unix_computer_use

unix_computer_use is a skill for Claude Code from razzant/ouroboros. It costs 33 tokens per session (1,710 once invoked), scanned A, original, MIT.

A set of tools for viewing and controlling macOS or Linux desktops, either on the same computer or on configured remote machines.

In plain words
What is it for?
It helps with supervised desktop tasks such as taking screenshots, clicking, typing, and managing local or remote connections.
Why use it?
It gives an agent a consistent way to inspect screens and perform mouse and keyboard actions without manually converting image coordinates.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Good fit It helps with supervised desktop tasks such as taking screenshots, clicking, typing, and managing local or remote connections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/razzant/ouroboros/unix_computer_use
About the project

Ouroboros is a general-purpose AI agent that maintains its identity, memory, and task history across restarts while working on external projects and coordinating specialist agents. It runs as a desktop application or headless command-line tool, using configured remote APIs or a local model for inference. The catalogue skills support working with or modifying Ouroboros.

razzant/ouroboros · 1,279 stars · on GitHub · ouroboros-agent.ai

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.

Any agent
npx skills add razzant/ouroboros --skill unix_computer_use
Clone the repo
git clone --depth 1 https://github.com/razzant/ouroboros

Made for: Claude Code.

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 unix_computer_use

README.md
[![agentmods](https://agentmods.dev/badge/skills/razzant/ouroboros/unix_computer_use.svg)](https://agentmods.dev/skills/razzant/ouroboros/unix_computer_use)
Your own site
<a href="https://agentmods.dev/skills/razzant/ouroboros/unix_computer_use"><img src="https://agentmods.dev/badge/skills/razzant/ouroboros/unix_computer_use.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00033 $0.01710
Opus 5 $0.00016 $0.00855
Sonnet 5 $0.00007 $0.00342
Haiku 4.5 $0.00003 $0.00171

Measured 8d ago against content hash 4863301b4590, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

unix_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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (plugin.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/unix_computer_use/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unix Computer Use

This bundled extension exposes a reviewable computer-use substrate for local macOS/Linux desktops and explicitly configured remote targets. All actions are for supervised, low-risk workflows under human or benchmark observation. Windows support is deferred to a separate backend/skill.

Tools:

  • capabilities reports the platform, display-session type, and detected screenshot/input backends plus the active connection/backend.
  • list_connections, add_connection, test_connection, activate_connection, and use_local manage the local/remote connection registry in skill state.
  • screenshot captures the desktop, downscales the image to fit WXGA (1280x800, configurable) and persists the exact image-to-input coordinate transform. Pass coordinates read off the returned image directly to the input tools — they are remapped automatically. The result carries the typed auto_attach_image field, so the host attaches the image to the conversation in the same round (v6.81.1) — no view_image call is needed for a fresh capture; the returned path stays view_image-readable for re-viewing later.
  • click (left/right/middle, double/triple), the thin aliases double_click/triple_click (models call these names unprompted), move, left_click_drag, mouse_down/mouse_up, cursor_position, type_text, key, hold_key, scroll, and wait execute input through platform tools when available. Pointer coordinates pass through one normalizer that accepts the malformations models actually emit (the pair packed into x with y absent or duplicated) and fails loudly on anything ambiguous.
  • window_list lists visible windows/processes where the platform exposes a lightweight backend.
  • ax_tree returns a set-of-marks accessibility snapshot of the frontmost window on macOS: numbered interactive elements (role, title, center coordinates in input space — click them with raw=true). It degrades honestly to a process/window list when the AX walk fails or on Linux.
  • remote_exec runs a shell command on the active remote backend only; it refuses on local backend. Use ordinary Ouroboros shell/file tools for local work.

Coordinate contract:

  • Input tools accept coordinates in the LAST screenshot's image space and remap them through the stored transform; raw=true bypasses remapping.
  • macOS input consumes LOGICAL points while screenshots are physical pixels; the stored transform already folds the Retina scale in. On multi-display Macs the scale is approximate (approx flag) — prefer ax_tree marks.

