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/migoxlab/webqa-agent/webqanpx skills add MigoXLab/webqa-agent --skill webqagit clone --depth 1 https://github.com/MigoXLab/webqa-agentWhat 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 | $0.00036 | $0.00337 |
| Opus 5 | $0.00018 | $0.00169 |
| Sonnet 5 | $0.00007 | $0.00067 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
webqa 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 2d 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
WebQA
Use WebQA when the user wants to test a website or page from a real user's perspective.
Route
- For a normal website, page, URL, feature, login, search, form, navigation, or core-flow test, read
references/mini-agent.md. - For MCP server installation, API key setup, IDE configuration, or environment variables, read
references/setup.md. - For authenticated testing with browser cookies, read
references/cookies.mdbefore running the test. - For API errors, execution timeouts, missing reports, worker-limit errors, or stuck executions, read
references/troubleshooting.md.
Defaults
- If the user provides a URL and no specific objective, run the default mini-agent task: verify the homepage loads, core entry points are visible, and the main interactions show no obvious errors.
- If the user describes a test objective but gives no URL, ask for the URL before running WebQA.
- Keep the task focused on one URL and one natural-language objective.
- Do not treat execution completion as test success; final pass/fail reporting must come from the test report or documented fallback logic.
Boundaries
- This public skill exposes WebQA's MCP quick-mode testing workflow.
- Do not promise future capabilities until their reference files exist.
- Do not load
cookies.md,setup.md, ortroubleshooting.mdduring a normal public-page test unless that context is needed.
What ships with it
4 files 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.
- 2d ago First seen · 29 lines · 36 tokens per session scan A eef62cc0b427
webqa is a skill published in the GitHub repository MigoXLab/webqa-agent (228 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 337 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
printed-curtain-render
Generate a browser-based p5.js curtain simulation that weaves user-supplied PNG, JPEG, or WebP artwork and optional text into individually moving strands. Use when users ask for an interactive curtain or thread simulation, artwork woven into cloth or ropes, image-bearing fabric motion, 可交互线帘/幕布, 图片织入布料, printed…
threejs-earth-render
Clone or update https://github.com/vibe-motion/threejs-earth and render the Three.js Earth route animation with Puppeteer frame capture. Use when users ask for 三维地球航线动画, Three.js Earth, 地球飞线, globe route animation, or exporting an Earth GIF/MP4/PNG sequence.
find-docs
Use globally installed ctx7 for API/library docs when local docs or CLI help are insufficient. Trigger for API syntax, config, setup, migrations, version-sensitive, or post-cutoff questions. Do not use for web research, local files, browser automation, or installs.
tavily-web
Use Tavily CLI for web search, URL extraction, site mapping, and cited research. Trigger when the user needs current web info, asks to search/read a page, provides URLs, or wants a sourced report. Do not use for browser automation, local docs, or Tavily setup.
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
当用户明确希望连接到已运行的 Chrome 浏览器、扫描本地 CDP 端口、显式指定 cdpport，或让多个 agent / 工具共享同一个浏览器时，使用本 skill。browser 默认不开放调试端口；仅当用户明确希望其他本地工具附加时才显式传入 cdpport。.