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 Limbicnation/hermes-asset-pipeline --skill asset-format-bridgegit clone --depth 1 https://github.com/Limbicnation/hermes-asset-pipelineWrote 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/limbicnation/hermes-asset-pipeline/asset-format-bridge)<a href="https://agentmods.dev/skills/limbicnation/hermes-asset-pipeline/asset-format-bridge"><img src="https://agentmods.dev/badge/skills/limbicnation/hermes-asset-pipeline/asset-format-bridge/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/limbicnation/hermes-asset-pipeline/asset-format-bridge"><img src="https://agentmods.dev/badge/skills/limbicnation/hermes-asset-pipeline/asset-format-bridge.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 | $0.00055 | $0.01525 |
| Opus 5.5 | $0.00022 | $0.00610 |
| Sonnet 5.5 | $0.00011 | $0.00305 |
| Haiku 4.5 | $0.00006 | $0.00153 |
Grade A, and why
asset-format-bridge 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 2mo 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset Format Bridge Skill
Convert and transport assets between ComfyUI (image/DTX), Blender (mesh/texture), and Godot (GLTF scene) environments.
Format Priority for This Pipeline
| From | To | Best Format | Notes |
|---|---|---|---|
| ComfyUI (image) | Blender | PNG 2K/4K → UV-project or texture paint | Use as albedo/normal map in Blender |
| ComfyUI (image) | Godot | WebP or PNG in res://textures/ |
Sprite2D or StandardMaterial3D texture |
| Blender (mesh) | Godot | GLB (binary GLTF) | Godot 4.x native GLTF import |
| Blender (mesh) | ComfyUI | FBX → USD → image render | Texture projection workflow |
| Godot (scene) | Blender | GLB export via Godot CLI | Scene-to-mesh for re texturing |
Core Conversion Tools
Image Format Conversion
from PIL import Image
from pathlib import Path
def convert_image(src: Path, dst_format: str = "PNG", size: tuple[int,int] = None, quality: int = 95) -> Path:
"""Convert image to target format, optional resize."""
img = Image.open(src)
if size:
img = img.resize(size, Image.LANCZOS)
if img.mode in ("RGBA", "P") and dst_format in ("JPG", "JPEG"):
img = img.convert("RGB")
out = src.with_suffix(f".{dst_format.lower()}")
img.save(out, format=dst_format, quality=quality)
return out
Texture Pack Generation (ComfyUI → 3D)
from PIL import Image, ImageDraw
from pathlib import Path
def generate_texture_pack(diffuse_path: Path, output_dir: Path = None) -> dict[str, Path]:
"""Generate albedo + normal + roughness texture set from a single diffuse.
For pipeline: ComfyUI output → projection-ready texture set for Blender/Godot.
"""
output_dir = output_dir or diffuse_path.parent
diffuse = Image.open(diffuse_path).convert("RGB")
base = diffuse_path.stem
textures = {}
# Albedo (diffuse as-is)
albedo = output_dir / f"{base}_albedo.png"
diffuse.save(albedo)
textures["albedo"] = albedo
# Normal map approximation (Sobel on diffuse)
import numpy as np
arr = np.array(diffuse, dtype=np.float32)
gray = 0.299*arr[:,:,0] + 0.587*arr[:,:,1] + 0.114*arr[:,:,2]
sobel_x = np.gradient(gray, axis=1)
sobel_y = np.gradient(gray, axis=0)
normal_z = np.sqrt(1 - np.clip(sobel_x**2 + sobel_y**2, 0, 1))
normal = np.stack([sobel_x, sobel_y, normal_z], axis=-1)
normal = ((normal + 1) / 2 * 255).astype(np.uint8)
normal_map = Image.fromarray(normal, mode="RGB")
normal_path = output_dir / f"{base}_normal.png"
normal_map.save(normal_path)
textures["normal"] = normal_path
return textures
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.
- 2mo ago First seen · 154 lines · 55 tokens per session scan A 709c0ba4740b
asset-format-bridge is a skill published in the GitHub repository Limbicnation/hermes-asset-pipeline (7 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,525 once invoked, about $0.0002 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 2026-08-31.
asset-format-bridge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| asset-format-bridgeLimbicnation/hermes-asset-pipeline | Skill | 7 | 6mo ago | Apache-2.0 | A | 55 | Claude Code, Codex |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 10d ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 121 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.0k | 8d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| unity-addressablesBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 25 | Claude Code, Codex |
| unity-manual-componentBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 36 | Claude Code, Codex |