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/GEMINI.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/gemini-md)<a href="https://agentmods.dev/instructions/levy-street/world-of-claudecraft/gemini-md"><img src="https://agentmods.dev/badge/instructions/levy-street/world-of-claudecraft/gemini-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/gemini-md"><img src="https://agentmods.dev/badge/instructions/levy-street/world-of-claudecraft/gemini-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 | $0.00777 | $0.00777 |
| Opus 5 | $0.00388 | $0.00388 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade B, and why
world-of-claudecraft GEMINI.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Configs live in `~/.gemini/config/mcp_config.json` and `~/.gemini/settings.json`. How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Developer Guide: World of ClaudeCraft
The root CLAUDE.md and the per-directory CLAUDE.md files are the canonical source of
truth. This project is driven primarily through Claude Code; read the root CLAUDE.md in full
and the local CLAUDE.md when you open files in a directory. They own the architecture, the hard
invariants (sim purity and determinism, graphics fairness, i18n, secrets, the no-em-dash and
no-emoji rule), the module-first doctrine, the commands, the UI / a11y / i18n rules, the git
conventions (Conventional Commits WITH a scope, and every commit carries a body), and the
default task workflow: base the work on the latest release/** branch rather than main,
use a separate worktree, add tests with every src/sim/ or server/ change, and deliver a
mergeable PR gated locally with node scripts/gate_select.mjs (the pre-merge bar; npm run gate is the deeper full suite). Before calling an implementation complete,
run the QA gate described in docs/qa-gate.md. When this guide and CLAUDE.md disagree,
CLAUDE.md wins. Do not keep a second copy of those rules here; this file holds only the
Gemini-session notes that have no home in CLAUDE.md.
GEMINI.md is tracked (committed); do not add it to .gitignore.
Model capabilities and optimization
- Thinking level. Raise it for complex logic (simulation consistency, pathfinding, WS sync, DB schemas, multi-step algorithms); lower it for lightweight edits (docs, simple UI alignment) to save latency and cost. Reason through edge cases and blast radius before writing code, and red-team your own diff before declaring it done.
- Context-cache discipline (large input discount). Keep imports stable and grouped at the
top of files; avoid gratuitous edits to the large coordinators (
src/sim/sim.ts,src/ui/hud.ts,src/main.ts,src/render/renderer.ts, this guide), since any prefix or import change invalidates the cache and raises latency and cost. Keep static reference material early in the prompt. - Agentic loop. Spawn a research subagent for long-horizon research or verbose E2E runs to
keep the main context clean. Use the native
scheduletool for delayed or recurring checks instead of terminalsleep. Gemini at high reasoning tends toward flowery narration, so keep comments and explanations concise and functional.
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 · 44 lines · 777 tokens per session scan B 0223d15bbe4a
world-of-claudecraft GEMINI.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 777 tokens to every session, about $0.0039 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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).