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 dcc-mcp/dcc-mcp-blender --skill blender-asset-sourcegit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-blenderWrote 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/dcc-mcp/dcc-mcp-blender/blender-asset-source)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-blender/blender-asset-source"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-blender/blender-asset-source/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/dcc-mcp/dcc-mcp-blender/blender-asset-source"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-blender/blender-asset-source.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 | $0.00024 | $0.00600 |
| Opus 5.5 | $0.00010 | $0.00240 |
| Sonnet 5.5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
blender-asset-source 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.
What it actually says
blender-asset-source
Search discoverable asset sources and return validated AssetDescriptor[] for
the downstream import pipeline.
Supports:
- Filesystem search — walk a local directory for supported 3D file formats.
- Blender asset library search — scan registered Blender asset libraries.
- Type filtering — restrict results to specific formats (blend, fbx, obj, usd, etc.).
- Name matching — case-insensitive substring filter on asset names.
Library registrations come from bpy.context.preferences.filepaths.asset_libraries.
Search is read-only: it does not refresh Asset Browser UI or save preferences.
context.asset_library_status distinguishes scanned, no_libraries,
unavailable, partial, and error; missing APIs or unreadable libraries are not empty
successful library searches. Broken registrations do not hide later valid
libraries: partial results include explicit status and warnings. With source=all, filesystem results can be
returned with a library warning. Reaching the result budget may truncate search.
This searches supported files directly inside registered local directories,
not asset-marked data-blocks inside .blend files. Remote libraries, catalogs,
tags, and recursive dependency discovery require separate capabilities.
Tools
| Tool | Description |
|---|---|
search_assets |
Search asset sources and return validated AssetDescriptor[] |
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.
- 1mo ago Changed · +2 lines dfcfb795fd16
- 1mo ago Changed · +12 lines 8c7f78cd4014
- 2mo ago First seen · 53 lines · 24 tokens per session scan A 3aa8fadf948e
blender-asset-source is a skill published in the GitHub repository dcc-mcp/dcc-mcp-blender (62 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 600 once invoked, about $0.0001 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 2026-08-30.
blender-asset-source compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blender-asset-sourcedcc-mcp/dcc-mcp-blender | Skill | 62 | 2d ago | MIT | A | 24 | Claude Code |
| blender-bridgeCallMeJones/blender-agent-bridge | Skill | 27 | 28d ago | GPL-3.0 | A | 89 | Codex |
| blender-reference-modelingCallMeJones/blender-agent-bridge | Skill | 27 | 28d ago | GPL-3.0 | A | 79 | Codex |
| blender-retopologyCallMeJones/blender-agent-bridge | Skill | 27 | 28d ago | GPL-3.0 | A | 76 | Codex |
| blender-directorarjun988/blender-skills | Skill | 2.2k | 2d ago | MIT | A | 0 | Claude Code |
| environment-artistarjun988/blender-skills | Skill | 2.2k | 2d ago | MIT | A | 43 | Claude Code |
| hard-surfacearjun988/blender-skills | Skill | 2.2k | 2d ago | MIT | A | 54 | Claude Code |