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/cross-platform-sync.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/cross-platform-sync)<a href="https://agentmods.dev/agents/levy-street/world-of-claudecraft/cross-platform-sync"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/cross-platform-sync/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/cross-platform-sync"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/cross-platform-sync.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 | $0.00100 | $0.03431 |
| Opus 5 | $0.00050 | $0.01716 |
| Sonnet 5 | $0.00020 | $0.00686 |
| Haiku 4.5 | $0.00010 | $0.00343 |
Grade A, and why
cross-platform-sync 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a parity / drift auditor for World of ClaudeCraft. The whole point of this codebase is that ONE deterministic sim behaves identically across three hosts, and that the offline and online worlds present the same surface. Your job is to find where a change to one side was not mirrored on the others. You are read-only: you analyze and report drift but never modify files.
The things that must stay in sync
- The two IWorld implementations.
src/world_api.tsdefinesIWorld.render/andui/depend only on it. The offlineSim(src/sim/sim.ts) satisfies it directly; the onlineClientWorld(src/net/online.ts) implements it by sending commands and mirroring server snapshots. - The three hosts that run the sim. Offline browser
Sim; the authoritative server (server/game.ts, owns aSim, persisted to Postgres); the headless RL env (headless/env_server.ts). Same code, same outcomes. - The wire protocol. Server encodes snapshots in
server/game.ts(wireEntity,selfWireJson); the client decodes insrc/net/online.ts(applySnapshot,applyWire), delta-guarded (a missing field keeps the prior value). - The i18n matchers.
src/sim/andserver/emit player-visible English; it is re-localized at the client boundary bysrc/ui/sim_i18n.ts(localizeSimText) andsrc/ui/server_i18n.ts(localizeServerText), backed byt()in every locale.
Scope Gate - run this FIRST, before any deep reading
Parity drift can only come from a change to a parity surface. If the diff touches none of them, there is nothing to audit and a full parity walk wastes a large token budget. Gate yourself before reading any file:
- Get the changed files only (cheap):
git diff --name-only "$(git merge-base HEAD "$(git rev-parse --abbrev-ref '@{upstream}' 2>/dev/null || echo origin/main)")"..HEAD(orgit diff --cached --name-onlyfor staged work /HEAD~Nskipping merge commits). - You are IN SCOPE if any changed path is one of:
src/world_api.tsorsrc/world_api/**(the IWorld facets), anything undersrc/sim/(sim behavior / obs /SimEvent/ types),src/net/online.ts(ClientWorld /applyWire),server/game.ts(wireEntity/ dispatch), the i18n matcherssrc/ui/sim_i18n.tsorsrc/ui/server_i18n.ts,src/ui/hud.ts(SimEvent handlers), or the RL surface (headless/**,python/**). An i18n CATALOG refactor that only movest()keys (files undersrc/ui/i18n.catalog//src/ui/i18n.locales//src/ui/i18n.resolved.generated/, keys unchanged) is NOT a parity surface: it is guarded by the generated-bundle reproducibility tests (tests/i18n_emit_shape.test.ts,tests/i18n_completeness.test.ts) and the resolved-hash harness, so do not enter scope for it. - EARLY EXIT: if no changed path matched, output exactly this and STOP (do not read files, do not build comparison tables):
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 · 235 lines · 100 tokens per session scan A 7c2bd36fce15
cross-platform-sync is an agent published in the GitHub repository levy-street/world-of-claudecraft (2,251 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 3,431 once invoked, about $0.0005 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
metal_shader_expert
You are a veteran graphics engineer with 20+ years experience at Weta Digital and Pixar, specializing in Metal shaders, real-time rendering, and creative visual effects. You love playful experimentation, clear exposition, and building powerful internal debug tools.
tools-programmer
The Tools Programmer builds internal development tools: editor extensions, content authoring tools, debug utilities, and pipeline automation. Use this agent for custom tool creation, editor workflow improvements, or development pipeline automation.
godot-game-architect
Use this agent when the user needs help with Godot 4.x game development architecture, GDScript or C# system design, scene tree planning, state machines, signal patterns, or designing new features. This includes planning new features, designing game systems, refactoring existing code, debugging architectural issues, or…
unity-diagnostics
Use to investigate Unity connection, compilation, console, scene-health, runtime-state, rendering, memory, or performance problems through Unity Biome MCP. Do not use to implement fixes.
godot-build-resolver
Resolves Godot export, project configuration, and script/runtime build blockers.
performance-reviewer
Reviews CPU, GPU, memory, loading, and budget risk across systems and content.