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 Kevin-Liu-01/Agent-Machines --skill qagit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/qa)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/qa"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/qa/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/kevin-liu-01/agent-machines/qa"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/qa.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 | $0.00055 | $0.01234 |
| Opus 5.5 | $0.00022 | $0.00494 |
| Sonnet 5.5 | $0.00011 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
qa 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 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.
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.
This is a copy
89% identical to gstack-qa — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA — Test, Find Bugs, Fix, Verify
Adapted from GStack by Garry Tan. You are a QA lead testing a real application in a real browser. You find bugs, fix them, generate regression tests, and verify.
Contract
This skill guarantees:
- Real browser testing via agent-browser (Lightpanda default, Chrome for auth)
- Every bug found has a reproduction path with screenshots
- Fixes are atomic (one commit per bug)
- Every fix generates a regression test
- Tests run and pass before the fix is committed
- Commit format:
fix(qa): BUG-NNN — description - Test commit format:
test(qa): regression test for BUG-NNN
Phases
Phase 1: Discover the App
agent-browser snapshot <url>
Understand the app:
- What is this? (Marketing site, dashboard, SaaS app, docs site)
- What are the key user flows?
- What's the tech stack? (Check page source, framework indicators)
- Is auth required? (If redirected to login, ask Kevin for credentials or use
--engine chrome --profilefor existing session)
Phase 2: Test Key Flows
Walk through 3-5 key user flows. For each:
- Navigate to the starting point
- Screenshot the initial state
- Interact — click buttons, fill forms, navigate
- Observe — check for:
- Console errors (
agent-browser console --errors) - Visual glitches (overlapping elements, broken layouts)
- Functional failures (buttons that don't work, forms that don't submit)
- Loading states (missing spinners, infinite loading)
- Error handling (what happens when things go wrong?)
- Responsive behavior (test at 375px, 768px, 1440px)
- Console errors (
- Screenshot the result of each interaction
Phase 3: Bug Report
For each bug found:
BUG-NNN: {title}
=================
Severity: CRITICAL / HIGH / MEDIUM / LOW
Flow: {which user flow}
Steps to reproduce:
1. Navigate to {url}
2. Click {element}
3. Observe {behavior}
Expected: {what should happen}
Actual: {what actually happens}
Screenshot: {path}
Console errors: {if any}
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 · 157 lines · 55 tokens per session scan A a8f6c96c2175
qa is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (30 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 1,234 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to gstack-qa, differing in 13 lines, and is treated as a copy.
Other skills, from other repositories
adhoc-verification
Produce fresh, focused, local verification evidence for a code change without relying on the full test suite. Use when a system reminder (or the user) demands ad-hoc verification after an edit, or when you want to prove one behavior in isolation. Covers the correct way to write a throwaway supertest/harness script…
bestow-curse
Bestow Curse saddles a target with a lasting disadvantage. The real-world version is constraint injection: deliberately adding friction, limitations, or handicaps to see how a system, process, or team adapts. This is the skill of resilience testing through artificial adversity — bandwidth throttling, feature removal…
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
bug-bash
Run an agent bug bash of the Xum web UI in the bug-bash sandbox (TesterArmy e2e explore charters, each in its own locked-down Docker container with a seeded xum server), then verify each finding with a failing repro test. Use when asked to "bug bash" Xum, run e2e explore agents, the MCP Apps suite or the story tests…