claude-code

A setup guide for using Webcmd with Claude Code, Anthropic's coding-agent command-line tool. Webcmd adds browser-related skills and instructions to Claude Code.

In plain words
What is it for?
Use it to install Webcmd, check its browser requirements, load its skills, and configure Claude Code for browser work.
Why use it?
It shows the supported installation methods and helps avoid duplicate skill installations or confusion between Webcmd updates and plugin updates.

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/claude-code
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 1,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.01093
Opus 5 $0.00000 $0.00547
Sonnet 5 $0.00000 $0.00219
Haiku 4.5 $0.00000 $0.00109

Measured yesterday against content hash 10bb8d1b6889, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-code 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Deny `WebFetch`. It is lossy by design: a small, fast model runs an extraction prompt against the page and Claude receives that model's answer, not the page. Webcmd returns the real content. Add to the user or project se
docs/agents/claude-code.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 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+
  • The webcmd npm CLI, installed globally or in the project
  • Claude Code (claude), installed globally or in the project
  • A browser runtime; confirm with webcmd doctor before browser work

Install the plugin

claude plugin marketplace add agentrhq/webcmd
claude plugin install webcmd@webcmd

This installs all seven bundled Webcmd skills. Do not also add those skills with webcmd skills add; running both leaves two copies that can sit at different versions.

Plugin updates are version-gated, not commit-gated. Run claude plugin update webcmd@webcmd to pick up a new release; it is separate from webcmd update, which upgrades only the npm CLI.

Install and configure without the plugin

Install Webcmd and its skills:

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

When webcmd skills add prompts, choose the claude provider. It installs into ~/.claude/skills/ (user) or .claude/skills/ (project), which Claude Code reads on startup. Claude Code then surfaces webcmd-usage and webcmd-browser as skills when a task matches their descriptions.

Restart Claude Code (or start a new session) after installing skills.

Override default tools

Claude Code ships two native web tools — WebFetch (fetch a URL) and WebSearch (search) — both permission-gated by default.

Deny WebFetch. It is lossy by design: a small, fast model runs an extraction prompt against the page and Claude receives that model's answer, not the page. Webcmd returns the real content. Add to the user or project settings file (.claude/settings.json in the project, or ~/.claude/settings.json):

{
  "permissions": {
    "deny": ["WebFetch"]
  }
}

Or per invocation:

claude --disallowedTools WebFetch

Keep WebSearch. It returns result titles and URLs without fetching the pages, which is exactly the step Webcmd does not cover — Webcmd has no search index. Let Claude Code search, then let Webcmd read what it finds.

Read the full file on GitHub · 98 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 · 98 lines · 0 tokens per session scan B 10bb8d1b6889

Subscribe to this mod's changes

claude-code 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 1,093 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.