webcmd-usage

A usage guide for Webcmd, a command-line tool that lets coding agents work with websites, desktop apps, and external command-line tools through one consistent interface.

In plain words
What is it for?
Use it to learn what Webcmd supports, discover the right adapter or specialized guide, and start a Webcmd session correctly.
Why use it?
It helps an agent choose the right command and follow the required setup and fetch rules instead of guessing or relying on screen scraping.

Skill for Claude CodeCodex

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 skills/agentrhq/webcmd/webcmd-usage
Any agent
npx skills add agentrhq/webcmd --skill webcmd-usage
Clone the repo
git clone --depth 1 https://github.com/agentrhq/webcmd

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,017 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 $0.00074 $0.04017
Opus 5 $0.00037 $0.02008
Sonnet 5 $0.00015 $0.00803
Haiku 4.5 $0.00007 $0.00402

Measured yesterday against content hash 4766b863275c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

webcmd-usage 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.

skills/webcmd-usage/SKILL.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

webcmd-usage

Webcmd turns websites, Electron desktop apps, and external CLIs into a uniform webcmd <site> <command> surface that agents can drive without screen scraping. This skill is the orientation layer. Once you know the task, load the specialized skill that fits it.

For any search, research, source discovery, direct URL fetch, evidence gathering, or “look this up” request, load smart-search before choosing commands. smart-search owns fetch-first search, browser-fetch escalation, last-resort search adapters, and source-summary rules.

For a known URL, the first-choice Webcmd fetch path is webcmd web fetch --url <url>. Use it before browser work or non-Webcmd HTTP clients. Do not open a browser until that command returns FETCH_BLOCKED or FETCH_REQUIRES_BROWSER.

CLI Preflight

Before the first Webcmd command in a session, run:

webcmd --version

If it succeeds, continue without reinstalling or updating Webcmd.

If the shell reports that webcmd is missing, tell the user that the Codex plugin includes the skills but needs the Webcmd CLI, then install and verify it:

npm install -g @agentrhq/webcmd
webcmd --version

If npm is unavailable or installation fails, stop and report the exact error. Do not install Node.js or silently fall back to npx.

The Three Pillars

  • Adapter commands: webcmd <site> <command> [...]. Core ships no site adapters; every site — official and community — lives in an independently installable plugin under plugins/<plugin-name>/ in the main repo, or ~/.webcmd/plugins/<plugin-name>/ once installed. Private iteration adapters live in ~/.webcmd/clis/. A command in ~/.webcmd/clis/<site>/<command>.js takes precedence over the same command from an installed plugin. Each command has a strategy such as PUBLIC, COOKIE, INTERCEPT, UI, or LOCAL.
  • Browser driving: use an existing adapter command first; otherwise load webcmd-browser, create a session, and run Playwright with root --session <session-id>.
  • External CLI passthrough: webcmd gh, webcmd docker, webcmd vercel, and similar wrappers. Manage them with webcmd external install <name> or webcmd external register <name>.

Read the full file on GitHub · 288 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 · 288 lines · 74 tokens per session scan A 4766b863275c

Subscribe to this mod's changes

webcmd-usage is a skill published in the GitHub repository agentrhq/webcmd (1,594 stars, last pushed 2d ago), licensed Apache-2.0. It adds 74 tokens to every session and 4,017 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

x402

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…

browser-use/browser-use · 175 tokens

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

browser-use/browser-use · 26 tokens

remote-browser

Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.

browser-use/browser-use · 22 tokens

opencli-browser

Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…

jackwener/OpenCLI · 80 tokens

opencli-adapter-author

Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level…

jackwener/OpenCLI · 88 tokens

opencli-autofix

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.

jackwener/OpenCLI · 61 tokens