reference-analysis-validator

A checking workflow for comparing reconstructed 3D assets with supplied images, wireframes, texture layouts, or renders. It turns visual similarity into measured checks before export.

In plain words
What is it for?
Use it to analyze reference files, count expected components, compare a Blender render with a reference, and produce overlay and mask-validation reports.
Why use it?
It helps catch missing parts, incorrect shapes, and mismatched views that might otherwise be accepted because they merely look close.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/roble3/cc-blender-skill/reference-analysis-validator
Any agent
npx skills add RobLe3/cc-blender-skill --skill reference-analysis-validator
Clone the repo
git clone --depth 1 https://github.com/RobLe3/cc-blender-skill

Made for: Claude Code, Codex.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 725 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00091 $0.00725
Opus 5 $0.00046 $0.00362
Sonnet 5 $0.00018 $0.00145
Haiku 4.5 $0.00009 $0.00072

Measured 3d ago against content hash 53850bf7af94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reference-analysis-validator 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/reference_manifest_compiler.py, scripts/render_overlay_validator.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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugin/skills/reference-analysis-validator/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reference Analysis Validator

This skill converts “looks close” into measurable gates. For brand/logo/mascot work, do not model or export until a source manifest and validation thresholds exist.

Required outputs

Create these in the asset output folder:

  • reference_manifest.json — classified source files, expected parts, thresholds.
  • source_analysis/*.json — image metadata, masks/components/landmarks.
  • validation/front_overlay_reference.png — reference and render overlay.
  • validation/front_mask_validation.json — IoU/SSIM/bbox/centroid report.

Workflow

  1. Classify sources: front, side, back, top, texture atlas, decals, maps, lightmap, aura/context.
  2. Build/refresh reference_manifest.json with hard expected counts and view roles.
  3. Extract masks/components from each source using scripts/reference_manifest_compiler.py or existing analyzers.
  4. Render model from matching orthographic camera with reference planes hidden.
  5. Compare reference mask vs render mask using scripts/render_overlay_validator.py.
  6. Refuse final export if hard gates fail.

Modality rule

Compare like with like. A wireframe edge mask compared against a shaded beauty render gives misleadingly low IoU. For hard gates, render a flat silhouette/matte pass from Blender or compare reference edges to render edges. Use render_overlay_validator.py --reference-mode ... --render-mode ... when the source and render need different mask extraction modes.

Default validation gates

  • primary structural part count: exact.
  • front silhouette IoU: target >= 0.90 for rigid/logotype shapes; >= 0.82 acceptable for first mascot reconstruction pass.
  • bbox center drift: <= 12 px at 1024 px validation size.
  • bbox size drift: <= 3% of image dimension.
  • face/eye/smile landmark drift: <= 2% of image dimension when landmarks are defined.

Failure policy

If a repeated mismatch occurs, record the measured failure, then route to the missing specialty skill:

  • wrong silhouette → contour-to-mesh
  • wrong depth/side/back → orthographic-registration
  • wrong textures → atlas-uv-fitting
  • wrong whole workflow → mascot-logo-reconstruction

Read the full file on GitHub · 63 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. 3d ago First seen · 63 lines · 91 tokens per session scan A 53850bf7af94

Subscribe to this mod's changes

reference-analysis-validator is a skill published in the GitHub repository RobLe3/cc-blender-skill (48 stars, last pushed 4mo ago), licensed MIT. It adds 91 tokens to every session and 725 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

blender-director

Use when starting any Blender asset task, planning a production pipeline, coordinating multiple disciplines, or matching a reference photo/concept art. Invoke for game-ready assets, hard surface, environment, character, creature, export, or any multi-skill Blender workflow.

arjun988/blender-skills · 56 tokens

hard-surface

AAA hard surface modeling for sci-fi, industrial, military, vehicles, weapons, robotics, and mechanical props. Use for boolean/bevel workflows, panel lines, greebles, chamfers, and manufacturing-accurate surfaces in Blender via MCP.

arjun988/blender-skills · 54 tokens

environment-artist

AAA environment art for modular kits, buildings, terrain, vegetation, architecture, and scene composition. Use for game-optimized environments, storytelling through space, and modular asset pipelines in Blender via MCP.

arjun988/blender-skills · 43 tokens

horror-style

Psychological horror art direction for Blender assets inspired by Silent Hill, Resident Evil, Chilla's Art, Fear to Fathom, and Iron Lung. Use for sparse industrial environments, analog aesthetics, and tension-driven lighting.

arjun988/blender-skills · 49 tokens

animation

Game-ready animation in Blender including walk/run/idle cycles, combat, mechanical animation, camera animation, constraints, Graph Editor, and NLA workflows via MCP.

arjun988/blender-skills · 34 tokens

asset-optimization

Validates and optimizes Blender assets for polycount, topology, UV efficiency, material count, naming, collections, and game-ready performance. Use before export on all production assets via MCP.

arjun988/blender-skills · 42 tokens