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/s3yed/appie-kit/computer-usenpx skills add S3YED/appie-kit --skill computer-usegit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/computer-use)<a href="https://agentmods.dev/skills/s3yed/appie-kit/computer-use"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/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 5.1 | $0.00068 | $0.02739 |
| Opus 5 | $0.00034 | $0.01370 |
| Sonnet 5 | $0.00014 | $0.00548 |
| Haiku 4.5 | $0.00007 | $0.00274 |
Grade F, and why
computer-use scanned grade F with 4 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider | Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider | Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider | This is a copy
100% identical to computer-use — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer Use (universal, any-model, cross-platform)
You have a computer_use tool that drives the user's desktop in the
background — your actions do NOT move the user's cursor, steal
keyboard focus, or switch virtual desktops / Spaces. The user can keep
typing in their editor while you click around in a browser in another
window. This is the opposite of pyautogui-style automation.
Everything here works with any tool-capable model — Claude, GPT, Gemini, or an open model on a local OpenAI-compatible endpoint. There is no Anthropic-native schema to learn.
Hermes drives cua-driver under the hood
for the platform plumbing. The Hermes-side computer_use tool exposed
in this skill is a higher-level Hermes vocabulary; the raw cua-driver
MCP tools (which a different agent harness would see) are NOT what you
call — call the computer_use actions documented below.
The canonical workflow
Step 1 — Capture first. Almost every task starts with:
computer_use(action="capture", mode="som", app="<the app you're driving>")
Returns a screenshot with numbered overlays on every interactable element AND an AX-tree index like:
#1 AXButton 'Back' @ (12, 80, 28, 28) [Chrome]
#2 AXTextField 'Address bar' @ (80, 80, 900, 32) [Chrome]
#7 Link 'Sign In' @ (900, 420, 80, 24) [Chrome]
...
The role names match the host platform's accessibility framework
(AXButton on macOS, Button on Windows UIA, push button on Linux
AT-SPI) — treat them as labels, not as strict types.
Step 2 — Click by element index. This is the single most important habit:
computer_use(action="click", element=7)
Much more reliable than pixel coordinates for every model. Claude was trained on both; other models are often only reliable with indices.
Step 3 — Verify. After any state-changing action, re-capture. You can save a round-trip by asking for the post-action capture inline:
computer_use(action="click", element=7, capture_after=True)
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.
- 2d ago First seen · 264 lines · 68 tokens per session scan F 33fdce112f14
computer-use is a skill published in the GitHub repository S3YED/appie-kit (7 stars, last pushed 10d ago), licensed MIT. It adds 68 tokens to every session and 2,739 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). It is 100% identical to computer-use, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
schedule
Create, list, remove or inspect this bot's scheduled work — recurring jobs ("every morning at 7 tell me X", "every weekday at 9 post the standup") and one-shot follow-ups ("check back in 20 minutes", "watch that deploy until it lands", "remind me on Friday"). Use whenever something must happen on a schedule…
digest
Activate for: daily digest, morning briefing, what's happening today, start of day brief, week ahead, Monday brief, weekly digest, start of week, what do I need to know today, morning rundown, daily overview, what's due today, Friday close, end of week summary. NOT for: executive dashboard (use progress-tracker)…
meeting-intelligence
Activate for: meeting prep, meeting synthesis, before the meeting, after the meeting, D/A/F/Q/R, meeting brief, stakeholder prep, meeting notes synthesis, meeting follow-up, meeting actions, meeting decisions, post-meeting notes, synthesise the meeting, what was decided in the meeting, meeting record. NOT for…
task-intelligence
Activate for: brain dump, prioritise, P1 P2 P3, critical path, daily priorities, weekly planning, backlog review, cross-domain plan, what should I work on, capture everything in my head, sort my priorities, what is most important right now, weekly critical path. NOT for: basic task CRUD (use official productivity…
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
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.