agentrhq/webcmd is browser infrastructure for AI agents that learns website navigation and turns familiar workflows into reusable commands. Agents use it to explore websites in a browser, record site structure and actions, and later automate known tasks with less repeated navigation. Its catalogue add-ons provide agent workflows and tools for using webcmd.
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 skills add agentrhq/webcmd --skill webcmd-browsergit clone --depth 1 https://github.com/agentrhq/webcmdWrote 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/agentrhq/webcmd/webcmd-browser)<a href="https://agentmods.dev/skills/agentrhq/webcmd/webcmd-browser"><img src="https://agentmods.dev/badge/skills/agentrhq/webcmd/webcmd-browser/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/agentrhq/webcmd/webcmd-browser"><img src="https://agentmods.dev/badge/skills/agentrhq/webcmd/webcmd-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 Excessive Agency · line 172 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00030 | $0.03627 |
| Opus 5.5 | $0.00012 | $0.01451 |
| Sonnet 5.5 | $0.00006 | $0.00725 |
| Haiku 4.5 | $0.00003 | $0.00363 |
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 1mo 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.
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 — 268 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.
After preflight and Session creation, run webcmd site memory context <url> --task-id <id> -f json before any live browser action.
Load references/sitemap-memory.md after context, before relying on memory, editing draftPath, or acting on provisional-fallback or readOnly.
Load references/candidate-schema.md when a qualifying observation appears.
Load references/git-lifecycle.md before checkpoint, or when SITE.md exceeds 500 lines.
Load references/browser-run-playwright.md before writing a browser run program.
Do not complete a payment or checkout without explicit user confirmation.
Keep normal task output task-focused. Do not routinely announce memory reads, writes, or checkpoints. Surface memory diagnostics only on request, verbose mode, or a material retention failure.
Prerequisites
webcmd doctor
Until doctor is green, browser commands may fail.
Memory loop
Learning is automatic, invisible, and secondary to the user's task. Run it around the browser work, never instead of it.
webcmd site memory context <url> --task-id <id> -f jsonbefore the first live action. ReadsiteMarkdown; open only thereferencesthis goal needs.- Complete the user's task. The live browser is truth; memory is dated prior knowledge.
- Evaluate only what the task already surfaced. Capture each qualifying observation with
webcmd site memory candidate add. - Search related pending candidates, then decide ingestion.
- When active memory should change, rerun context, edit the returned
draftPath, and publish withwebcmd site memory checkpoint.
Capture a candidate when the task revealed:
- top-level action space or routes that will cut blind navigation next time;
- a demonstrably better path, such as an alternate interface or a feed that avoids repeated page work;
- a durable access fact, including what works without login;
- a high-consequence blunder: bans, rate limits, moderation or removal, financial or destructive effects; or
- a repeated ordinary mistake that now supports a specific correction.
What ships with it
4 files 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.
- 1mo ago Changed · +1 lines 87175ac80a52
- 1mo ago Changed · -8 lines 8b698e4c53c5
- 1mo ago Changed · -15 lines · -7 tokens per session a2eec9d3337f
- 1mo ago First seen · 290 lines · 37 tokens per session scan A 4da375c2664f
webcmd-browser is a skill published in the GitHub repository agentrhq/webcmd (2,715 stars, last pushed 21d ago), licensed Apache-2.0. It adds 30 tokens to every session and 3,627 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
gem-pw
Browser-automated Gemini Gem CLI (CDP-first) — chat, CRUD, image gen, deep research, --collab surgical-diff review. No API key.
browser-use
An open-source framework that lets an AI agent control a real web browser. The agent can open links, click buttons, fill in forms, wait for results, collect page content, and return structured data.
qprobe
QUESTPIE Probe — dev testing CLI for AI coding agents. Start servers, test APIs, control browsers via agent-browser, record and replay regression tests with zero tokens. Use when testing web apps, starting dev servers, reading logs, debugging errors, making API calls, checking browser console/network, or composing…