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/kortix-ai/agent-computer-use/claude-mdgit clone --depth 1 https://github.com/kortix-ai/agent-computer-useWrote 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/kortix-ai/agent-computer-use/claude-md)<a href="https://agentmods.dev/instructions/kortix-ai/agent-computer-use/claude-md"><img src="https://agentmods.dev/badge/instructions/kortix-ai/agent-computer-use/claude-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 | $0.00956 | $0.00956 |
| Opus 5 | $0.00478 | $0.00478 |
| Sonnet 5 | $0.00191 | $0.00191 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
agent-computer-use 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 5d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-computer-use
Computer use CLI for AI agents. Built with Rust, distributed via npm.
Repo structure
agent-computer-use/
├── cli/ Rust CLI (Cargo workspace)
│ ├── src/ Main binary, handlers, actions, snapshot, wait, DSL parser
│ └── crates/
│ ├── agent-computer-use-core/ Platform trait, AccessibilityNode, Selector, element utils
│ ├── agent-computer-use-macos/ macOS backend (AXUIElement, CGEvent, batch attribute fetch)
│ ├── agent-computer-use-cdp/ CDP bridge for Electron apps (WebSocket, DOM walker, JS interaction)
│ ├── agent-computer-use-linux/ Linux backend (AT-SPI2)
│ ├── agent-computer-use-windows/ Windows backend (UIAutomation)
│ └── agent-computer-use-mcp/ MCP server wrapper
├── docs/ Next.js docs site
├── benchmark/ E2E benchmarks, stress tests, comparison
├── bin/ JS wrapper + precompiled binaries
├── docker/ Cross-compilation Dockerfiles
├── scripts/ Setup, build, bench scripts
└── .github/ CI/CD workflows
Quick reference
pnpm setup # first-time setup (checks deps, builds, installs)
pnpm build # build CLI (release)
pnpm test # run Rust tests
pnpm lint # cargo fmt --check + clippy
pnpm format # auto-format Rust + JS/TS
pnpm dev # start docs dev server
pnpm check # lint + test (pre-commit)
pnpm bench # criterion micro-benchmarks
pnpm bench:e2e # real-world app benchmarks
pnpm bench:stress # reliability stress test
pnpm bench:diff # compare benchmark runs
Working on the CLI
Rust code lives in cli/. The workspace has:
agent-computer-use(crate) — produces theagent-cubinary, CLI args, handlersagent-computer-use-core— platform-agnostic types (Platform trait, AccessibilityNode, Selector, element utilities)agent-computer-use-macos— macOS backend (AXUIElement, CGEvent, batchAXUIElementCopyMultipleAttributeValues)agent-computer-use-cdp— CDP bridge (auto-detects Electron, auto-relaunches with debug port, WebSocket connection caching)
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.
- 5d ago First seen · 91 lines · 956 tokens per session scan A 24f742dd873b
agent-computer-use CLAUDE.md is an instructions file published in the GitHub repository kortix-ai/agent-computer-use (55 stars, last pushed 3mo ago), licensed MIT. It adds 956 tokens to every session, about $0.0048 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
wolffish-app AGENTS.md
AGENTS.md instructions for thewolffish/wolffish-app, covering wolffish — agent guide, stack, project layout, folder convention — one thing per folder and data location — /.wolffish/ is the entire footprint.
microsandbox AGENTS.md
AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.
warp AGENTS.md
AGENTS.md instructions for warpdotdev/warp, covering agents.md, development commands, build and run, running with local warp-server and connect to server on default port 8080.
terax-ai AGENTS.md
AGENTS.md instructions for crynta/terax-ai, a project described as: Lightweight (7MB) Terminal-first AI-native dev workspace.
swift-tui AGENTS.md
AGENTS.md instructions for SwiftTUI/swift-tui, covering agents.md, build & test commands, architecture (one-page summary), development guidelines and code style.
best-claude-hud AGENTS.md
Instructions for GaoSSR/best-claude-hud, covering project agent instructions and release work.