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 AtlasOmnia/hermes-custom-pack --skill macos-app-automationgit 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/macos-app-automation)<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/macos-app-automation"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/macos-app-automation/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/atlasomnia/hermes-custom-pack/macos-app-automation"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/macos-app-automation.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 | $0.00043 | $0.05180 |
| Opus 5 | $0.00022 | $0.02590 |
| Sonnet 5 | $0.00009 | $0.01036 |
| Haiku 4.5 | $0.00004 | $0.00518 |
Grade B, and why
macos-app-automation scanned grade B with 1 finding 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 10d 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.
5. If WebDriver still reports Remote Automation disabled, the user must run `sudo safaridriver --enable`; never type their administrator password. This is a copy
100% identical to macos-app-automation — 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS App Automation
Use this skill when the user asks whether Hermes can control a native macOS app, or asks you to verify, configure, or troubleshoot AppleScript/Automation access for an app.
Preferred automation ladder
- AppleScript dictionary / app scripting API
- Best for structured app data and repeatable operations.
- Verify with the app's bundle ID, version, and scripting dictionary before promising coverage.
- App URL scheme
- Good for quick-add or deep-link actions when documented by the app.
- System Events / Accessibility scripting
- Useful for menu items and UI operations not exposed in the app dictionary.
- Hermes
computer_use
- Last-resort GUI operation for UI-only features. Capture first, click by element index, verify after state changes.
- If the wrapper reports that its cua-driver session ended, recover the same session before concluding GUI control is blocked. If Hermes has already rejected repeated identical calls, change the wrapper call signature or continue through direct
cua-driver calloperations rather than retrying the same arguments. - Do not turn an internal wrapper guardrail into the user-facing result. Recover through the direct driver path first; if a real blocker remains, report it in task language with the evidence that distinguishes it (for example, asleep display versus locked login screen).
- On an unattended Mac, wake a black/asleep display non-destructively and recapture before diagnosing capture failure. A visible login/password screen is a credential gate: never type, request, infer, or bypass the password, and never claim a click reached an app behind the lock screen without verified state change.
- After the user unlocks the Mac for a long unattended native-app workflow, start a tracked
/usr/bin/caffeinate -dimsuprocess immediately and stop it during cleanup;caffeinate -u -t 2wakes only and does not prevent a later relock. - Electron/webview drawers can retain off-screen controls in the accessibility tree with zero- or one-pixel bounds. Programmatic
set_valueby accessible label may still work, but never use an off-screen element as a human handoff target—especially for credentials. Scroll the exact row into view, recapture, require visible nonzero bounds, focus the intended field, and verify the adjacent action before asking the user to paste or confirm. After Save, recapture neighboring ordinary fields such as Endpoint and Model to catch a paste that landed in the wrong control without echoing its value. - Treat a modal dismissal as coordinate-invalidating: perform one click, recapture, and only then choose the next target. Never batch raw coordinate clicks across a dialog close.
- See
references/cua-session-recovery.mdfor deterministic session revival, black-capture diagnosis, lock-screen handling, repeated-call-guard fallback, and modal-safe clicking.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/apple-mail-multi-account-search.md 3.7 KB
- references/chrome-native-messaging-hosts.md 6.2 KB
- references/chromium-file-upload-fallback.md 2.4 KB
- references/cua-session-recovery.md 11 KB
- references/desktop-launcher-icon-workflow.md 2.3 KB
- references/electron-smoke-isolation.md 2.5 KB
- references/icloud-dataless-files.md 3.8 KB
- references/macos-memory-process-cleanup.md 2.9 KB
- references/notes-creation-date-count.md 2.2 KB
- references/safari-screenshot-evidence.md 3.2 KB
- references/tauri-native-app-bundle-isolation.md 5.8 KB
- references/terminal-frozen-last-login.md 1.9 KB
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.
- 10d ago First seen · 323 lines · 43 tokens per session scan B 57ab821d545d
macos-app-automation is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (56 stars, last pushed 26d ago), licensed MIT. It adds 43 tokens to every session and 5,180 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). It is 100% identical to macos-app-automation, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
defuddle
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already…
humanize-automation
Human-like mouse, keyboard and scroll behavior for behavioral bot bypass.
js-reverse-automation
A workflow for examining JavaScript in a real browser to find where login data, API requests, form fields, or responses are encrypted or signed. It then produces code and connection documentation for using that logic elsewhere.
dogfood
This skill guides you through systematic exploratory QA testing of web applications using the browser toolset. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.
dynamic-content-extraction
Extract structured data (prices, listings, product details) from JavaScript-heavy sites where key data is rendered by React/Vue/Angular and doesn't appear in compact accessibility snapshots.
yao-chatgpt-crawler
Use when a user provides ChatGPT web AI-search keywords, repeat count, target entity, entity type, OpenCLI profile, and crawl interval preference, then needs repeated crawls aggregated into JSON plus a Kami HTML GEO report. Not for generic crawling, ChatGPT API chat, SEO writing, or one-off answers.