Borrowing it
Nothing to install: this file belongs to OhaoTech/niua-blender-mcp. 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/OhaoTech/niua-blender-mcp/main/.grok/skills/niua-blender-finisher/SKILL.mdgit clone --depth 1 https://github.com/OhaoTech/niua-blender-mcpWrote 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/ohaotech/niua-blender-mcp/niua-blender-finisher)<a href="https://agentmods.dev/skills/ohaotech/niua-blender-mcp/niua-blender-finisher"><img src="https://agentmods.dev/badge/skills/ohaotech/niua-blender-mcp/niua-blender-finisher/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/ohaotech/niua-blender-mcp/niua-blender-finisher"><img src="https://agentmods.dev/badge/skills/ohaotech/niua-blender-mcp/niua-blender-finisher.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 | $0.00059 | $0.00721 |
| Opus 5 | $0.00030 | $0.00360 |
| Sonnet 5 | $0.00012 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
niua-blender-finisher 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 11d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NIUA Blender Finisher
The MCP is the hands. This is how you look without paying for pixels twice.
Connect
The bridge autostarts with Blender (0.2.2) — no N-panel click. system-health
tells you the truth: bridge: alive plus the open .blend. If it is down, the
N-panel (View3D → sidebar → Niua) has Start/Stop and the preference to opt out;
NIUA_BLENDER_MCP_AUTOSTART=0 / NIUA_BLENDER_MCP_PORT=<port> override it.
Observe
- Numbers first:
feedback-readinessandfeedback-quality. No images. - Look:
feedback-critique(orfeedback-capture/feedback-capture_views). Images arrive as MCP image parts. The JSON isreport/uv/ view metadata only —datais omitted on purpose. Missing JSONdatais not a failed capture; checkavailableand the image parts. - Do not
read_filethose PNGs after a critique. You already have the images. - Leave
resat the tool default (640 on critique). Do not raise it unless asked. - Prefer
ortho4. One visual call per turn. No turntable/lookdev loops. feedback-capturewithview: "current"renders the live scene camera and honoursMATERIAL/RENDERED— use it to judge a material. Theortho4presets frame every mesh in the scene, so a studio floor or backdrop will dwarf the subject; hide the set first, or passobject.
Reach past the tool surface
system-execute_python is enabled by default and returns what it learns:
captured stdout, plus a result variable if the snippet sets one, plus partial
stdout on failure. Use it to answer questions the typed tools do not cover —
engine settings, node graphs, per-vertex data — not to bypass tools that exist.
result = {"engine": bpy.context.scene.render.engine,
"raytracing": bpy.context.scene.eevee.use_raytracing}
If a call is refused, system-health's python_enabled is the effective
answer for both gates (the add-on preference AND the server's
NIUA_BLENDER_MCP_ALLOW_PYTHON).
Trust the reports
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.
- 11d ago First seen · 59 lines · 59 tokens per session scan A 14bee2840fa0
niua-blender-finisher is a skill published in the GitHub repository OhaoTech/niua-blender-mcp (0 stars, last pushed 27d ago), licensed Apache-2.0. It adds 59 tokens to every session and 721 once invoked, about $0.0003 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 2026-08-31.
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.