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/yokingma/weclaws/agent-browsernpx skills add yokingma/weclaws --skill agent-browsergit clone --depth 1 https://github.com/yokingma/weclawsWhat 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 | $0.00035 | $0.00936 |
| Opus 5 | $0.00017 | $0.00468 |
| Sonnet 5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
agent-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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-browser
Browser automation CLI for AI agents. In WeClaws, browser automation is remote-only: the only supported runtime paths are agent-browser -p browserless and explicit remote --cdp connections, so the real browser runs in a remote backend instead of inside the nested sandbox or on the host.
Loading Skills
You must run agent-browser skills get <name> before running any agent-browser commands.
This file does not contain command syntax, flags, or workflows. That content is served
by the CLI and changes between versions. Guessing at commands without loading the skill
will produce incorrect or outdated invocations.
agent-browser skills get core --full # Required before core browser automation
agent-browser skills get <name> --full # Include references and templates
Available Skills
- core — Core browser automation
- dogfood — Exploratory testing and QA
- electron — Electron desktop app automation
- slack — Slack workspace automation
- vercel-sandbox — Browser automation in Vercel Sandbox
- agentcore — Browser automation on AWS Bedrock AgentCore
WeClaws Runtime Path
Primary path in the default Compose deployment:
export BROWSERLESS_API_URL="http://browserless:3000"
export BROWSERLESS_API_KEY="your-browserless-token"
agent-browser -p browserless open https://example.com
Alternative supported path for direct CDP debugging:
agent-browser --cdp "ws://browserless:3000/chromium?token=your-browserless-token" open https://example.com
Browserless Direct
Use Browserless directly only when the task is a one-shot remote browser job and does not need agent-browser's interactive workflow.
- Prefer
agent-browser -p browserlessfor multi-step page interaction, refs/snapshots, form filling, QA, and exploratory debugging. - Prefer direct Browserless HTTP or WebSocket/CDP usage when the task is closer to backend browser execution, such as a single screenshot, PDF, scrape, or attach/connect flow.
- Treat Browserless as the remote browser backend and
agent-browseras the default operator-facing workflow on top of that backend. - If the task starts as a one-shot Browserless job but turns into iterative page interaction, switch back to
agent-browser -p browserless.
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.
- 3d ago First seen · 87 lines · 35 tokens per session scan A de48c0f0b1c1
agent-browser is a skill published in the GitHub repository yokingma/weclaws (38 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 936 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
ui-screenshots
Take UI screenshots using agent-browser. Use this skill to capture visual state of UI components for code review, visual regression testing, or documentation.
md-fetch-summarize
Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…
playwright
Use when the task requires capturing or automating a real browser from the terminal.
browse
Drive a real stealth browser from your shell — act on websites (order food, file an expense, pull data behind a login), with per-person persistent sign-ins via the provider's managed auth (Kernel, Anchor, or Browserbase — picked by which API key you have). Use for ACTING on a site; to just read a page, use curl/wget…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.