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 espennilsen/pi --skill qa-testinggit clone --depth 1 https://github.com/espennilsen/piWrote 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/espennilsen/pi/qa-testing)<a href="https://agentmods.dev/skills/espennilsen/pi/qa-testing"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/qa-testing/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/espennilsen/pi/qa-testing"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/qa-testing.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 | $0.00173 | $0.02940 |
| Opus 5.5 | $0.00069 | $0.01176 |
| Sonnet 5.5 | $0.00035 | $0.00588 |
| Haiku 4.5 | $0.00017 | $0.00294 |
Grade A, and why
qa-testing scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
timeout 60 bash -c 'until curl -sf http://localhost:3000 > /dev/null; do sleep 2; done' How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Testing — Web Application Testing with cmux_browser
Test running web applications by interacting as a real user via cmux_browser, then report findings with structured evidence.
Prerequisites
- The application must be running and accessible via HTTP
- cmux_browser tool must be available
- If the app isn't running, start it first (see Setup below)
Workflow
Step 1: Setup
If the app is already running, skip to Step 2.
If the app needs to be started:
# Start in a background cmux pane
cmux_split({ direction: "down", command: "cd /path/to/project && npm run dev\n" })
# Wait for it to be ready (check the pane output)
cmux_read({ surface: "surface:N" })
# Or poll the URL
cmux_browser({ action: "open", url: "http://localhost:3000" })
cmux_browser({ action: "wait", waitCondition: "load-state", loadState: "networkidle" })
If Docker is needed:
cd /path/to/project && docker compose up -d
# Wait for healthy
timeout 60 bash -c 'until curl -sf http://localhost:3000 > /dev/null; do sleep 2; done'
Step 2: Smoke Test
Verify the app loads at all before deeper testing.
# Open the app
cmux_browser({ action: "open", url: "http://localhost:3000" })
# Wait for it to load
cmux_browser({ action: "wait", waitCondition: "load-state", loadState: "networkidle" })
# Screenshot the initial state
cmux_browser({ action: "screenshot" })
# Check for JavaScript errors
cmux_browser({ action: "errors" })
# Check console output
cmux_browser({ action: "console" })
# Get a DOM snapshot (accessibility tree)
cmux_browser({ action: "snapshot" })
If the smoke test fails (page doesn't load, crash errors), stop and report immediately.
Step 3: Functional Testing
For each acceptance criterion, follow this pattern:
# 1. Navigate to the relevant state
cmux_browser({ action: "navigate", url: "/some-page" })
cmux_browser({ action: "wait", waitCondition: "load-state", loadState: "networkidle" })
# 2. Interact as a real user
cmux_browser({ action: "click", selector: "button.submit" })
cmux_browser({ action: "fill", selector: "input[name='email']", value: "[email protected]" })
cmux_browser({ action: "press", key: "Enter" })
# 3. Verify outcomes
cmux_browser({ action: "wait", waitCondition: "text", text: "Success" })
cmux_browser({ action: "snapshot", interactive: true }) # check element states
cmux_browser({ action: "get", selector: ".result", subaction: "textContent" })
cmux_browser({ action: "is", selector: ".modal", subaction: "visible" })
# 4. Screenshot as evidence
cmux_browser({ action: "screenshot" })
# 5. Check for errors after the interaction
cmux_browser({ action: "errors" })
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 · 327 lines · 173 tokens per session scan A 840dcd23d82f
qa-testing is a skill published in the GitHub repository espennilsen/pi (122 stars, last pushed 9d ago), licensed MIT. It adds 173 tokens to every session and 2,940 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…