agentmods.dev

sandbox-mcp CLAUDE.md

sandbox-mcp CLAUDE.md is an instructions file for coding agents from bird/sandbox-mcp. It costs 355 tokens per session, scanned A, original, MIT.

A project instruction file for a server that provides Apple Container sandboxes through MCP, a standard way for AI tools to call external services. It documents the project layout, coding rules, commands, and tests.

In plain words
What is it for?
Use it when developing, running, or testing the sandbox-mcp project, including its Python server and Go command-line tool.
Why use it?
It gives coding agents the project-specific rules they need before editing or testing the server. This helps prevent mistakes such as writing protocol output to the wrong place.

Instructions file

not rated 1 6mo ago A scan 355 tokens original MIT
View the source file bird/sandbox-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/bird/sandbox-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/bird/sandbox-mcp

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 sandbox-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bird/sandbox-mcp/claude-md.svg)](https://agentmods.dev/instructions/bird/sandbox-mcp/claude-md)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 355 This file is loaded in full into every session.
When invoked 355 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00355 $0.00355
Opus 5 $0.00178 $0.00178
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00036 $0.00036

Measured 4d ago against content hash 389201c6d2dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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 · 41 lines

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=False for internal/diagnostic commands to keep the audit log clean.
  • Port forwarding: Uses container exec -i <name> nc proxy, NOT -p flag (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

  1. Add manager method to SandboxManager class
  2. Add @mcp_server.tool() function that calls the manager method
  3. Run tests
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. 4d ago First seen · 41 lines · 355 tokens per session scan A 389201c6d2dd

Subscribe to this mod's changes

sandbox-mcp CLAUDE.md is an instructions file published in the GitHub repository bird/sandbox-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 355 tokens to every session, about $0.0018 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.

Apple Siliconai-agentsapple-containerizationclaude-codedeveloper-toolslinux-vm
Related

Other instructions, from other repositories

apfel CLAUDE.md

Instructions for Arthur-Ficial/apfel, covering apfel - project instructions, the golden goal, core product (this is what apfel is), byproducts (useful, but not the pitch) and readme.md structure rule.

Arthur-Ficial/apfel · 7,076 tokens

stenoai CLAUDE.md

Claude Code instructions for stenolabs/stenoai, covering claude.md, architecture, development commands, backend (python) and desktop app (electron).

stenolabs/stenoai · 8,179 tokens

speech-swift AGENTS.md

AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.

soniqo/speech-swift · 5,053 tokens

stenoai AGENTS.md

AGENTS.md instructions for stenolabs/stenoai, covering agents.md, code review rules, bundled binaries with an api, bare exit() in python and platform parity.

stenolabs/stenoai · 949 tokens

humla CLAUDE.md

Claude Code instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.

michaelwilhelmsen/humla · 19,981 tokens

humla AGENTS.md

AGENTS.md instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.

michaelwilhelmsen/humla · 6,738 tokens