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/ifuryst/open-codex-computer-use/open-computer-usenpx skills add iFurySt/open-codex-computer-use --skill open-computer-usegit clone --depth 1 https://github.com/iFurySt/open-codex-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/skills/ifuryst/open-codex-computer-use/open-computer-use)<a href="https://agentmods.dev/skills/ifuryst/open-codex-computer-use/open-computer-use"><img src="https://agentmods.dev/badge/skills/ifuryst/open-codex-computer-use/open-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 | $0.00068 | $0.01230 |
| Opus 5 | $0.00034 | $0.00615 |
| Sonnet 5 | $0.00014 | $0.00246 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
open-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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Computer Use
Overview
Open Computer Use exposes Computer Use as a local CLI and stdio MCP server. It is not Codex.app-specific; adapt the commands and MCP config to the agent runtime you are operating in.
The macOS runtime requires macOS 14.0 or later. Windows and Linux use their own platform runtimes and are not subject to this macOS minimum.
It supports the same core tool surface across macOS, Linux, and Windows:
list_apps, get_app_state, click, perform_secondary_action, scroll,
drag, type_text, press_key, and set_value.
Core Workflow
- On macOS, run
sw_vers -productVersionbefore invoking the CLI and require macOS 14.0 or later. On older versions, explain that the runtime cannot launch; do not recommenddoctoror permission changes as a fix for binary incompatibility. - Check the CLI is installed with
open-computer-use -horocu -h. If installation or setup is missing, read references/installation.md. - On supported macOS versions, run
open-computer-use doctorbefore the first real GUI task. If permissions are missing, ask the user to approve Accessibility and Screen Recording in the onboarding UI. - Inspect available apps before acting:
open-computer-use call list_apps. - Capture current UI state with
open-computer-use call get_app_state --args '{"app":"TextEdit"}'. The default state is usually enough for UI operation. - When the task needs longer semantic text, such as chat history, email bodies, document text, or long form content, call
get_app_statewithtext_limit: 1000ortext_limit: "max". - When visible long pages or lists appear incomplete even after scrolling, call
get_app_statewith a largermax_tree_nodesormax_tree_depth. - Prefer element-targeted actions using
element_indexfrom the latestget_app_stateresult. - For multi-step CLI work, use
open-computer-use call --calls '<json-array>'so one process can reuse the latest element index mapping. - For agent runtimes that support local MCP servers, configure
open-computer-use mcporocu mcpand call the exposed Computer Use tools directly. Read references/usage.md. - If communication, permission, or desktop-session access fails, read references/troubleshooting.md.
What ships with it
4 files 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.
- 4d ago First seen · 84 lines · 68 tokens per session scan A 3f9521ebfa03
open-computer-use is a skill published in the GitHub repository iFurySt/open-codex-computer-use (1,893 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 1,230 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 2026-08-30.
Other skills, from other repositories
macos-harness
Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…
axstream
Fast deterministic macOS UI automation via replayable macros. Use BEFORE driving any macOS app's UI by hand (clicking/typing via computer-use or screenshots) — if a macro exists, replay finishes the task in seconds with no per-step reasoning; after doing a UI task manually, save it as a macro so the next run is fast.…
nova-grounding
AX-first reading and grounded activation workflow for Nova desktop automation on macOS and Windows. Use for reading UI, clicking controls, OCR fallback, screenshots, and coordinate input without guessing.
web-navigator
Web 浏览器自动化路由规则。通过 webnavigator 将 Web 场景路由到 Playwright MCP 或 mcp-chrome。.
computer-use
Linux/X11 desktop control — inspect, click, type into visible windows via AT-SPI + xdotool. Returns @eN refs from the focused window's accessibility tree.
chrome
Google Chrome heuristics for background-computer-use. Use when the user asks you to navigate, scroll, click links, fill forms, or otherwise drive Chrome without stealing focus. Also applies to Chromium-family browsers (Brave, Edge, Arc) that share the same AppleScript JavaScript execution primitive.