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 skills add tykimos/cheliped-skills --skill computer-usegit clone --depth 1 https://github.com/tykimos/cheliped-skillsWrote 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/tykimos/cheliped-skills/computer-use)<a href="https://agentmods.dev/skills/tykimos/cheliped-skills/computer-use"><img src="https://agentmods.dev/badge/skills/tykimos/cheliped-skills/computer-use/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.
<a href="https://agentmods.dev/skills/tykimos/cheliped-skills/computer-use"><img src="https://agentmods.dev/badge/skills/tykimos/cheliped-skills/computer-use.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00169 | $0.02077 |
| Opus 5.5 | $0.00068 | $0.00831 |
| Sonnet 5.5 | $0.00034 | $0.00415 |
| Haiku 4.5 | $0.00017 | $0.00208 |
Grade A, and why
cheliped-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 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cheliped Computer Use (macOS)
Drive the local Mac from the terminal. One CLI takes a JSON array of commands and returns JSON — the same shape as the browser skill.
Output Envelope
Output is always a JSON array, one envelope per command, compact by default:
[{ "cmd": "screenshot", "ok": true, "result": { "path": "...", "scale": 2 } },
{ "cmd": "type", "ok": false, "error": { "code": "E_NO_PERMISSION", "message": "..." } }]
Each command runs even if a prior one fails (per-command isolation). Error code is one of E_NO_PERMISSION (Accessibility off), E_NO_CLICLICK, E_WRONG_FOCUS, E_DISABLED (escape hatch not enabled), E_BAD_ARG, E_UNKNOWN_CMD, E_TIMEOUT, E_UNKNOWN.
Flags (before the JSON arg): --pretty indents output; --allow-shell enables the run-shell / run-applescript escape hatches (off by default).
Setup
Built-ins (osascript, screencapture) need no install. Mouse control needs cliclick:
brew install cliclick
Permissions: the terminal/agent process must be granted Accessibility and Screen Recording in System Settings → Privacy & Security. The CLI now preflights Accessibility and returns E_NO_PERMISSION (instead of a silent no-op) when keyboard/mouse input would not be delivered; screenshots that come back near-uniform get a warning hinting at missing Screen Recording. Grant the permissions, then restart the terminal (permissions only apply to a freshly launched process).
Core Workflow: Observe-Act Loop
# 1. See the screen
node scripts/computer-cli.mjs '[{"cmd":"screenshot","args":["/tmp/now.png"]}]'
# 2. Act on what you saw (read the screenshot, then click / type)
node scripts/computer-cli.mjs '[{"cmd":"click","args":[640,400]},{"cmd":"type","args":["hello"]}]'
Read the screenshot with the Read tool, decide coordinates, then act. Re-screenshot to confirm.
Commands
Each row's Returns is the result object inside the envelope.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 125 lines · 169 tokens per session scan A e834477df4ce
cheliped-computer-use is a skill published in the GitHub repository tykimos/cheliped-skills (62 stars, last pushed 4mo ago), licensed MIT. It adds 169 tokens to every session and 2,077 once invoked, about $0.0007 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 2026-08-30.
cheliped-computer-use compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cheliped-computer-usetykimos/cheliped-skills | Skill | 62 | 4mo ago | MIT | A | 169 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |