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 agentmods add skills/ifbars/blender-agent-studio/blender-iterative-refinementnpx skills add ifBars/blender-agent-studio --skill blender-iterative-refinementgit clone --depth 1 https://github.com/ifBars/blender-agent-studioWrote 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/ifbars/blender-agent-studio/blender-iterative-refinement)<a href="https://agentmods.dev/skills/ifbars/blender-agent-studio/blender-iterative-refinement"><img src="https://agentmods.dev/badge/skills/ifbars/blender-agent-studio/blender-iterative-refinement.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.00823 |
| Opus 5 | $0.00039 | $0.00411 |
| Sonnet 5 | $0.00015 | $0.00165 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
blender-iterative-refinement 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 5d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Iterative Refinement
Start from a complete candidate produced by the relevant creation workflows. Do not replace their normal construction stages. This skill adds a bounded critic, source repair, identical recheck, and rollback decision.
Freeze the candidate
- Turn the user-visible request into critical requirements, other visible requirements, technical gates, and explicit exclusions.
- Record invariants the repair must preserve: scale, aggregate world bounds, orientation, names, hierarchy, animation range, materials, approved forms, editable systems, and export behavior.
- Preserve the candidate source, authored artifact, fresh export import, metrics, hero view, fixed multiview contact sheet, and required animation or deformation frames. Never overwrite the only copy of the candidate.
Run a separate critic pass
Open the preserved images with an image-viewing tool. Before editing, write a
pass, fail, or unclear ledger for every critical requirement and cite the
view or frame that proves the judgment. Names, source code, hierarchy, and
metrics cannot make an absent, occluded, or unreadable subject a visual pass.
Treat transmissive enclosures and emissive subjects as a coupled visibility problem. Inspect the actual target render engine and exposure: a valid shader graph is not enough when glass becomes opaque or emission blooms into a white blob. The enclosed subject must retain a traceable silhouette and local color contrast in every required view and animation sample.
Prioritize in this order:
- missing or unreadable primary subject, required operation, or critical relationship;
- failed deterministic gate or aggregate task limit;
- severe geometry, deformation, contact, material, lighting, or export defect;
- secondary polish.
For a visible mechanism, trace the whole causal chain across critical frames:
driver, connector, attachment, pivot or guide, moving part, and final state.
Thin, occluded, or low-contrast connections are unclear, even when numerical
endpoint residuals pass.
What ships with it
1 file 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.
- 5d ago First seen · 84 lines · 77 tokens per session scan A 62d23042e659
blender-iterative-refinement is a skill published in the GitHub repository ifBars/blender-agent-studio (10 stars, last pushed 18d ago), licensed MIT. It adds 77 tokens to every session and 823 once invoked, about $0.0004 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
dcc-mcp-blender-setup
Set up dcc-mcp-blender for an agent or operator: install Blender Python dependencies with Blender's bundled interpreter, install a startup bridge, generate MCP host configuration, and run a first live-tool smoke prompt.
blender-import-to-scene
Blender cross-DCC asset import skill — consumes an AssetDescriptor, opens the asset file in Blender, and returns an ImportToSceneResult. Use as the receiving end of the asset import pipeline after an asset-source skill resolves the descriptor.
3d-asset-quality
Model what a 3D object is, not merely its outline, and prove quality with geometry-only close-up renders plus a manifest. Use before building, generating, importing, cleaning, reviewing, or signing off on meshes, props, buildings, terrain, environments, levels, dioramas, and set dressing in Blender, game engines, glTF…
asset-judge-loop
The build→judge→rebuild loop for MULTI-asset 3D work — whenever a scene, environment, village, level, diorama or any batch of more than 3 assets is being built (in Blender, via MCP, procedurally, or by generation), and especially when builder subagents are doing the work. The parent orchestrates; builders never…
codex-subagent
Run OpenAI Codex CLI as an external subagent from Claude Code, either once or as a parallel fanout, through hardened codex-sub and codex-fanout wrappers. Use for independent review, cross-model judging, structured second opinions, image analysis, or isolated passes over files and subsystems, especially when the user…
blender-mcp
Drive Blender via the catalog blender MCP, with bpy recipes.