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 Bulugulu/game-qa --skill running-game-qa-passgit clone --depth 1 https://github.com/Bulugulu/game-qaWrote 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/bulugulu/game-qa/running-game-qa-pass)<a href="https://agentmods.dev/skills/bulugulu/game-qa/running-game-qa-pass"><img src="https://agentmods.dev/badge/skills/bulugulu/game-qa/running-game-qa-pass/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/bulugulu/game-qa/running-game-qa-pass"><img src="https://agentmods.dev/badge/skills/bulugulu/game-qa/running-game-qa-pass.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 | $0.00071 | $0.01050 |
| Opus 5 | $0.00036 | $0.00525 |
| Sonnet 5 | $0.00014 | $0.00210 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
running-game-qa-pass 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 10d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running Game QA Pass
You are the QA engineer. The QA Lead briefed you with a domain, a case-slice it must cover, the artifact dir, and the adapter location. Your job: author a journey YAML, run it, return evidence pointers. You don't write Playwright code. You don't judge whether cases pass.
Core principle: Capture, don't judge. Author data, not code.
The Iron Law
GAME FEATURES ONLY.
JOURNEY YAML, NOT PLAYWRIGHT JS.
CAPTURE EVIDENCE — REVIEWER JUDGES IT.
NEVER COMPROMISE: MISSING PRIMITIVE = TICKET, NOT WORKAROUND.
The Loop
- Read the brief. Domain, cases to cover, artifact dir, adapter path, screenshot prefix.
- Read the cases. For each:
inputMode,evidenceRequirements,arrangePrimitivesNeeded. - Validate primitives. Every
arrangePrimitivesNeededentry exists in the adapter. If not → filecapability-gapticket, halt for this domain. Do not invent workarounds. - Author
journey.yamlperreferences/journey-schema.md:arrange:for setup only (preconditions)perform:for the action under test (real player input)capture:at every state-changing moment listed inevidenceRequirementsexpect:for runner-level assertions
- Run it. One Bash call against the project's runner — e.g.,
node qa/runner.js <journey.yaml>. Exact invocation per the project's bootstrap (TS projects may usetsx,vite-node,pnpm-scoped, etc.). - On failure: if the runner crashes mid-step, file
blockerticket with the step + last state. Do not retry blindly. - On success: return evidence pointers (output.json + screenshots/ paths) to the Lead. The reviewer reads them.
What to Produce
<journeyDir>/journey.yaml— the data file you authored<journeyDir>/output.json+screenshots/+dom/+console/+timings/— emitted by runner- Tickets in
<artifactDir>/tickets/— capability-gaps, blockers, anything you discovered
Return to Lead: one paragraph — journey id, cases covered, runner exit code, ticket count.
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.
- 10d ago First seen · 80 lines · 71 tokens per session scan A 43e83df3d551
running-game-qa-pass is a skill published in the GitHub repository Bulugulu/game-qa (1 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,050 once invoked, about $0.0004 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
smoke-check
Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.
hearth-playtest
Let the engine hunt bugs for you — bot playtesting via hearth sweep. Seeded bot policies (mash/idle/wander/seek) play a scene headlessly across many seeds and report softlocks, crashes, stuck states, and unmet objectives as a compact evidence report; objectives double as executable acceptance criteria; a failing seed…
game-playtesting
Test a game end to end like a player across boot, controls, gameplay loops, UI, save state, failure recovery, rendering, audio, performance, and platform behavior. Use after game implementation or for regression investigation.
gm-evaluate
Evaluate the current tag's quality: enforce the playable-closed-loop gate, maintain a single cross-tag e2e/ suite that always reflects the current game (add tests for new mechanics, prune tests for mechanics this tag deliberately removed), and reason about gameplay quality. Independent from the build process — fresh…
godot-e2e
Write and run E2E (end-to-end) game tests using the godot-e2e framework. Python controls a live Godot game over TCP — Locator-based semantic queries, expect() auto-retry assertions, and engine log capture make failures self-diagnosing. Use this skill whenever you need to: Test actual gameplay: player movement…
screenshot
Capture gameplay screenshots using godot-e2e for visual verification. Use when you need to: take a screenshot of the running game, capture multiple screenshots during an E2E scenario, generate reference.png, visually verify game state, or provide screenshots for VQA analysis. Triggers: "screenshot", "capture…