Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add arjun988/blender-skills --skill collision-proxygit clone --depth 1 https://github.com/arjun988/blender-skillsWrote 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/arjun988/blender-skills/collision-proxy)<a href="https://agentmods.dev/skills/arjun988/blender-skills/collision-proxy"><img src="https://agentmods.dev/badge/skills/arjun988/blender-skills/collision-proxy.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00553 |
| Opus 5 | $0.00016 | $0.00277 |
| Sonnet 5 | $0.00006 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
collision-proxy 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 8d 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.
What it actually says
Collision Proxy
Simple, stable colliders. Prefer primitives and convex pieces over render mesh.
When to Use
- Game physics / blocking volumes
- Unreal UCX export
- Unity mesh or primitive colliders
- Hitboxes for interactables
Workflow
Identify collision needs → Build proxies → Name correctly
→ Test overlaps → Export with render mesh
Collider Types
| Type | Use |
|---|---|
| Box | Crates, walls, simple props |
| Capsule | Characters, poles |
| Sphere | Balls, soft approximates |
| Convex hull | Organic / irregular single body |
| Multiple convex (UCX) | Vehicles, complex props |
Unreal Naming
UCX_SM_Asset_01
UCX_SM_Asset_02
- Must match associated mesh naming rules for auto-association
- Convex only for UCX
Unity Notes
- Prefer engine primitives when possible
- Mesh colliders: convex toggle for dynamic rigidbodies
- Keep proxy collection exportable
Authoring Rules
- Slightly smaller than visual mesh to reduce snagging (project-dependent)
- No holes; watertight convex pieces
- Apply scale
- Origin aligned with render mesh
- Collection:
COL_Collision_[Asset]
Validation
- Player cannot fall through intended blockers
- No huge invisible walls beyond mesh
- Wheel/character capsules oriented correctly
- Named for target engine
Constraints
MUST DO
- Prefer few simple shapes over one complex mesh
- Match engine naming conventions
- Keep proxies in dedicated collection
MUST NOT DO
- Use render LOD0 as physics mesh by default
- Non-convex UCX for Unreal auto-convex workflows
Reference Guide
| Topic | Reference | Load When |
|---|---|---|
| Collider Recipes | references/collider-recipes.md |
When needed |
| Engine Naming | references/engine-naming.md |
When needed |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 90 lines · 32 tokens per session scan A 35c3b05ea2b3
collision-proxy is a skill published in the GitHub repository arjun988/blender-skills (172 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 553 once invoked, about $0.0002 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
alpha-scene-gen
Generates AI 3D models through the Alpha3D MCP connector and imports them directly into the user's currently open Blender scene, scaled and placed to build out a described environment, prop set, or character roster. Use this skill whenever the user wants to populate, build, dress, furnish, or fill a Blender scene with…
blender-interchange
Blender interchange skill for typed FBX/OBJ/USD imports, GLTF/USD/Alembic exports, and repeatable batch exports. Use for moving assets between DCC, game, and pipeline tools before falling back to scripting.
blender-physics
Blender rigid body, soft body, cloth, collision, force fields, particle systems, constraints, and simulation cache tools.
blender-asset-source
Blender asset source discovery — search filesystem and asset libraries for importable 3D assets.
blender-light-rig
Blender reusable light rigs, HDRI/world setup and rotation animation, light grouping, and render-view controls.
blender-rigging
Blender authoring skill for armatures, bones, constraints, armature binding, shape keys, drivers, and simple retargeting. Use this for character setup before falling back to blender-scripting.