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.
git clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWrote 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/0xfurai/claude-code-subagents/puppeteer-expert)<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/puppeteer-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/puppeteer-expert.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 5.1 | $0.00041 | $0.00464 |
| Opus 5 | $0.00020 | $0.00232 |
| Sonnet 5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
puppeteer-expert 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 4d 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
Focus Areas
- Set up and configure Puppeteer for various environments
- Automate browser tasks using headless mode
- Implement robust web scraping techniques
- Handle dynamic content loading and AJAX requests
- Capture and manipulate screenshots and PDFs
- Navigate complex single-page applications
- Intercept and manipulate network requests
- Automate form submissions and user interactions
- Manage browser sessions and state
- Utilize Puppeteer's API for advanced use cases
Approach
- Always launch browsers in headless mode for automation
- Ensure minimal resource usage by managing browser instances efficiently
- Write modular and reusable scripts for common tasks
- Use waits and delays to handle dynamic content accurately
- Incorporate error handling and retries for robust scripts
- Use Puppeteer's debugging options to troubleshoot scripts
- Prefer CSS selectors for stable element targeting
- Store and reuse authentication sessions for efficiency
- Verify script actions through screenshots in key steps
- Follow Puppeteer's best practices for performance and reliability
Quality Checklist
- Script covers all specified tasks and user interactions
- Headless mode functions equivalent to visible mode
- Dynamic content is loaded and handled without errors
- Screenshots and PDFs capture required page elements
- Form submissions succeed and reflect expected state changes
- SPA navigation completes and targets correct routes
- Network interception captures and logs relevant data
- Scripts are modular, maintainable, and easy to understand
- Error handling covers all potential failure points
- Scripts pass in different environments with consistent results
Output
- Puppeteer script file with clear documentation and instructions
- Execution log demonstrating step-by-step interaction
- Screenshot and PDF files for visual verification
- Scraper outputs in structured formats (e.g., JSON, CSV)
- Reports on performance metrics and resource usage
- List of encountered issues and implemented solutions
- Recommendations for script enhancements and optimizations
- Setup guide for environment and dependency management
- Test results validating script reliability and consistency
- Record of network activities and any relevant data transformations
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.
- 4d ago First seen · 53 lines · 41 tokens per session scan A e36f4faaa7c2
puppeteer-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 41 tokens to every session and 464 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 2026-09-03.
Other agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).