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/atlasomnia/hermes-custom-pack/computer-usenpx skills add AtlasOmnia/hermes-custom-pack --skill computer-usegit clone --depth 1 https://github.com/AtlasOmnia/hermes-custom-packWrote 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/atlasomnia/hermes-custom-pack/computer-use)<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/computer-use"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/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 | $0.00071 | $0.02987 |
| Opus 5 | $0.00036 | $0.01494 |
| Sonnet 5 | $0.00014 | $0.00597 |
| Haiku 4.5 | $0.00007 | $0.00299 |
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 5d 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
94% identical to computer-use — 134 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 — 288 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.
- 5d ago First seen · 288 lines · 71 tokens per session scan F bb792db8128b
computer-use is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (55 stars, last pushed 20d ago), licensed MIT. It adds 71 tokens to every session and 2,987 once invoked, about $0.0004 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 94% identical to computer-use, differing in 134 lines, and is treated as a copy.
Other skills, from other repositories
config
Use when configuring obshare-cli credentials, checking saved settings, testing connectivity, clearing local config, or setting optional Obsidian bridge values used by the V0.2.0 direct-share stack.
obshare-cli
Use when setting up obshare-cli 0.2.0, reviewing available commands, or choosing the right command for config, upload, permission, history, delete, and the plugin-first direct-share workflow.
upload
Use when uploading a Markdown note to Feishu, optionally applying public or copy/download permissions, or requesting JSON upload results for automation or the Obsidian plugin direct-share flow.
permission
Use when changing Feishu document visibility, copy permissions, or download permissions for an uploaded document token.
list
Use when checking obshare-cli upload history, finding document tokens, or reviewing previous upload URLs and permission snapshots.
delete
Use when removing a Feishu document by token and cleaning the matching entry from local obshare-cli upload history.