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/blender-anim-pipeline/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/blender-anim-pipeline)<a href="https://agentmods.dev/skills/levy-street/world-of-claudecraft/blender-anim-pipeline"><img src="https://agentmods.dev/badge/skills/levy-street/world-of-claudecraft/blender-anim-pipeline/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/blender-anim-pipeline"><img src="https://agentmods.dev/badge/skills/levy-street/world-of-claudecraft/blender-anim-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 125 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00074 | $0.02671 |
| Opus 5 | $0.00037 | $0.01336 |
| Sonnet 5 | $0.00015 | $0.00534 |
| Haiku 4.5 | $0.00007 | $0.00267 |
Grade A, and why
blender-anim-pipeline 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Animation authoring: pose-sample-and-blend, with a Blender escalation path
Full mechanics reference: scripts/anim/pose_blend.mjs (the shared module every consumer
imports; read its JSDoc before writing a new build script). This skill is the operating
procedure and the decision of when to escalate past it.
Scope check first
This is for new authored clips on rigs this repo already ships (public/models/chars/,
public/models/creatures/). A brand-new creature or player skin needs the asset-pipeline
skill first (rig + base clip vocabulary); this skill only adds MORE clips to a rig that
already has a donor clip library baked in.
Why two techniques, not one
Issue #2889 proposed a Blender MCP server driving new clip authoring at scale (1000+ clips). Investigation found:
- No
blender-mcpserver is connected to this project, and no script in this repo invokes ablenderbinary. Blender-driven authoring is genuinely new tooling, not a wired-up path. scripts/build_bow_anims.mjs(merged, live in production, powers the hunter's bow-draw clip) is an existing, dependency-free precedent for authoring brand new clips WITHOUT Blender: it samples poses already baked into a rig's OWN clip library at chosen timestamps, blends between them with hand-authored easing, and bakes the result into a new clip wired through the ordinaryanimUrls+ClipMapmechanism.
So: pose-sample-and-blend is the primary technique for the large majority of this initiative's scope (a class or creature family needing a distinct clip almost always has a rig that already ships adjacent donor poses: an idle, a windup, a hold, a gesture). Headless Blender is the escalation path, used only when no donor clip anywhere in the rig's shipped library can supply the pose the new clip needs (a genuinely novel silhouette: a new weapon grip angle, a creature-specific pose no shipped clip approximates).
Both land through the exact same seam: an animUrls GLB entry consumed by an existing or new
VisualDef/ClipMap in src/render/characters/manifest.ts. Neither technique touches
src/render/renderer.ts as the animation driver, and neither adds a dispatch path outside
visualKeyFor / ClipMap / VisualDef (issue #2889's own acceptance criteria).
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 · 170 lines · 74 tokens per session scan A 2dd503b5a969
blender-anim-pipeline is a skill published in the GitHub repository levy-street/world-of-claudecraft (2,251 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 2,671 once invoked, about $0.0004 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 skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.