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 skills/hmbown/codewhale/computer-usenpx skills add Hmbown/Codewhale --skill computer-usegit clone --depth 1 https://github.com/Hmbown/CodewhaleWrote 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/skills/hmbown/codewhale/computer-use)<a href="https://agentmods.dev/skills/hmbown/codewhale/computer-use"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/computer-use.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 | $0.00028 | $0.00389 |
| Opus 5 | $0.00014 | $0.00195 |
| Sonnet 5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
computer-use 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 today.
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.
What it actually says
Computer use
You can see this machine's screen and operate its mouse and keyboard
through the computer MCP server. Work in a tight look-act-verify
loop and never act blind.
The loop
- Look: call
mcp_computer_screenshotfirst. The image arrives as a vision block; read positions from it, never guess coordinates. - Act: exactly one action per turn —
mcp_computer_click,mcp_computer_type_text,mcp_computer_press_key, ormcp_computer_scroll. Coordinates are pixels in the latest screenshot from the top-left, matchingmcp_computer_screen_size; the server scales them to the display. - Verify: screenshot again after every action that should change something visible. If the screen did not change as expected, stop and report instead of retrying harder.
Safety rules
- Every action tool asks for approval unless the session runs in Always-approve posture. Say what you are about to click or type before the approval prompt appears.
- Never type passwords, secrets, or one-time codes. If a login screen appears, stop and hand control back to the user.
- Never dismiss system permission dialogs (Accessibility, Screen Recording) yourself. If the server reports a missing permission, tell the user exactly which toggle to flip and stop.
- Prefer keyboard over mouse (Tab, arrows, Enter) — it is precise and does not depend on pixel coordinates.
- If a tool reports
unsupported_platformormissing_helper, stop and relay the server's message verbatim.
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.
- today First seen · 39 lines · 28 tokens per session scan A 4c97d0e7250b
computer-use is a skill published in the GitHub repository Hmbown/Codewhale (40,916 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 389 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
best-of-n
Generate a small set of independent candidate solutions in worktrees, judge them against one explicit rubric, and apply the winner only after PASS verification.
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale fleet runs and workers.
handoff
Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / "pass the baton" / "hand off", or a long-running operation needs a durable state checkpoint.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-close-issues
Close resolved Codewhale issues only after verifying the landed commit/behavior, with a positive crediting comment; never from title alone.