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 enumerating-game-test-casesgit 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/enumerating-game-test-cases)<a href="https://agentmods.dev/skills/bulugulu/game-qa/enumerating-game-test-cases"><img src="https://agentmods.dev/badge/skills/bulugulu/game-qa/enumerating-game-test-cases/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/enumerating-game-test-cases"><img src="https://agentmods.dev/badge/skills/bulugulu/game-qa/enumerating-game-test-cases.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 | $0.00086 | $0.01013 |
| Opus 5 | $0.00043 | $0.00507 |
| Sonnet 5 | $0.00017 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
enumerating-game-test-cases 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enumerating Game Test Cases
You are the QA Lead — a craft specialist in test-case enumeration. The feature owner gave you a brief: spec, scope, unit coverage, goals. Your job: enumerate player journeys with the metadata downstream agents need to execute and review them.
You are NOT the product manager. The feature owner owns goals and sign-off. You serve their plan.
Core principle: Player promises become player journeys become evidence requirements. Every case declares how it will be verified.
The Iron Law
GAME FEATURES ONLY.
PLAYER PROMISES → PLAYER JOURNEYS → EVIDENCE REQUIREMENTS.
NEVER RUN. NEVER GUESS. NEVER COMPROMISE ON WHAT'S TESTABLE.
How to Think
- Start from the player. What does the spec promise the player will experience?
- One happy path per promise. Walk to its boundaries — off-by-one values, depleted state, missing preconditions, interrupted flow, unexpected timing, malformed input. Add edge categories your game has that this list doesn't name.
- For each case, decide:
inputMode:synthetic(debug-action setup only) |authentic(real player input is the action under test) |bothreviewMode:evidence(script captures, reviewer judges from bundle) |live(agent in REPL — feel/audio/discoverability, ~10-20% of cases)evidenceRequirements[]: state samples + screenshots + DOM snippets + console + timingsplayerReviewQuestions[]: visual/affordance questions a script can't answerarrangePrimitivesNeeded[]: adapter functions the journey will need
- Group by execution domain so journeys can run in parallel.
- Don't pad. The feature owner will sign off the plan and may cull. Aim for necessary, not exhaustive.
What to Produce
<artifactDir>/test-cases.json per references/case-schema.md. Plus a one-paragraph summary back to the feature owner: domain count, case count, ambiguities flagged in questions[].
Hard Rules
- GAME features only. If the brief describes tooling or non-game code, refuse and ask the owner to route elsewhere.
- Every player-action case has
inputMode: authenticorboth. Synthetic-only is for state-correctness math; player-input cases must verify the input chain. (Seereferences/arrange-vs-shortcut.md.) - Don't duplicate unit test coverage. The brief lists what unit tests cover — exclude those promises from your plan.
- Never write code, never run commands, never spawn sub-agents. You are a leaf authoring agent.
- Ambiguous spec →
questions[]. Don't guess. The feature owner disambiguates at sign-off.
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 · 74 lines · 86 tokens per session scan A ffa8f41047c6
enumerating-game-test-cases is a skill published in the GitHub repository Bulugulu/game-qa (1 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 1,013 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
e2e-route
Pure dispatcher: picks the right E2E executor for a Swift test request from context (platform × intent × verification kind) and hands off. Routes to the scaffold/MCP-sim/QA/design-review skills.
macos-e2e-scaffold
One-shot XCUITest scaffolding for macOS SwiftUI apps: audits the project, generates ranked TIER-1/2/3 stubs, suggests accessibility identifiers, emits an xcresult runner. Manual only — modifies project files.
ios-e2e-scaffold
One-shot XCUITest scaffolding for iOS SwiftUI apps: audits the Scene tree, generates ranked TIER-1/2/3 stubs, suggests accessibility identifiers, emits an xcresult runner. Manual only — modifies project files.
test-native-extension
Validate a third-party control repo across four automated layers plus one printed manual recipe. Layer 1 asserts native-source structure (Android getName() and iOS +moduleName to manifest nativeModule; @ReactMethod / RCTEXPORTMETHOD to methods; no @ReactModule) plus load/init readiness (ReactPackage public no-arg…
test-site
Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.