What is machine-mcp AGENTS.md?

A set of instructions for using machine-mcp, a server that lets an agent work with files and commands on the user's laptop. It provides tools for checking the machine, running commands, reading and writing files, and recording terminal activity.

Use it when working through machine-mcp to check the environment, run Copilot, Git, FFmpeg, or compiler commands, and manage files in its permitted workspace.

It gives the agent the machine-specific rules and workspace limits it needs to use these tools safely and correctly.

How AndreaGriffiths11/machine-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to AndreaGriffiths11/machine-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.

Copy the file

curl -O https://raw.githubusercontent.com/AndreaGriffiths11/machine-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/AndreaGriffiths11/machine-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/andreagriffiths11/machine-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/andreagriffiths11/machine-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/andreagriffiths11/machine-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/andreagriffiths11/machine-mcp/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/andreagriffiths11/machine-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/andreagriffiths11/machine-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 531 This file is loaded in full into every session.

When invoked 531 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00531	$0.00531
Opus 5.5	$0.00212	$0.00212
Sonnet 5.5	$0.00106	$0.00106
Haiku 4.5	$0.00053	$0.00053

Measured 2mo ago against content hash 5398b3c3f89a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

machine-mcp AGENTS.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.

AGENTS.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent notes for machine-mcp

You are using the human's laptop through this MCP server. stdio means you are already inside their process. Do not invent a pairing step. Do not ask them to log into GitHub, Copilot, or Cursor through these tools.

What this is

Laptop-side tools: status, run, record_terminal, write_file, read_file. Workspace root is MACHINE_MCP_WORKSPACE or ~/machine-mcp-workspace. File tools cannot leave that root.

This does not replace Grok Bot Computers or Local execution. Those are a different control path. This server is the tool process on the machine they already use.

How to use the tools

Call status first. Note OS, cwd, workspace, and whether copilot, ffmpeg, and git are on PATH.
Put demo scripts and output files in the workspace with write_file / read_file. Relative paths only.
Use run for commands that should execute in the workspace (copilot, git, ffmpeg, compilers). Pass a real argv string. Timeouts cap at 120 seconds.
record_terminal will not produce a video. On Linux, install ffmpeg if needed and run its suggested command yourself via run. Other platforms return an unsupported-platform error. Do not fake a recording.

Never

Never read SSH keys, Copilot config dirs, .env files, credential files, cookies, or token stores.
Never run copilot login, gh auth login, or any login/device-code flow. Copilot CLI on this machine is already signed in. Use it.
Never print, log, or echo secrets. run redacts github_pat_ and AWS key shapes if they leak into stdout. Do not try to bypass that.
Never pass parent-directory segments or absolute paths to write_file / read_file.
Never start an HTTP listener or bind a port. v1 is stdio only.
Never git push or force-push unless the human explicitly asked in this turn.

Copilot CLI demos

Record or script Copilot CLI demos on this machine because it is already signed in. Prefer run with copilot on PATH. Keep demo artifacts inside the workspace. If you need a screen capture, use the ffmpeg command from record_terminal on Linux. Do not pretend a file exists if you did not capture one.

Read the full file on GitHub · 34 lines

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.

2mo ago First seen · 34 lines · 531 tokens per session scan A 5398b3c3f89a

Subscribe to this mod's changes

machine-mcp AGENTS.md is an instructions file published in the GitHub repository AndreaGriffiths11/machine-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 531 tokens to every session, about $0.0021 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.

machine-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
machine-mcp AGENTS.mdAndreaGriffiths11/machine-mcp	Instructions file	2	2mo ago	MIT	A	531	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

machine-mcp: Instructions file for Codex