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/skills/hunt-live-programs/SKILL.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/skills/levy-street/world-of-claudecraft/hunt-live-programs)<a href="https://agentmods.dev/skills/levy-street/world-of-claudecraft/hunt-live-programs"><img src="https://agentmods.dev/badge/skills/levy-street/world-of-claudecraft/hunt-live-programs/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/skills/levy-street/world-of-claudecraft/hunt-live-programs"><img src="https://agentmods.dev/badge/skills/levy-street/world-of-claudecraft/hunt-live-programs.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 | $0.00121 | $0.02042 |
| Opus 5.5 | $0.00048 | $0.00817 |
| Sonnet 5.5 | $0.00024 | $0.00408 |
| Haiku 4.5 | $0.00012 | $0.00204 |
Grade A, and why
hunt-live-programs 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 1mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunt live programs
The rule (src/render/CLAUDE.md, "Every material a live frame can draw for the first time
after the curtain has a prewarm home"): a program linked live blocks the presenting thread
for 40 ms when the driver cache is warm and for 0.4 to 2.3 s when it is cold, and several in
one frame add up to the multi-second freezes the fleet reports. This skill is the procedure
to find WHICH materials escape, name their owner, and give each one a home.
Why a fleet capture is not enough
- The
live-programevents inrenderer.gpuPrep.eventscarry a LABEL, which isprogram.name || cacheKey, and three names a program aftermaterial.name. Most escapees are unnamed, so the label is a raw cache key nobody can map to a file. - The two tools that name materials,
renderDiagnostics(newMaterials,firstVisibleObjects) and the shader warm audit (unexpectedByName), only arm on a DEV build served on localhost with?perfTrace=1. - An offline tour misses what a live world brings: gear, mounts, pets, other players, dungeon and raid content, encounter VFX.
So the hunt runs the dev client of THIS worktree, proxied to production, in a browser the operator plays in, and aggregates at the end. Nobody reads the raw feed live.
Step 1: run the session
node scripts/live_program_hunt.mjs
What it does, in order: kills the port, purges node_modules/.vite and .vite-temp,
starts vite with --force on a generated prod-hookup config (/api and /ws proxied to
https://worldofclaudecraft.com, changeOrigin on the WebSocket entry, the part the base
config lacks), grep-verifies the served module, opens a headed Chrome on
http://localhost:5173/?perfTrace=1&perf with a persistent profile under tmp/ (the login
survives sessions), polls the renderer four times a second while the operator plays, and on
Enter, Ctrl-C or browser close writes tmp/live-program-hunt-<id>/report.md (plus the raw
samples.ndjson and meta.json) and stops vite.
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.
- 1mo ago First seen · 128 lines · 121 tokens per session scan A 10152cf5a5da
hunt-live-programs is a skill published in the GitHub repository levy-street/world-of-claudecraft (2,323 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 2,042 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-18.
Other skills, from other repositories
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
cli-anything-nsight-graphics
Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.
performance-optimization
Find and fix game performance problems methodically — measure with the engine profiler first, reason about the frame-time budget, locate the CPU-vs-GPU bottleneck, then apply the right fix: object pooling, draw-call batching, fewer allocations/GC spikes, and asset budgets. Engine- neutral method that pairs with each…
unity-console
Capture and query the Unity Editor console.
diagnosing-bgs-problems
A symptom-first guide for investigating crashes, frame-rate drops, stuttering, freezes, and startup failures in Bethesda Game Studios games with mods.
axiom-audit-spritekit
Use when the user wants to audit SpriteKit game code for common issues — physics bitmask issues, draw call waste, node accumulation, and action leaks.