exo-control

exo-control is a skill for Claude Code, Codex from ImAvgErix/ExoControl. It costs 46 tokens per session (1,191 once invoked), scanned A, original, MIT.

A control tool for letting AI agents use a Windows computer, web browser, files, registry, and operating-system functions through MCP, a command line, or Python.

In plain words
What is it for?
Use it to inspect and operate desktop interfaces, automate browser tasks, manage local files, access system operations, and use optional search or scraping services.
Why use it?
It provides one interface for computer tasks across different AI systems and encourages grouped, verifiable actions instead of repeated manual clicks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to inspect and operate desktop interfaces, automate browser tasks, manage local files, access system operations, and use optional search or scraping services.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/imavgerix/exocontrol/exo-control
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 ImAvgErix/ExoControl --skill exo-control
Clone the repo
git clone --depth 1 https://github.com/ImAvgErix/ExoControl

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 exo-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/imavgerix/exocontrol/exo-control.svg)](https://agentmods.dev/skills/imavgerix/exocontrol/exo-control)
Your own site
<a href="https://agentmods.dev/skills/imavgerix/exocontrol/exo-control"><img src="https://agentmods.dev/badge/skills/imavgerix/exocontrol/exo-control.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,191 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.
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 $0.00046 $0.01191
Opus 5 $0.00023 $0.00596
Sonnet 5 $0.00009 $0.00238
Haiku 4.5 $0.00005 $0.00119

Measured 7d ago against content hash fc5ba766849e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

exo-control 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 7d 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.

skills/exo-control/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exo Control (any AI · any harness)

Hardened PC control plane. Not tied to Cursor, Grok, Claude, or Codex — those are just hosts.

Surfaces (in priority order for agents)

  1. MCP: exo_exec / exo_screenshot / exo_help
  2. CLI: exo-control exec or exo-control script steps.json
  3. Python: from exo_control import ExoExecEngine

Server: python -m exo_control.slim_mcp_server
Install: pip install "git+https://github.com/ImAvgErix/[email protected]" (or pip install -e .).
Optional: pip install "exo-control[browser]" (CDP) or "exo-control[web]" (Browser Use).
Env: EXO_PREFER_CUA=0. State under ~/.exo/. PERPLEXITY_API_KEY unlocks search. BROWSER_USE_API_KEY unlocks browser_use. FIRECRAWL_API_KEY unlocks scrape. Local files_convert / files_find / memory_* work without cloud keys.

Rules

  1. Script-first — one batched exec, not click spam.
  2. lease_acquire before hands; lease_release after.
  3. Structure first (observe/read/verify); screenshot only on miss or explicit ask.
  4. Prefer web_task for multi-step web jobs (structure mode). Screenshots only on miss.
  5. {"op":"help"} or exo_help if unsure of ops. find for a control by name. pc for volume/power/idle/wifi.
  6. confirm=true for destructive OS ops unless Full-Trust is on. Full-Trust is owner mode (broker auto-elevates). Kill file ~/.exo/KILL still wins.
  7. Multi-monitor: pass monitor on focus/observe/shot; wrong display fails closed.
  8. Human kill-switch is ~/.exo/KILL. Do not try to disarm a kill file.

Web search (not UI find)

Lease-free Perplexity Search as Code. Fan out queries, then filter / dedupe / rank in the result. Requires PERPLEXITY_API_KEY. Do not open a browser to look something up.

{"op": "search", "query": ["rust async runtimes", "tokio vs async-std"], "max": 5, "dedupe": true}
{"op": "search_content", "query": "installation", "urls": ["https://docs.rs/tokio"]}

Browser Use Cloud

Hosted web agent or a managed Chromium you drive with existing browser_* ops. Requires BROWSER_USE_API_KEY. Exo Control is Windows-only; this is the remote browser path.

Read the full file on GitHub · 92 lines

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. 7d ago First seen · 92 lines · 46 tokens per session scan A fc5ba766849e

Subscribe to this mod's changes

exo-control is a skill published in the GitHub repository ImAvgErix/ExoControl (0 stars, last pushed 22d ago), licensed MIT. It adds 46 tokens to every session and 1,191 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 2026-08-31.

Related

Other skills, from other repositories

computer-use-windows

Top-level Windows computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.

wimi321/windows-computer-use-skill · 36 tokens

clawdcursor

FALLBACK ONLY — do not invoke unless you have already ruled out (1) a native API (Gmail API, GitHub API, Slack API …), (2) a CLI (git, gh, aws, npm, curl …), (3) direct file editing, and (4) existing browser automation (Playwright, Puppeteer). Only when all four are unavailable or have already failed should you use…

AmrDab/clawdcursor · 265 tokens

computer-use

A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.

Plocr/Reasonix-computer-use · 23 tokens

web-navigator

A browser-automation routing guide for web tasks. It directs navigation, page inspection, and actions such as clicking or filling forms to the appropriate browser tool.

Plocr/Reasonix-computer-use · 30 tokens

screen-use

A Windows desktop automation skill for clicking controls, entering text, using keyboard shortcuts, scrolling, and taking screenshots. It can also carry out multi-step tasks through visual guidance.

tongriyaotxt/screen-use · 58 tokens

computer-use-macos

Top-level macOS computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.

wimi321/macos-computer-use-skill · 37 tokens