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/openclawgit 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 | $0.00000 | $0.01018 |
| Opus 5 | $0.00000 | $0.00509 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
openclaw 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 — 91 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 - An OpenClaw Gateway + an agent session where
execis enabled - A browser runtime; confirm with
webcmd doctorbefore browser work
Install and configure
Install Webcmd and its skills:
npm install -g @agentrhq/webcmd
webcmd doctor
webcmd skills add
When webcmd skills add prompts, choose the agents provider. It installs into ~/.agents/skills/ (user) or .agents/skills/ (project), both of which OpenClaw checks for skills. OpenClaw then surfaces webcmd-browser as a skill.
Restart the Gateway (or start a new session) after installing skills.
Override default tools
Deny web_fetch. It is an HTTP fetch with readable extraction and does not execute JavaScript, so it fails on exactly the dynamic sites Webcmd handles. In the Gateway config (~/.openclaw/openclaw.json):
{
"tools": {
"deny": ["web_fetch"]
}
}
Keep the search tools — web_search (backed by Brave, Gemini, Grok, Kimi, or Perplexity), x_search, and search_news. Webcmd has no search index of its own, so search stays the cheapest way to find URLs for Webcmd to read.
The browser tool is a single tool with subcommands (doctor, status, start, stop, tabs, open, focus, close, snapshot, screenshot, navigate, act). It reaches both localhost and the open web, so keep it for the app being edited and route open-web work to Webcmd. State that split in your OpenClaw system prompt or project instructions.
Worth raising with the user: OpenClaw's browser has a user profile that reuses their existing signed-in sessions, which overlaps directly with Webcmd's auth profiles. Its isolated openclaw profile does not.
The Gateway watches the config file and applies changes automatically. Denying these tools does not affect the exec tool, which is how webcmd is driven.
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 Changed · -1 lines b3f8cad01959
- 3d ago First seen · 92 lines · 0 tokens per session scan A d38a84e6b8a1
openclaw is an agent published in the GitHub repository agentrhq/webcmd (1,558 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,018 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 2026-08-30.
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.
website-requester
Agent for submitting website indexing requests to Actionbook using agent-browser CLI.
scraper-executor
Agent for generating agent-browser scraper scripts using Actionbook selectors.
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.
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。.