blender-character-workflow

blender-character-workflow is a skill for Codex from ifBars/blender-agent-studio. It costs 70 tokens per session (799 once invoked), scanned A, original, MIT.

A workflow for creating and checking Blender characters, creatures, avatars, and facial rigs. It covers meshes, skeletons, skin weights, controls, facial shapes, animation, and export when those are required.

In plain words
What is it for?
Use it to build or repair character models, armatures, IK/FK controls, skinning, facial animation, humanoid or VRM exports, and deformation tests.
Why use it?
It checks whether a character actually deforms correctly in poses and movement, rather than treating a mesh with a skeleton as finished. It also keeps naming, scale, budgets, and runtime requirements in view.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it to build or repair character models, armatures, IK/FK controls, skinning, facial animation, humanoid or VRM exports, and deformation tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ifbars/blender-agent-studio/blender-character-workflow
Install

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.

Any agent
npx skills add ifBars/blender-agent-studio --skill blender-character-workflow
Clone the repo
git clone --depth 1 https://github.com/ifBars/blender-agent-studio

Made for: Codex.

Wrote 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.

agentmods badge for blender-character-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/ifbars/blender-agent-studio/blender-character-workflow.svg)](https://agentmods.dev/skills/ifbars/blender-agent-studio/blender-character-workflow)
Your own site
<a href="https://agentmods.dev/skills/ifbars/blender-agent-studio/blender-character-workflow"><img src="https://agentmods.dev/badge/skills/ifbars/blender-agent-studio/blender-character-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.00799
Opus 5 $0.00035 $0.00400
Sonnet 5 $0.00014 $0.00160
Haiku 4.5 $0.00007 $0.00080

Measured today against content hash d373a0dc1b92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

blender-character-workflow 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fit_vrchat_hair.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/blender-agent-studio/skills/blender-character-workflow/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blender Character Workflow

Read the shared execution guidance once per task for autonomous decisions, evidence cadence, and long-task continuity.

Character completion requires deformation evidence. A mesh plus an armature is not a finished rig.

Establish the character contract

Record intended platform and export format, body/face scope, scale and axis, triangle/material/texture budgets, bone naming and hierarchy requirements, required controls, facial shape keys, poses/actions, and engine/avatar constraints. Identify the minimum acceptance poses: neutral, extreme bend for each major joint, reach, twist, locomotion/contact, and any required facial expression.

Build and rig deliberately

  1. Keep the authored mesh, armature, controls, deformation helpers, and export mesh in named collections. Apply or deliberately preserve transforms before skinning; document the choice.
  2. Create anatomically or mechanically plausible joint placement and semantic bone names. Separate deform bones from animator controls where the target benefits from it.
  3. Keep symmetry and mirror workflows explicit. Limit vertex influences and normalize weights according to the target runtime requirements.
  4. Add IK/FK, constraints, corrective shapes, or drivers only when they solve a named deformation need. Test without relying on a single flattering pose.
  5. For facial work, name shape keys semantically and test combinations that reveal volume loss, collisions, or eyelid/mouth failures.

Validate export and motion

  1. Render the neutral and every contract pose from front, profile, back, and close-up deformation views. Open the evidence.
  2. Check volume preservation, joint collapse, candy-wrapper twisting, clipping, foot/hand contact, constraint cycles, control readability, and unwanted scale/shear.
  3. Export to the requested format, fresh-import it in a clean Blender process, and compare armature hierarchy, skin weights where supported, materials, actions, frame ranges, scale, and orientation.
  4. Use $blender-agent-studio:blender-animation-workflow for action timing and $blender-agent-studio:blender-asset-validation for authored/exported geometry and hierarchy evidence.

Read the full file on GitHub · 74 lines

Files

What ships with it

3 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.

Changes

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.

  1. today Changed · +3 lines d373a0dc1b92
  2. 8d ago First seen · 71 lines · 70 tokens per session scan A 34988fff2575

Subscribe to this mod's changes

blender-character-workflow is a skill published in the GitHub repository ifBars/blender-agent-studio (14 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 799 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.