Hermes Agent is an AI assistant that learns from its use by creating and improving skills, retaining knowledge, searching past conversations, and adapting to its users. It is for people who want to run an agent through a terminal or messaging platforms while connecting it to different AI models and scheduled tasks.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NousResearch/hermes-agentnpx agentmods add skills/nousresearch/hermes-agent/inspecting-hermes-desktop-domWrote 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/nousresearch/hermes-agent/inspecting-hermes-desktop-dom)<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/inspecting-hermes-desktop-dom"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/inspecting-hermes-desktop-dom/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/nousresearch/hermes-agent/inspecting-hermes-desktop-dom"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/inspecting-hermes-desktop-dom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 128 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00020 | $0.01618 |
| Opus 5 | $0.00010 | $0.00809 |
| Sonnet 5 | $0.00004 | $0.00324 |
| Haiku 4.5 | $0.00002 | $0.00162 |
Grade A, and why
inspecting-hermes-desktop-dom scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s --max-time 3 http://127.0.0.1:${HERMES_DESKTOP_CDP_PORT:-9222}/json/version Copies of this mod
4 near-identical copies found in the catalogue:
- inspecting-hermes-desktop-dom — 100% identical, 0 lines differ
- inspecting-hermes-desktop-dom — 100% identical, 0 lines differ
- inspecting-hermes-desktop-dom — 94% identical, 70 lines differ
- inspecting-hermes-desktop-dom — 94% identical, 70 lines differ
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspecting the live Hermes desktop DOM
Overview
When you are developing apps/desktop and the user is running that same app
(hgui / npm run dev), you can read the live rendered DOM of the window
they are looking at — computed styles, geometry, which CSS rule actually won,
console output — instead of inferring it from .tsx and being wrong.
Dev-server runs open a Chrome DevTools Protocol port on 127.0.0.1:9222
automatically. The renderer is a Chromium page, so everything DevTools can read,
a script can read.
This does not replace looking at it. CDP answers factual questions ("what is the computed padding", "did this element render", "which selector matches"). It cannot tell you whether the result looks good. Colour balance, spacing feel, and "is this ugly" still need the user's eyes or a screenshot. Answer facts with CDP; hand aesthetics to the user.
When to Use
- Verifying a UI change actually took effect in the running app
- "Why is this element still X?" — find the winning rule before editing anything
- Locating a stable selector for a component you're about to change
- Checking a design token's computed value on a real node
- Reading renderer console errors the user mentions but can't copy out
Don't use for: perf profiling or heap work (node-inspect-debugger,
debugging-hermes-desktop), or anything where the real question is "does this
look right".
The port
Open on 127.0.0.1:9222 for any dev-server run. Closed in exactly two cases
(apps/desktop/electron/dev-cdp.ts):
- packaged builds — always, and no environment value overrides it;
- no
HERMES_DESKTOP_DEV_SERVER— an unpackagedelectron .againstdist/is how the packaged app gets smoke tested, so it behaves like one.
HERMES_DESKTOP_CDP_PORT moves the port (=9333) or disables it (=off).
Check before doing anything else:
curl -s --max-time 3 http://127.0.0.1:${HERMES_DESKTOP_CDP_PORT:-9222}/json/version
Empty → no port. Do not guess another port silently.
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.
- 7d ago First seen · 160 lines · 20 tokens per session scan A a78a5f8d277a
inspecting-hermes-desktop-dom is a skill published in the GitHub repository NousResearch/hermes-agent (244,059 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,618 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
html-email
Send-ready single-file email.
12-landing-page-brief-global
Use when a NEW landing page, sales page, or single-product page has to be built — seven-section structure, one page one goal one CTA, copy per block, mobile-first rules, technical and speed requirements, tracking plan, A/B test plan, and a dropshipping single-product mode. Trigger on 'landing page brief', 'build a…
12-brief-landing-page
Dung khi can viet brief de XAY landing page moi hoac trang ban hang moi — cau truc section, copy tung khoi, yeu cau ky thuat, tracking va timeline giao dev. Kich hoat khi user nhac 'brief landing page', 'lam trang ban hang', 'can trang dich', 'thue dev lam landing', 'landing page can gi', 'viet noi dung cho trang'.…
49-html-email-template-global
Use when responsive HTML email has to render correctly in every client — table-based structure, inline CSS, 600px max width, dark mode handling, quirks for Gmail, Apple Mail, Outlook and Yahoo, bulletproof buttons, and a pre-send test checklist, shipping a self-contained .html file to paste into Klaviyo, Mailchimp…
49-html-email-template
Dung khi can FILE HTML email chay duoc tren moi email client — cau truc table, CSS inline, be ngang 600px, dark mode, spec rieng cho Gmail, Outlook, Apple Mail va checklist test truoc khi gui. Mau va font lay tu brand guideline. Kich hoat khi user nhac 'email HTML', 'code email', 'template email', 'email responsive'…
ui-animation
Builds, reviews, and measures UI motion, including springs, gestures, scroll effects, and curve fitting from recordings. Use when asked to "add animation", "match this easing", "reverse engineer this motion", or find animation opportunities. For action semantics use product-design; for visual layout use ui-design.