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.
npx agentmods add instructions/remorses/usecomputer/agents-mdgit clone --depth 1 https://github.com/remorses/usecomputerWhat 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 | $0.02375 | $0.02375 |
| Opus 5 | $0.01188 | $0.01188 |
| Sonnet 5 | $0.00475 | $0.00475 |
| Haiku 4.5 | $0.00237 | $0.00237 |
Grade A, and why
usecomputer 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 2d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
usecomputer agent notes
Goal
usecomputer is a macOS desktop automation CLI for AI agents.
The package should expose stable, scriptable computer-use commands (mouse,
keyboard, screenshot, clipboard, window actions) backed by a native Zig N-API
module, with behavior aligned to CUA command semantics.
Source of truth for command behavior
CUA references are the primary behavioral source of truth for command semantics and edge cases. When implementing or adjusting command behavior, always compare against these files first:
- CUA macOS handler (core command behavior): https://github.com/trycua/cua/blob/main/libs/python/computer-server/computer_server/handlers/macos.py
- CUA server command routing and payload shapes: https://github.com/trycua/cua/blob/main/libs/python/computer-server/computer_server/main.py
Implementation note: this package does not use pyobjc. We implement the same
command behavior using Zig + native macOS APIs.
Native implementation dependencies
- zig-objc (Objective-C runtime bindings used by this package): https://github.com/mitchellh/zig-objc
- napigen (N-API glue used by Zig module exports): https://github.com/cztomsik/napigen
Cross-platform input backend reference
For mouse/keyboard parity across macOS, Windows, and Linux, use pynput as a
behavior and backend reference (do not copy code directly; keep implementation
native in Zig):
- Repository: https://github.com/moses-palmer/pynput
- Mouse base API (undefined unit semantics for scroll): https://github.com/moses-palmer/pynput/blob/master/lib/pynput/mouse/_base.py
- macOS backend (
CGEventCreateScrollWheelEvent): https://github.com/moses-palmer/pynput/blob/master/lib/pynput/mouse/_darwin.py - Windows backend (
SendInputwheel/hwheel,WHEEL_DELTA): https://github.com/moses-palmer/pynput/blob/master/lib/pynput/mouse/_win32.py - X11 backend (button-based scroll 4/5/6/7 with XTest): https://github.com/moses-palmer/pynput/blob/master/lib/pynput/mouse/_xorg.py
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.
- 2d ago First seen · 259 lines · 2,375 tokens per session scan A 348c9148f9a5
usecomputer AGENTS.md is an instructions file published in the GitHub repository remorses/usecomputer (315 stars, last pushed 1mo ago), licensed MIT. It adds 2,375 tokens to every session, about $0.0119 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.