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 skills add nobodyohm-web/Thot --skill computer-usegit clone --depth 1 https://github.com/nobodyohm-web/ThotWrote 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/nobodyohm-web/thot/computer-use)<a href="https://agentmods.dev/skills/nobodyohm-web/thot/computer-use"><img src="https://agentmods.dev/badge/skills/nobodyohm-web/thot/computer-use/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nobodyohm-web/thot/computer-use"><img src="https://agentmods.dev/badge/skills/nobodyohm-web/thot/computer-use.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.04470 |
| Opus 5.5 | $0.00005 | $0.01788 |
| Sonnet 5.5 | $0.00003 | $0.00894 |
| Haiku 4.5 | $0.00001 | $0.00447 |
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 1mo 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.
This is a copy
86% identical to computer-use — 151 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 — 389 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.
This wrapper skill teaches the Hermes computer_use workflow and action
vocabulary. Call the actions documented below instead of raw cua-driver MCP
tools. For driver internals and platform-specific behavior, follow the Cua
skill installed by cua-driver skills install. Hermes autodetection is a
planned cua-driver follow-up, so currently point Hermes at the resulting
~/.cua-driver/skills/cua-driver directory or symlink it into your skill space.
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:
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.
- 1mo ago First seen · 389 lines · 13 tokens per session scan F 89e2eddc61cf
computer-use is a skill published in the GitHub repository nobodyohm-web/Thot (0 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 4,470 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to computer-use, differing in 151 lines, and is treated as a copy.
Other skills, from other repositories
first-task
Run the first task chat that setup hands off.
box
Box manages cloud files, sharing, search, and metadata.
obsidian
Read, search, create, and edit notes in the Obsidian vault.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
routine-from-chat
Turn a plain-language "do this automatically" request into a routine — either event-triggered ("text me when I get an email from my landlord") or scheduled ("remind me every Friday at 9am"). For third-party events (Gmail, GitHub, Slack…) it confirms with the guardian and then subscribes to the connector trigger so the…
output-eval-error-analysis
Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops.