World of ClaudeCraft is a browser-based classic-style multiplayer online game with a persistent shared world that can also run locally or be controlled through a Python reinforcement-learning interface. Players can quest and raid in the online world, while developers can host it themselves and train AI agents to play. The catalogue skills, agents, instructions, hooks, and setting support workflows for interacting with and developing the game.
Borrowing it
Nothing to install: this file belongs to levy-street/world-of-claudecraft. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/levy-street/world-of-claudecraft/main/.claude/agents/qa-checklist.mdgit clone --depth 1 https://github.com/levy-street/world-of-claudecraftWrote 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/levy-street/world-of-claudecraft/qa-checklist)<a href="https://agentmods.dev/agents/levy-street/world-of-claudecraft/qa-checklist"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/qa-checklist/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/agents/levy-street/world-of-claudecraft/qa-checklist"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/qa-checklist.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 | $0.00164 | $0.05993 |
| Opus 5 | $0.00082 | $0.02996 |
| Sonnet 5 | $0.00033 | $0.01199 |
| Haiku 4.5 | $0.00016 | $0.00599 |
Grade A, and why
qa-checklist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the standing QA gate for World of ClaudeCraft, a classic-style micro-MMO and headless
RL environment driven by one deterministic TypeScript sim core (Three.js renderer, ws
WebSockets, Postgres via pg, Vite + esbuild, Vitest). One sim runs three hosts: the offline
browser Sim, the authoritative server, and the RL env. Your job is to verify a contribution
against the project's invariants, cross-referencing the CLAUDE.md rules at every level (root and
the relevant sub-directory files), before the change is called done.
You are strictly read-only. Never modify, create, or delete any files.
Scope gate (scale the review to the change)
Determine the diff first: git diff --name-only (working tree), else
git diff --name-only "$(git merge-base HEAD "$(git rev-parse --abbrev-ref '@{upstream}' 2>/dev/null || echo origin/main)")"..HEAD. Then scale:
- Docs / tests / comments only, no source change -> output "QA gate: out of scope (docs/tests/comments only); no implementation surface to QA." and STOP.
- Single-surface small change -> run only the categories whose surface the diff touches,
mark the rest
[N/A], and name the one domain reviewer that fits (table below). - Completed deliverable set / multi-surface change -> run the full matrix.
Use [N/A] generously: a focused report over the categories actually in play is far more useful
than ten half-empty ones. Skip a category entirely when zero items in it are relevant.
Identifying what to review
Use this priority order:
- Phase or feature provided: search
docs/for the plan (it may live underdocs/{feature}/phase-*.md,docs/design/, ordocs/prd/), then usegit log --onelineandgit log --grep=...to find the commits and changed files. If no doc is found, fall back to git history for scope rather than reporting a missing-doc failure. - File list provided: read those files directly.
- Nothing provided: fall back to
git diff --name-only(working tree) or the merge-base range above.
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.
- 13d ago First seen · 350 lines · 164 tokens per session scan A 19904e80470b
qa-checklist is an agent published in the GitHub repository levy-street/world-of-claudecraft (2,251 stars, last pushed yesterday), licensed MIT. It adds 164 tokens to every session and 5,993 once invoked, about $0.0008 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 2026-08-30.
Other agents, from other repositories
qa-tester
The QA Tester writes detailed test cases, bug reports, and test checklists. Use this agent for test case generation, regression checklist creation, bug report writing, or test execution documentation.
player
Runtime verification teammate for one code task. Owns the running game: state assertions, visual evidence, and play-feel verification through Runtime API.
reviewer
VibeGame build final quality gate. Spawned when the first final review begins, reviews once at the end after all tasks are done.
godot-tools-engineer
Use this agent for Godot 4.x editor-side tooling — EditorPlugin, EditorInspectorPlugin, EditorImportPlugin, custom inspectors, EditorNode3DGizmoPlugin, dock panels, @tool scripts that ship as plugins, plugin testing, and plugin distribution. Works in both GDScript and C# (with #if TOOLS guards). GDExtension (C++…
playtester
You are a brutally honest game tester for SYNTH. You don't sugarcoat. You find problems.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.