Backend matrix (honest limitations):

  • macOS: screencapture + cliclick + osascript; sips for downscaling. scroll is unsupported (cliclick has no scroll-wheel command — page via key with page-down/page-up); middle click and non-left mouse_down/mouse_up are unsupported via cliclick. hold_key holds PURE-MODIFIER combos only (cmd, cmd+shift, ...): cliclick kd:/ku: accept only modifiers and kp: cannot hold — non-modifier holds report an honest error. In key combos the base key is tapped while modifiers are held (cmd+s = hold cmd, tap s). TCC permission state (Screen Recording / Accessibility) is NOT verified: tools exit 0 even when denied (wallpaper-only capture / dropped input) — ensure grants.
  • Linux X11: xdotool (input), gnome-screenshot/scrot (capture), wmctrl (windows), ImageMagick (downscaling). Function keys and case-sensitive keysyms are supported (f5F5, XF86AudioPlay as-is).
  • Linux Wayland: ydotool (pointer + typing; requires a running ydotoold) or wtype (typing only), grim or gnome-screenshot (capture). xdotool does NOT work on Wayland. key and hold_key are unsupported on Wayland (ydotool key takes raw keycodes only — combos would silently no-op, which this skill refuses to fake); use type_text for text. Pointer press/release uses ydotool button masks (0x40/0x80).
  • Remote OSWorld HTTP: screenshot uses GET <target>/screenshot; input and remote_exec use POST <target>/execute, matching OSWorld's in-VM pyautogui channel. The runner writes an osworld_http connection before each task. Honesty guarantees on this backend: scroll clicks are 1:1 wheel detents (not multiplied); non-ASCII type_text is pasted via the in-VM clipboard (pyperclip + ctrl+v, ASCII typewrite fallback) so Unicode is not silently dropped; every action's ok reflects the guest process returncode/status (HTTP 200 alone is not success); key backspace presses BackSpace and fwd-delete presses forward Delete; screenshots are capped at 20 MB and PNG-validated before use.
  • Remote SSH macOS: screenshot uses remote screencapture + scp; input uses a remote input helper path. The remote Mac must have Screen Recording and Accessibility grants configured by the owner. This skill does not install or store private SSH keys.

Read the full file on GitHub · 120 lines

Files

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.

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. 8d ago First seen · 120 lines · 33 tokens per session scan A 4863301b4590

Subscribe to this mod's changes

unix_computer_use is a skill published in the GitHub repository razzant/ouroboros (1,279 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,710 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

control-chrome

Control the user's Chrome browser for tasks that depend on existing Chrome state: tabs, logged-in sessions, or extensions. Prefer purpose-built connectors, APIs, or CLIs when available.

rojim666/SztuCode · 40 tokens

chrome

Use "${id}", the user's OWN signed-in browser, via its extension: open, read, click and type on the sites they allow. For anything needing THEIR session (work SSO, a passkey, a bank, a datacentre-blocked site), or when they say "my browser", "the tab I have open", or name a site they are signed into.

intentic/intentic · 0 tokens

website

Act as the signed-in user on ${site} through a real browser. Use whenever the user asks for something on that site.

intentic/intentic · 28 tokens

omk-computeruse

Route and operate OMK computer-use tasks across native desktop apps, WSL-to-Windows experiments, deterministic browser tools, Stagehand core, and Browserbase MCP without introducing a second orchestrator. Use when an OMK task must inspect or control macOS, Windows, Linux, Chrome, VS Code, Explorer, native GUI…

dmae97/omk · 88 tokens

feature-video

Record a video walkthrough of a feature and add it to the PR description. Use when a PR needs a visual demo for reviewers, when the user asks to demo a feature, create a PR video, record a walkthrough, show what changed visually, or add a video to a pull request.

gvkhosla/compound-engineering-pi · 61 tokens

web-browser

Interact with web pages via browser automation: navigate, click, fill forms, screenshot, and evaluate JavaScript. Uses Chrome/Chromium remote debugging (CDP).

aretw0/agents-lab · 36 tokens