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 CheshireJCat/blender --skill blender-skill-harmonizergit clone --depth 1 https://github.com/CheshireJCat/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/cheshirejcat/blender/blender-skill-harmonizer)<a href="https://agentmods.dev/skills/cheshirejcat/blender/blender-skill-harmonizer"><img src="https://agentmods.dev/badge/skills/cheshirejcat/blender/blender-skill-harmonizer/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/cheshirejcat/blender/blender-skill-harmonizer"><img src="https://agentmods.dev/badge/skills/cheshirejcat/blender/blender-skill-harmonizer.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 | $0.00075 | $0.01582 |
| Opus 5 | $0.00037 | $0.00791 |
| Sonnet 5 | $0.00015 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
blender-skill-harmonizer 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.
This is a copy
92% identical to blender-skill-harmonizer — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Skill Harmonizer
This is the meta-layer for the Blender skill stack. It prevents independently useful skills from producing incoherent work when combined.
Use a Merge → Consistency → Optimize → Store cycle:
- Merge: list all triggered skills and their intended outputs.
- Consistency: detect conflicts in assumptions, coordinate systems, source hierarchy, object naming, or validation gates.
- Optimize: choose one orchestrator, one source-of-truth policy, and a staged/parallel execution plan.
- Store: write the chosen plan and durable lessons into project docs/memory.
Skill category map
- Top-level orchestrators:
create-3d-model,quality-refinement-autoloop,mascot-logo-reconstruction. - General production:
blender-pro-workflow,blender-modeling,blender-materials,blender-lighting,blender-cameras,blender-rendering,blender-animation,blender-export. - Reference reconstruction:
reference-to-3d,wireframe-to-3d,reference-analysis-validator,source-part-segmentation,orthographic-registration,multiview-constraint-solver,contour-to-mesh,texture-driven-mesh-fitting,landmark-fit-repair,multiview-fit-loop,fit-repair-optimizer. - Texture/UV:
blender-uv-texturing,atlas-uv-fitting,closed-surface-uv-coverage. - Look calibration:
reference-look-calibration. - Animation/motion design:
texture-state-animation,orbital-hud-motion,animation-quality-gate, coordinated byblender-animation. - Task-specific/full workflow:
mascot-logo-reconstruction.
Activation precedence
For a task involving references/templates/textures:
blender-skill-harmonizer— choose the pipeline and conflict policy. 1a.quality-refinement-autoloop— if output is rejected/subpar, freeze product work, diagnose, sanitize/patch generic skill knowledge, validate, then retry.reference-analysis-validator— source manifest and source-of-truth classification.orthographic-registration— view consistency and coordinate contract.multiview-constraint-solver— rigid feasibility and canonical view policy.fit-repair-optimizer— dependency repair queue if validation fails.source-part-segmentation— split overlapping structural/decorative masks.contour-to-mesh/wireframe-to-3d/blender-modeling— geometry, selected by source type.texture-driven-mesh-fitting+landmark-fit-repair— fit mesh boundaries and named landmarks to source/texture.atlas-uv-fitting/blender-uv-texturing/closed-surface-uv-coverage— UV, texture fit, and full front/back/side surface coverage.multiview-fit-loop— render/compare/adjust loop.reference-look-calibration+blender-materials/blender-lighting/blender-rendering— look only after geometry/UV gates.blender-export— only after validation gates.blender-animation— only after static fit acceptance.texture-state-animation/orbital-hud-motion— design texture/HUD motion as layered, source-derived animation.animation-quality-gate— render contact sheet and reject bad motion before final export.
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.
- 11d ago First seen · 112 lines · 75 tokens per session scan A c6304683de99
blender-skill-harmonizer is a skill published in the GitHub repository CheshireJCat/blender (26 stars, last pushed 21d ago), licensed MIT. It adds 75 tokens to every session and 1,582 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to blender-skill-harmonizer, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
yao-image
Image expert. ALWAYS invoke this skill when you need to read, analyze, describe, or generate images. Use for screenshots, photos, charts, diagrams, AI-generated images, or any visual content.
yao-audio
Audio expert. ALWAYS invoke this skill when the user asks to transcribe, recognize, or convert speech/audio to text.
agent-first-screenshots
Agent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screenshots (newsletters, landing pages, social, decks, PR). Dual-channel verification (DOM + pixels + vision) in a capture loop. Use for any "take/redo screenshots of the app" task.
ipollowork-template-generation
Create or update reusable iPolloWork templates through conversation for Design, Slides/native editable PPT, and HyperFrames Video. Use when planning, generating, repairing, validating, or saving a template package, manifest, reusable variables, cover, slide/PPT markers, video composition, or design-system token…
voiceover
write the voice-over, demo script first, voiceover instead of PRD, voiceover-first development, align on the demo, script the demo, ship a feature demo-first. The whole demo-driven journey — approve the narration BEFORE any code, then build on a fresh worktree until the demo holds and open the PR with the proof on it.…