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/AGENTS.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/instructions/levy-street/world-of-claudecraft/agents-md)<a href="https://agentmods.dev/instructions/levy-street/world-of-claudecraft/agents-md"><img src="https://agentmods.dev/badge/instructions/levy-street/world-of-claudecraft/agents-md/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/instructions/levy-street/world-of-claudecraft/agents-md"><img src="https://agentmods.dev/badge/instructions/levy-street/world-of-claudecraft/agents-md.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 | $0.00990 | $0.00990 |
| Opus 5 | $0.00495 | $0.00495 |
| Sonnet 5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
world-of-claudecraft AGENTS.md 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex entry point
This file owns Codex runtime behavior for World of ClaudeCraft. The root and
directory-local CLAUDE.md files remain canonical for repository facts, architecture,
hard invariants, conventions, commands, the default task workflow and deliverable
contract, and the QA contract. Claude-specific model,
memory, Workflow, slash-command, and agent-runtime instructions do not apply to Codex.
Do not edit or replace the Claude setup unless the user explicitly asks for that work.
Start safely
- Run
git status --shortbefore edits and preserve unrelated user work. - Follow the default task workflow in
CLAUDE.md: base the work on the latestrelease/**branch, nevermain, and create a separate worktree for the task. - Read the root
CLAUDE.mdin full. Before reading or changing files in a directory, read that directory'sCLAUDE.mdif it exists. Codex builds its instruction chain at session start, so opening a nested file does not load local guidance automatically. - Use
rgand targeted reads to discover the current shape. Follow existing code and tests instead of relying on remembered inventories or line numbers.
Never revert, discard, stage, commit, push, file an issue, post a review, or mutate a
remote system unless the user authorized that action. If a commit is requested, stage
only this task's files and follow the scoped Conventional Commit rule in CLAUDE.md.
Work effectively
- Keep the main thread responsible for integration and final verification.
- Parallelize bounded exploration, log analysis, and read-only reviews when useful. Give overlapping files one implementation owner and wait for every delegated task before reporting completion.
- Treat subagent results as evidence to verify, not verdicts to relay unchanged.
- Use the active session model and reasoning setting. Do not weaken acceptance criteria, tests, or review depth for a faster model. Route by task shape, not a hardcoded model: clear mechanical work can run fast, while ambiguous architecture and security work needs deeper reasoning.
- Fetch current official documentation for external APIs and libraries. Do not write unstable interfaces from memory.
- Prefer small modules, decisive tests, and existing seams. Do not add frameworks or abstractions without a concrete repository need.
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 · 79 lines · 990 tokens per session scan A f5921cfd1ef8
world-of-claudecraft AGENTS.md is an instructions file published in the GitHub repository levy-street/world-of-claudecraft (2,251 stars, last pushed yesterday), licensed MIT. It adds 990 tokens to every session, about $0.0049 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).