computer-use

computer-use is a skill for Claude Code, Codex from iBerry420/gorked. It costs 57 tokens per session (572 once invoked), scanned A, original, MIT.

Instructions for controlling a desktop through screen reading and mouse or keyboard actions. It uses OCR, which reads text from screenshots, and normally keeps actions in a safe dry-run mode.

In plain words
What is it for?
Use it to inspect a screen, find buttons or text, click, type, scroll, drag, and confirm the result of desktop actions.
Why use it?
It helps an agent locate visible controls and verify UI state while reducing the risk of sending unintended input.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/iberry420/gorked/computer-use
Any agent
npx skills add iBerry420/gorked --skill computer-use
Clone the repo
git clone --depth 1 https://github.com/iBerry420/gorked

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for computer-use

README.md
[![agentmods](https://agentmods.dev/badge/skills/iberry420/gorked/computer-use.svg)](https://agentmods.dev/skills/iberry420/gorked/computer-use)
Your own site
<a href="https://agentmods.dev/skills/iberry420/gorked/computer-use"><img src="https://agentmods.dev/badge/skills/iberry420/gorked/computer-use.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 572 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.00572
Opus 5 $0.00028 $0.00286
Sonnet 5 $0.00011 $0.00114
Haiku 4.5 $0.00006 $0.00057

Measured 3d ago against content hash 22968314f353, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

.grok/skills/computer-use/SKILL.md · 56 lines

What it actually says

Computer use (Gorked MCP)

You have gorked MCP tools for vision + input control.

Safety

  • Default is dry_run (actions logged, OS input not sent).
  • Only call set_live_mode(true, confirm_phrase="I_ACCEPT_LIVE_CONTROL") when the user explicitly wants live control.
  • Prefer dry-run demos unless asked otherwise.

Monitors (important)

  • Screenshots capture the primary monitor only.
  • Do not request monitor 0 (virtual all-monitors) — blocked and wastes tokens.
  • Secondary displays (TV, etc.) are never included. The terminal may live on another screen; that is fine — still only primary is captured.

Workflow

  1. thought("…") — narrate what you will do (user-visible process).
  2. get_status() — confirm dry_run / monitor / output dir.
  3. analyze_screen() — OCR every text region with center_screen click targets.
  4. Act using centers from OCR:
    • click_text("Save") (preferred for labeled UI)
    • or mouse_click(x, y) with center_screen from the scene
    • click_and_type, type_text, hotkey, mouse_drag, mouse_scroll
  5. wait_ms between steps if the UI needs time.
  6. Re-run analyze_screen / find_text to verify state.
  7. thought(..., kind="result") when done.

Rules

  • Never invent coordinates. Always come from gorked OCR centers.
  • Keep batches small; re-observe after important clicks.
  • Record reasoning with thought so the user sees your process.
  • Artifacts land in output/: annotated_*.png, scene_*.json, mcp_thoughts.jsonl.

Tool map

Tool Purpose
analyze_screen Capture + OCR boxes + centers
find_text / click_text Locate / click a label
mouse_click / mouse_move / mouse_drag Pointer
type_text / click_and_type / hotkey Keyboard
set_live_mode Toggle real input (gated)
thought Visible chain-of-thought
Changes

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.

  1. 3d ago First seen · 56 lines · 57 tokens per session scan A 22968314f353

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository iBerry420/gorked (1 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 572 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens