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 agentmods add agents/agentrhq/webcmd/clinegit 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/agents/agentrhq/webcmd/cline)<a href="https://agentmods.dev/agents/agentrhq/webcmd/cline"><img src="https://agentmods.dev/badge/agents/agentrhq/webcmd/cline.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01293 |
| Opus 5 | $0.00000 | $0.00647 |
| Sonnet 5 | $0.00000 | $0.00259 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
cline 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 2d 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 — 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+
- The
webcmdnpm CLI, installed globally or in the project - Cline — the VS Code extension, CLI, or JetBrains plugin
- A browser runtime; confirm with
webcmd doctorbefore browser work
Install and configure
Install Webcmd and its skills into Cline's skill directories:
npm install -g @agentrhq/webcmd
webcmd doctor
webcmd skills add --path ~/.cline/skills
For a project-scoped setup that travels with the repo:
webcmd skills add --path .cline/skills --scope project
Cline also discovers skills in ~/.cline/skills/, .cline/skills/, and .claude/skills/. It loads skill metadata at startup and activates webcmd-browser on demand through its use_skill tool.
Restart Cline (or start a new task) after installing skills. In the extension, confirm they appear under the Skills tab (scale icon in the Cline panel).
Override default tools
Cline's web surface depends on which app you are using:
| Surface | Tools | What to do |
|---|---|---|
| ClineCore (CLI, SDK, Kanban) | fetch_web |
Prefer Webcmd over fetch_web for reading pages |
| IDE extension (Cline provider) | web_fetch, web_search, browser_action |
Keep web_search; prefer Webcmd over web_fetch and browser_action on the open web |
fetch_web and web_fetch are lossy fetches — HTTP with HTML-to-markdown conversion, no real browser session. Webcmd returns authenticated, JavaScript-rendered content and supports multi-step automation. Keep web_search. Webcmd has no search index of its own.
Cline has no per-tool deny list like OpenCode. Steer it with a rule in .clinerules/webcmd.md:
# Webcmd for the open web
Use Webcmd for anything on the open web — fetching, authenticated third-party sites, multi-step automation, workflows worth making reusable:
- Check `webcmd list -f json` for an adapter that covers the task; use it first.
- Otherwise run `webcmd --profile work session create "Work Project"`, then drive its returned readable ID with `webcmd --profile work --session work-project-k7 browser tabs` via `bash`.
- Run `webcmd doctor` first; use `webcmd --profile work session list` to inspect state and `webcmd --profile work session close work-project-k7` when finished.
- For login walls, use Webcmd's human handoff; never type passwords, OTPs, cookies, or credentials.
Use Cline's `web_search` to find URLs, then Webcmd to read them.
Use `browser_action` only for the app being edited: localhost dev server, console and network triage, visual checks after a change.
Do not use `fetch_web`, `web_fetch`, or `browser_action` for external third-party sites when Webcmd can handle the task.
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.
- 2d ago First seen · 95 lines · 0 tokens per session scan A 8608eaf1c7eb
cline is an agent published in the GitHub repository agentrhq/webcmd (1,572 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,293 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 2026-09-02.
Other agents, from other repositories
e2e-tester
Tests web applications end-to-end using Glance browser MCP. Navigates pages, fills forms, clicks buttons, takes screenshots, runs assertions, and reports bugs. Use when you want to verify an app works correctly — login flows, forms, navigation, responsiveness — with real browser interaction.
browser-driver
Drives a delegated multi-step browser task through Fast Browser and returns only the distilled result.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
playwright-test-heal
Run all my tests and fix the failing ones.
web-research-analyst
Web research: browser automation, Tavily API, competitive intelligence, documentation capture, technical recon.
page-map-sync
用 Playwright 实地探索目标页面，全量覆写 pagemap/.yaml，产出 sync.md。由 orchestrator 在需要更新地图 / selector 漂移时派发。.