hermes

An instruction set for installing and configuring Webcmd for Hermes, an AI agent with terminal and browser tools.

In plain words
What is it for?
Use it to install Webcmd, run its system check, add its skills, configure Hermes to load them, and choose the right browser or web tools.
Why use it?
It explains the host requirements and configuration needed for Hermes to discover the browser skills and use them reliably.

Agent

Install

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.

agentmods
npx agentmods add agents/agentrhq/webcmd/hermes
Clone the repo
git clone --depth 1 https://github.com/agentrhq/webcmd
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,233 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01233
Opus 5 $0.00000 $0.00616
Sonnet 5 $0.00000 $0.00247
Haiku 4.5 $0.00000 $0.00123

Measured yesterday against content hash 7896b49e51be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hermes 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 yesterday.

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.

docs/agents/hermes.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent prompt

Fetch and follow https://raw.githubusercontent.com/agentrhq/webcmd/main/start.md to set up Webcmd end to end.

Manual

Requirements

  • Node.js 20.6+ on the Hermes host
  • The webcmd npm CLI, installed globally on the Hermes host
  • Hermes terminal toolset enabled (needed to run webcmd)
  • A browser runtime; confirm with webcmd doctor before browser work

Install and configure

Install Webcmd and its skills on the Hermes host:

npm install -g @agentrhq/webcmd
webcmd doctor
webcmd skills add

When webcmd skills add prompts, choose the agents provider (installs into ~/.agents/skills/). Then make Hermes load those skills by adding the external skills directory to ~/.hermes/config.yaml:

skills:
  external_dirs:
    - ~/.agents/skills

Hermes then reads webcmd-usage and webcmd-browser as skills. Restart Hermes after changing config and confirm the skills are discoverable.

Override default tools

Hermes' web surface spans three toolsets:

Toolset Tools What to do
web web_search, web_extract Keep enabled for web_search; prefer Webcmd over web_extract
browser browser_navigate, browser_click, browser_type, browser_scroll, browser_press, browser_back, browser_snapshot, browser_vision, browser_console, browser_get_images, plus CDP-gated browser_cdp and browser_dialog Keep for localhost, route open-web work to Webcmd
x_search x_search Keep — it is search, and it auto-enables whenever xAI credentials are present

web_search lives in web, not in browser, so disabling browser leaves search intact.

Hermes toggles toolsets, not individual tools. There is no way to drop web_extract while keeping web_search, so leave the web toolset on and steer the agent with instructions instead. Add this to your Hermes system prompt or project instructions:

Use Webcmd (webcmd list, then webcmd --profile work session create "Work Project" and webcmd --profile work --session work-project-k7 browser tabs via the terminal toolset) for anything on the open web: fetching, authenticated third-party sites, multi-step automation. Prefer it over web_extract. Use the browser_* tools only for the app being edited — localhost dev server, console and network triage, visual checks. Keep using web_search and x_search to find URLs.

Read the full file on GitHub · 95 lines

Changes

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.

  1. yesterday First seen · 95 lines · 0 tokens per session scan A 7896b49e51be

Subscribe to this mod's changes

hermes is an agent published in the GitHub repository agentrhq/webcmd (1,594 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,233 tokens. 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.