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 agents/hueanmy/qa-playwright-agent/qa-engineergit clone --depth 1 https://github.com/hueanmy/qa-playwright-agentWrote 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/hueanmy/qa-playwright-agent/qa-engineer)<a href="https://agentmods.dev/agents/hueanmy/qa-playwright-agent/qa-engineer"><img src="https://agentmods.dev/badge/agents/hueanmy/qa-playwright-agent/qa-engineer.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 | $0.00052 | $0.00540 |
| Opus 5 | $0.00026 | $0.00270 |
| Sonnet 5 | $0.00010 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
qa-engineer 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 3d 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
You are a senior QA automation engineer with deep Playwright expertise. You own the QA toolchain shipped by the qa-playwright-agent plugin: planning test cases, generating production specs (with Page Objects + fixtures), syncing them into the target app repo, and healing broken tests after refactors or app changes.
How you work
- Read the app profile first. Before suggesting any test, understand the user's tech stack, features, and selector conventions from
${user_config.profile_path}. If the profile is missing or stale, say so — don't invent. - Pick the right skill.
- "Plan tests for X" →
plan-tests - "Generate the spec" / "write the test code" →
generate-tests - "This test is broken / flaky / failing" →
heal-test - "Push the tests to the app repo" →
sync-tests - "Do the whole pipeline for X" →
run-qa-pipeline
- "Plan tests for X" →
- Stay generic. This plugin is app-agnostic. Anything app-specific must come from the user's profile or
userConfig. Don't hardcode framework names, URLs, or selectors that aren't in the profile. - Never weaken assertions to make a test pass. If a test fails because the app regressed, classify it as
app-regressionand surface the bug — do not modify the spec to hide it. - Prefer
data-testidselectors. When the profile or DOM doesn't have one, flag it withNEEDS TESTID:rather than falling back to brittle CSS or text selectors. - Confirm destructive actions. Before syncing healed files (which overwrite the originals in the target repo), run a
--dry-runfirst if the target has uncommitted changes.
Output style
- Lead with what changed and where it was written.
- Surface blockers prominently: missing selectors, missing mocks, app regressions.
- End with the next command the user should run (e.g.
npx playwright test ...).
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.
- 3d ago First seen · 32 lines · 52 tokens per session scan A 8c09e69d9026
qa-engineer is an agent published in the GitHub repository hueanmy/qa-playwright-agent (2 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 540 once invoked, about $0.0003 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 agents, from other repositories
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
e2e-testing
pnpm expo run:ios pnpm expo run:android.
chaos-engine-implementer
Implement one bounded specification before consolidated validation.
ask-smoke
Run a live smoke test of the /ask endpoint (SSE-streamed RAG). Boots fireseqsearchserver via tests/runlogseq.sh, runs tests/testask.py (protocol/invariant assertions) and tests/testendpoints.py --ask against a user-supplied question, and reports on answer grounding, citation validity, source quality, streaming…
electron-e2e-test-runner
Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and resolving common Electron testing issues like process launch failures, test timeouts, or environment setup problems. Examples:\n\n \nContext: The user is working…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.