Borrowing it
Nothing to install: this file belongs to astraclawteam/agent-computer-use-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/astraclawteam/agent-computer-use-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/astraclawteam/agent-computer-use-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/astraclawteam/agent-computer-use-mcp/agents-md)<a href="https://agentmods.dev/instructions/astraclawteam/agent-computer-use-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/astraclawteam/agent-computer-use-mcp/agents-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 | $0.01267 | $0.01267 |
| Opus 5 | $0.00633 | $0.00633 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
agent-computer-use-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 6d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Worker Rules
This repository is maintained by a large team and many contributors are AI agents. These rules are mandatory for every automated or human-assisted coding session.
Read Order
Before changing files, read:
AGENTS.mdREADME.mdCONTRIBUTING.md- The tests covering the files you plan to edit
If a host product provides a stricter instruction, follow the stricter rule.
Repository Purpose
agent-computer-use-mcp is a local MCP module for Gateway-managed computer use. The public contract is the computer.* MCP tool surface. The implementation may use cua-driver mcp, OCR, native desktop helper apps, and overlays internally, but clients should depend on the MCP contract rather than private internals.
Project Structure
src/: MCP server, tool definitions, provider router, driver/OCR/overlay integration, phase smoke scripts.test/: Node test runner tests. Every behavior change needs a focused test here.public/: browser demo and overlay visual prototype assets.gateway-overlay/: Windows user-only overlay helper.native-lab/: Windows native target app used for real desktop control validation.ocr-sidecar/: OCR sidecar experiments and ONNX Runtime integration.docs/: long-form governance or architecture docs.scripts/: maintainer automation scripts..github/: PR template, CODEOWNERS, CI, and GitHub metadata.
Branch And PR Rules
- Non-admin contributors and AI workers must not push directly to
main. - Repository administrators may push directly to
mainfor repository bootstrap, governance repair, or emergency recovery. - Work on short-lived branches named
type/short-topic, for examplefeat/ocr-region-cacheorfix/mcp-health-error. - Every change must go through a pull request.
- Every non-admin PR must have at least one maintainer approval before merge.
- CODEOWNERS review is required for protected areas.
- All required checks must pass before merge.
- Do not require approval from a different person than the latest pusher; this repository intentionally disables GitHub's "require approval of the most recent reviewable push" condition.
- Use squash merge unless maintainers explicitly choose otherwise.
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.
- 6d ago First seen · 109 lines · 1,267 tokens per session scan A a22afcb7bc36
agent-computer-use-mcp AGENTS.md is an instructions file published in the GitHub repository astraclawteam/agent-computer-use-mcp (1 stars, last pushed 24d ago), licensed MIT. It adds 1,267 tokens to every session, about $0.0063 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.