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 daxaur/openpaw --skill c-browsergit clone --depth 1 https://github.com/daxaur/openpawWrote 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/daxaur/openpaw/c-browser)<a href="https://agentmods.dev/skills/daxaur/openpaw/c-browser"><img src="https://agentmods.dev/badge/skills/daxaur/openpaw/c-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/daxaur/openpaw/c-browser"><img src="https://agentmods.dev/badge/skills/daxaur/openpaw/c-browser.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.00324 |
| Opus 5.5 | $0.00012 | $0.00130 |
| Sonnet 5.5 | $0.00006 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
c-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.
What it actually says
Browser Automation
agent-browser (Vercel)
Navigate and interact with web pages using structured snapshots:
# Open a URL
agent-browser open "https://example.com"
# Get interactive element snapshot (shows clickable refs)
agent-browser snapshot -i
# Click an element by ref
agent-browser click @e2
# Fill a form field
agent-browser fill @e5 "search query"
# Take annotated screenshot
agent-browser screenshot --annotate
# Type text
agent-browser type "hello world"
# Press keys
agent-browser press Enter
playwright-cli (Microsoft)
Token-efficient browser automation designed for AI agents:
# Install browser (first time)
playwright-cli install-browser
# Navigate to URL
playwright-cli navigate "https://example.com"
# Get page snapshot
playwright-cli snapshot
# Click element
playwright-cli click "Submit button"
# Fill input
playwright-cli fill "Search" "query text"
# Screenshot
playwright-cli screenshot
Guidelines
- Use agent-browser for AI-driven web interaction (snapshot-ref pattern)
- Use playwright-cli for structured automation and testing flows
- Always check snapshots before clicking — element refs change between pages
- For login flows, navigate step by step and verify each page loads
- Respect robots.txt and rate limits when scraping
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 First seen · 67 lines · 29 tokens per session scan A f660c1b3f97c
c-browser is a skill published in the GitHub repository daxaur/openpaw (173 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 324 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
Web Research
Browser-driven or scraping-based skill for real-time internet extraction using Playwright and HTTP-based fetching.
verify
Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.
ketch
Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but the CLI is the primary interface. Use when a question needs live sources: 'research X', 'what are people saying about Y'…
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
web-access
A method for handling difficult web tasks across search, page fetching, and a real browser. It covers sites that need login sessions, dynamic pages, anti-bot handling, or exploration before their structure is understood.
web-scraper
Scrape, crawl, and extract data from websites. Use when users ask to scrape web pages, extract content, crawl websites, or collect data from the internet.