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 AbdullahMalik17/malikclaw --skill browser-automation-cdpgit clone --depth 1 https://github.com/AbdullahMalik17/malikclawWrote 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/abdullahmalik17/malikclaw/browser-automation-cdp)<a href="https://agentmods.dev/skills/abdullahmalik17/malikclaw/browser-automation-cdp"><img src="https://agentmods.dev/badge/skills/abdullahmalik17/malikclaw/browser-automation-cdp/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/abdullahmalik17/malikclaw/browser-automation-cdp"><img src="https://agentmods.dev/badge/skills/abdullahmalik17/malikclaw/browser-automation-cdp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00216 |
| Opus 5 | $0.00015 | $0.00108 |
| Sonnet 5 | $0.00006 | $0.00043 |
| Haiku 4.5 | $0.00003 | $0.00022 |
Grade A, and why
browser-automation-cdp 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 9d 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 via CDP Skill
Use this skill for interacting with dynamic JavaScript-rendered single-page apps (SPAs), taking screenshots, and extracting structured web data.
Key Capabilities
- DOM Navigation & Execution: Execute JS scripts inside the browser context.
- Visual Capture: Take full-page screenshots or element clips.
- Form Automation: Click elements, input form text, handle file uploads.
- Network Inspection: Monitor HTTP headers, API calls, and performance metrics.
Example Tool Usage
{
"url": "https://news.ycombinator.com",
"action": "screenshot",
"wait_selector": ".titleline"
}
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.
- 9d ago First seen · 29 lines · 31 tokens per session scan A 83d687b0252c
browser-automation-cdp is a skill published in the GitHub repository AbdullahMalik17/malikclaw (15 stars, last pushed 13d ago), licensed MIT. It adds 31 tokens to every session and 216 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
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
web-browse
Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.
c-browser
Headless browser automation — navigate pages, click elements, fill forms, take screenshots, scrape content using agent-browser or playwright-cli.
browser-automation
Automate browser tasks - navigate, click, type, fill forms, extract data, take screenshots.
firecrawl
Scrape, search et interagit avec le web via Firecrawl — extrait du contenu propre en Markdown depuis n'importe quelle URL, recherche sur le web, crawl de sites entiers, et interaction avec des pages dynamiques (clics, formulaires). Clef API dans FIRECRAWLAPIKEY.
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.