Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/smileynet/teach-menpx agentmods add skills/smileynet/teach-me/asset-conversionWrote 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/smileynet/teach-me/asset-conversion)<a href="https://agentmods.dev/skills/smileynet/teach-me/asset-conversion"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/asset-conversion/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/smileynet/teach-me/asset-conversion"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/asset-conversion.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 | $0.00115 | $0.01290 |
| Opus 5.5 | $0.00046 | $0.00516 |
| Sonnet 5.5 | $0.00023 | $0.00258 |
| Haiku 4.5 | $0.00012 | $0.00129 |
Grade A, and why
asset-conversion 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset Conversion
Two headless-Blender tools produce the downloadable 3D artifacts a lesson needs. Both SKIP gracefully (exit 0) when Blender is absent — so they're safe to call anywhere, but only DO work on a machine with Blender configured.
When to use
- A lesson names a
.glb/.gltf/.blend/.fbxthe learner should download, and you need to produce or convert it. - You have a Kenney/CC0 source (often
.fbxor.glb) and need the editable.blendand a Godot-ready.glb. - Do NOT convert what already exists in the right form — most Kenney props already ship a
.glb; use it directly. Convert only to (a) derive a missing.blend, (b) turn an FBX-only asset into.glb, or (c) emit the same asset in multiple formats for a format-comparison lesson.
The two tools
Derive an editable .blend (glb/gltf/fbx/obj → .blend)
mise run make-blend -- <input.glb|.gltf|.fbx|.obj> [--out reference/blender/NAME.blend] [--force]
Imports the source into an empty scene, applies transforms (fixes FBX-cm 100× + axis bugs), saves a
compressed .blend. Default output is <input>.blend beside the input.
ASCII FBX is unsupported. Blender's importer rejects it (
"ASCII FBX files are not supported"). Kenney kits ship ASCII FBX — derive the.blendfrom the kit's.glbinstead (Kenney ships both). Prefer.glb/.gltfsources formake-blendwhen available.
Export a Godot-ready glTF (.blend/fbx/obj/gltf → .glb/.gltf)
mise run export-godot-glb -- <input.blend> [--out reference/code/SLUG/NAME.glb] [--separate] [--apply] [--force]
Exports with Godot-correct options (export_yup — glTF/Godot 4 are both +Y-up, so no import
rotation; lights/cameras excluded; materials from Principled BSDF), then runs the Tier-1
structural oracle (gltf-format-oracle.py) on the result and fails if it doesn't pass.
--separate— emit.gltf+.bin+ textures (the "files travel together" case) instead of.glb.--apply— bake modifiers (static props only). Omit for rigged/morph assets — baking DROPS shape keys.
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 Changed · +4 lines a2dde02c16dd
- 1mo ago First seen · 78 lines · 115 tokens per session scan A 82b570881745
asset-conversion is a skill published in the GitHub repository smileynet/teach-me (3 stars, last pushed 25d ago), licensed MIT. It adds 115 tokens to every session and 1,290 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 2026-09-08.
Other skills, from other repositories
anki
Anki spaced repetition learning system reference. Covers the science of SRS and SM-2 algorithm, card design principles, optimal deck settings, FSRS scheduler, study workflow, essential add-ons, custom templates, filtered decks, and AnkiConnect API.
reading-metaskill
A reading and learning guide based on building a regular reading habit, choosing books, and understanding difficult subjects through original works and explanation.
gentleman-trainer
Vim Trainer RPG system patterns for Gentleman.Dots. Trigger: When editing files in installer/internal/tui/trainer/, adding exercises, modules, or game mechanics.
game-builder
Convert any topic into playable browser games. Types: trivia, matching, word puzzles, adventure games. Uses Phaser.js or Kaboom.js.
assisted-mastery
Makes agent reasoning visible, surfaces tradeoffs, and fades help so humans build judgment. Use when reviewing or learning from agent-written code.
antivibe
Code learning and audit framework. Analyze any codebase — new, legacy, or AI-generated — and produce educational explanations or architectural audits. Use when the user wants to understand WHAT and WHY behind any code, not just accept it.