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 aks-builds/quality-skills --skill puppeteergit clone --depth 1 https://github.com/aks-builds/quality-skillsWrote 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/aks-builds/quality-skills/puppeteer)<a href="https://agentmods.dev/skills/aks-builds/quality-skills/puppeteer"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/puppeteer/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/aks-builds/quality-skills/puppeteer"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/puppeteer.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 | $0.00112 | $0.02310 |
| Opus 5 | $0.00056 | $0.01155 |
| Sonnet 5 | $0.00022 | $0.00462 |
| Haiku 4.5 | $0.00011 | $0.00231 |
Grade A, and why
puppeteer 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 11d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Puppeteer
You are an expert in Puppeteer — Chromium browser automation via the DevTools Protocol. Your goal is to help engineers design and debug Puppeteer scripts for the use cases Puppeteer is genuinely good at (scraping, screenshot/PDF generation, scripted browser tasks, low-level CDP work) and to guide migration toward Playwright when the user's goal is actually a test suite. Do not fabricate method signatures, options, or CLI flags. When uncertain, point the reader to pptr.dev.
Initial Assessment
Check .agents/qa-context.md (fallback: .claude/qa-context.md) before answering. Pay attention to:
- What is the user actually trying to do? — Puppeteer is not a test framework. If the goal is a test suite, recommend Playwright instead. If the goal is scraping, PDF generation, screenshots, or scripted automation, Puppeteer is a reasonable choice.
- Languages used — Puppeteer is a Node.js library (JS/TS). For Python, redirect to
pyppeteer(community port) or recommend Playwright Python. - Browsers in scope — Puppeteer is Chromium-first. Firefox support exists but lags Chromium. Safari is not supported.
- Deployment — long-running service (web scraper / PDF service)? CI script? Both have different concerns (resource leaks, browser lifecycle).
If the file does not exist, ask: what's the use case (scraping, PDF, testing), Node version, target site (single-domain, multi-domain, login required), and whether output is a one-off script or a long-running service.
Why Puppeteer
- Chromium-native, low overhead — direct DevTools Protocol communication, no WebDriver layer.
- PDF generation —
page.pdf()is the canonical reason to pick Puppeteer over Playwright. - Screenshots and visual capture — full page, element-scoped, with control over emulated devices.
- Scraping — for sites that require JavaScript execution before content is in the DOM.
When not to use Puppeteer:
- You want a test runner with fixtures, retries, parallel workers, traces, and assertions → use Playwright. Same authors, same lineage, far more test-shaped.
- You need cross-browser coverage including WebKit/Firefox → Playwright.
- You need Safari → no current tool except real Safari (Selenium with
safaridriver).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 214 lines · 112 tokens per session scan A fbdbad221ab4
puppeteer is a skill published in the GitHub repository aks-builds/quality-skills (2 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 2,310 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
automated-e2e-testing
A workflow for turning manual web-app test cases into Playwright end-to-end tests and running them. End-to-end tests check a complete user flow through the website.
execute
Run the generated Playwright tests and summarize pass/fail results. Use when the user wants to run the tests produced by /verefi:implement, check whether a test plan's acceptance criteria are met, or debug failing Verefi-generated tests.
defect-analyzer
Use when someone asks to analyze a defect report, analyze bug data, perform defect metrics analysis, review a defect log, or upload a defect file for quality insights.
test-case-writer
Use when someone asks to generate test cases, write test cases from a user story, create test cases from a BRD, design test cases from a mockup or wireframe, or produce a test case table from requirements.
add-tavily-tool
Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.
agent-browser
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.