5.5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
sandbox-mcp 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.
What it actually says
sandbox-mcp
MCP server for Apple Container sandboxes. Single-file Python server (sandbox_mcp_server.py) using FastMCP.
Project structure
sandbox_mcp_server.py # Sandbox class, SandboxManager, MCP tools
cmd/sandbox-ctl/ # In-container CLI for spawning sibling containers (Go)
pyproject.toml # uv/hatchling packaging, entry point: sandbox-mcp
Containerfile.mcp-dev # Alpine 3.23 image with Python/Node/Go/Rust
tests/ # pytest test suite
Key patterns
- Shell quoting: Always use
_sq(value)for any user-provided string interpolated into shell commands. Never use f-string quotes. - Env key validation: Use
_validate_env_key(key)before any env var operations. - Audit logging: Pass
audit=Falsefor internal/diagnostic commands to keep the audit log clean. - Port forwarding: Uses
container exec -i <name> ncproxy, NOT-pflag (broken in Apple Containers v0.9.0). - Profile tuple:
_get_profile()returns(cpus, memory, virtualization)— 3-tuple, unpack accordingly.
Running
uv run sandbox-mcp # stdio mode (for MCP clients)
python3 sandbox_mcp_server.py # also works
Testing
uv run pytest tests/ -v
Adding a new tool
- Add manager method to
SandboxManagerclass - Add
@mcp_server.tool()function that calls the manager method - Run tests
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 · 41 lines · 355 tokens per session scan A 389201c6d2dd
sandbox-mcp CLAUDE.md is an instructions file published in the GitHub repository bird/sandbox-mcp (1 stars, last pushed 8mo ago), licensed MIT. It adds 355 tokens to every session, about $0.0014 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.