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 browser-harness-authoringgit 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/browser-harness-authoring)<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/browser-harness-authoring"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/browser-harness-authoring/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/browser-harness-authoring"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/browser-harness-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.03021 |
| Opus 5 | $0.00030 | $0.01510 |
| Sonnet 5 | $0.00012 | $0.00604 |
| Haiku 4.5 | $0.00006 | $0.00302 |
Grade A, and why
browser-harness-authoring 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Harness Authoring
Overview
Map a repeatable website flow once, verify it safely, and save the result as a site-specific Hermes skill. The resulting browser harness records the browser lane, semantic targets, checkpoints, failure modes, recovery paths, and human decision gates needed to replay the flow without exploring the site from scratch every time.
This skill separates two modes:
- Authoring mode explores and documents with dummy data. It never completes irreversible actions.
- Execution mode replays a verified harness mechanically, pausing at decision gates and whenever reality differs from the harness.
A harness makes a known workflow less chaotic; it does not turn every website into a stable API. CAPTCHA, multifactor authentication, anti-bot systems, session expiry, and UI changes remain real constraints.
The approach originated in the community workshop Teach Hermes to Drive Any Website — Zero Config and has been updated for current Hermes browser, profile, skill, and cron behavior.
When to Use
Use when:
- a recurring website task has finite steps and objective success criteria;
- Hermes repeatedly spends tool turns rediscovering the same controls;
- a site requires a specific browser backend or interaction workaround;
- a read-only monitor or reversible workflow should run on a schedule;
- the user asks to map, survey, record, or harness a website flow.
Good targets include checking an order status, collecting a published price, preparing a form without submitting it, navigating to a known report, or reaching the final review screen of a booking.
Do not use when:
- the task is open-ended research, subjective comparison, or support chat;
- the flow is dominated by CAPTCHA, account recovery, or unpredictable challenges;
- the site forbids automation and no compliant automation path exists;
- the requested action would bypass access controls, rate limits, or anti-bot defenses;
- the workflow cannot be verified without creating real-world side effects.
What ships with it
6 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.
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 · 277 lines · 60 tokens per session scan A c235811acca2
browser-harness-authoring is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (56 stars, last pushed 26d ago), licensed MIT. It adds 60 tokens to every session and 3,021 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.