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 MilkyWay008/Hermes-OTG --skill computer-usegit clone --depth 1 https://github.com/MilkyWay008/Hermes-OTGWrote 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/milkyway008/hermes-otg/computer-use)<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/computer-use"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/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/milkyway008/hermes-otg/computer-use"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/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 | $0.00068 | $0.03458 |
| Opus 5.5 | $0.00027 | $0.01383 |
| Sonnet 5.5 | $0.00014 | $0.00692 |
| Haiku 4.5 | $0.00007 | $0.00346 |
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
98% identical to computer-use — 2 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 — 314 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.
- 1mo ago First seen · 314 lines · 68 tokens per session scan F b856c55bf4ef
computer-use is a skill published in the GitHub repository MilkyWay008/Hermes-OTG (20 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 3,458 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to computer-use, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
transcriptapi
Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, or anything…
youtube-playlist
Use when a YouTube playlist is involved: pasted playlist links or IDs, requests to list playlist videos, browse playlist contents, or work through a playlist for transcripts or research. Also use when the user wants all videos from a series, course, or collection. Not for creating playlists or account management.
yc-jobs-scraper
Scrape daily job listings from YCombinator's Workatastartup platform without duplicates. Use this skill when asked to scrape YC jobs, update the YC companies list, or retrieve the latest startup jobs. It handles authentication, extracts company slugs via Inertia.js JSON payloads, falls back to public YC job pages when…
wstg-web-pentest
Full WSTG-aligned web application pentest — 12-phase methodology from information gathering through reporting, with concrete commands, expected outputs, pitfalls, and verification per phase.
hunt-cors
Hunt CORS Misconfiguration — origin-reflection with credentials, null-origin trust, subdomain-regex bypass (unanchored vs unescaped-dot vs prefix-only), pre-flight (OPTIONS) gating bypass, postMessage origin checks. High only when an attacker-controlled origin can perform a CREDENTIALED cross-origin read of sensitive…
hunt-dom
Hunt client-side DOM vulnerabilities — DOM Clobbering (overwrite JS globals via HTML injection), PostMessage hijacking (missing origin check), Service Worker abuse (intercept requests from same-origin script), CSS Injection/Exfiltration (attribute selectors → token char-by-char via OOB), client-side template…