What is bootstrap-game-qa-system?

A one-time setup guide for browser-game projects that installs the foundation for automated quality checks. It provides a reusable test runner, a project-specific adapter, and a format for describing player journeys.

Use it only when starting QA infrastructure for a browser game, including debug-action setup, adapter creation, and authoring journeys for the runner.

It gives a game project a consistent way to prepare and run checks without rebuilding the testing foundation or replacing existing debug tools.

bootstrap-game-qa-system — Skill for Claude Code by Bulugulu

Install

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.

Any agent

npx skills add Bulugulu/game-qa --skill bootstrap-game-qa-system

Clone the repo

git clone --depth 1 https://github.com/Bulugulu/game-qa

Made for: Claude Code.

Or install game-qa, the plugin that ships this one along with the rest of its 6 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bulugulu/game-qa/bootstrap-game-qa-system/github.svg)](https://agentmods.dev/skills/bulugulu/game-qa/bootstrap-game-qa-system)

Your own site

<a href="https://agentmods.dev/skills/bulugulu/game-qa/bootstrap-game-qa-system"><img src="https://agentmods.dev/badge/skills/bulugulu/game-qa/bootstrap-game-qa-system/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bulugulu/game-qa/bootstrap-game-qa-system"><img src="https://agentmods.dev/badge/skills/bulugulu/game-qa/bootstrap-game-qa-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,762 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00056	$0.01762
Opus 5	$0.00028	$0.00881
Sonnet 5	$0.00011	$0.00352
Haiku 4.5	$0.00006	$0.00176

Measured 9d ago against content hash 6edbbe0c39fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bootstrap-game-qa-system 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (references/qa-adapter.template.ts, references/runner.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/game-qa/skills/bootstrap-game-qa-system/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bootstrap Game QA System

You are setting up game-qa infrastructure for a browser-game project. The plugin ships three reference artifacts you'll copy and adapt:

references/runner.ts — project-agnostic runner (copy as-is, do not modify)
references/qa-adapter.template.ts — adapter skeleton (copy and fill in)
references/journey-schema.md — YAML contract the runner consumes (don't copy; engineers read this to author journeys)

The seam: the runner is framework-fixed, the adapter is project-specific. If you need new behavior, add a primitive to the adapter or extend the journey schema — never fork the runner.

Run once per project. If parts exist, gap-fill — don't rebuild.

The Iron Law

GAME PROJECTS ONLY.
RUN ONCE. GAP-FILL, DON'T REPLACE.
ARRANGE/PROBE PRIMITIVES ONLY — NEVER ACTIONS-UNDER-TEST.

What to Build (in order)

Debug system. An action registry (server-authoritative for multiplayer projects; client-side for single-player), reflection-driven catalog (debug.help()), window.debug.<action> proxy on the client, [debug-ready] + [debug-event] console contract. If the project has these, verify and move on. If not, build the minimum: a window.debug object exposing project actions, plus a one-shot console.log("[debug-ready]") once it's wired.
Drop the runner. Copy references/runner.ts to <project>/qa/runner.ts. Start unmodified. The runner is extensible — add new perform: types or capture: at: kinds as your game needs them (see "Extending the framework" below) — but don't silently change existing semantics. If your project is plain JS, run via tsx / ts-node / vite-node, or strip type annotations after copy. The runner imports ./adapter.ts — the next step creates it.
Adapt the adapter. Copy references/qa-adapter.template.ts to <project>/qa/adapter.ts. Then fill in:
- url — your project's dev URL
- readyMarker — the console string your project emits when window.debug is wired
- hudSelector — optional CSS selector for the HUD if you want capture: at: [hud] to work
- arrange.* — wrappers around your window.debug.* for state setup (see arrange-vs-shortcut discipline below)
- probe.* — wrappers for read-only state queries; always include snapshot as the default fallback
- events.subscribe / events.drain — wire to your project's event source (DOM events, EventEmitter, WebSocket messages, etc.)
- reset — idempotent between-journey reset
- clearByTag — sweep entities this runner created (use the spawnTracker pattern in the template)

Read the full file on GitHub · 104 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

9d ago First seen · 104 lines · 56 tokens per session scan A 6edbbe0c39fd

Subscribe to this mod's changes

bootstrap-game-qa-system is a skill published in the GitHub repository Bulugulu/game-qa (1 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,762 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.

Claude Code E2E testing Game development Testing agentic-coding ai-agents browser-games claude-code-plugin game-development

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.

striderZA/OpenCodeGameStudios · 61 tokens

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…

echoo19/hearth · 112 tokens

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.

metaspartan/cybara · 48 tokens

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…

RandallLiuXin/GodotMaker · 84 tokens

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…

RandallLiuXin/GodotMaker · 189 tokens

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…

RandallLiuXin/GodotMaker · 87 tokens