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 agentmods add skills/agentrhq/webcmd/webcmd-browsernpx skills add agentrhq/webcmd --skill webcmd-browsergit clone --depth 1 https://github.com/agentrhq/webcmdWhat 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 | $0.00037 | $0.03881 |
| Opus 5 | $0.00018 | $0.01940 |
| Sonnet 5 | $0.00007 | $0.00776 |
| Haiku 4.5 | $0.00004 | $0.00388 |
Grade A, and why
webcmd-browser 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.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
webcmd-browser
The first reader of this CLI is an agent, not a human. Use browser output as structured evidence, not as prose to skim. This skill is for driving a live browser to finish a task or understand a surface. If the workflow should become reusable, switch to webcmd-adapter-author.
Adapter fallback gate
Before starting a raw browser session, filter webcmd list -f json at the source using request-derived terms across site, name, description, and columns; follow webcmd-usage for the exact command shape. Any truncation warning means adapter discovery is incomplete: narrow the filter and inspect again. Absence from truncated output never proves that no adapter exists.
Use raw webcmd browser only after a complete, non-truncated registry check shows no suitable adapter and a plugin search for the missing site or capability returns no match. If plugin search returns a match, offer installation of the returned installSource; if it errors, report the error instead of opening the browser.
Prerequisites
webcmd doctor
Until doctor is green, browser commands may fail. Registry and plugin discovery do not require doctor.
Session lifecycle
- Create a named browser Session before raw browser work:
webcmd --profile <profile> session create <name>. - Create a named profile first:
webcmd profile create <profile>. If an explicit profile returnsPROFILE_NOT_FOUND, create it, then retry session creation. - Raw browser commands require the returned readable ID at the root:
webcmd --profile <profile> --session <session-id> browser .... - Profiles are cookie jars and auth scope; Sessions are browser workspaces/windows within a Profile. Session IDs are immutable and Profile-scoped. Parallel agents use separate Sessions.
webcmd session listshows sessions and their handoff/runtime state; close finished work withwebcmd session close <session-id>. Close is blocked while that Session has a live handoff.- Browser state in the bound page persists between calls, but each
rungets a fresh JavaScript scope. webcmd --session <session-id> browser tabslists existing pages without creating a new one.webcmd --session <session-id> browser bind --page <page-id>explicitly attaches the session to an existing page.- If the user manually signs in or changes the visible tab, re-bind or inspect with a fresh snapshot before continuing.
What ships with it
1 file 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.
- yesterday First seen · 290 lines · 37 tokens per session scan A 4da375c2664f
webcmd-browser is a skill published in the GitHub repository agentrhq/webcmd (1,594 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 3,881 once invoked, about $0.0002 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
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
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
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…
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…
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.