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/ra100/blender-claude-plugin/blender-python-scriptingnpx skills add ra100/blender-claude-plugin --skill blender-python-scriptinggit clone --depth 1 https://github.com/ra100/blender-claude-pluginWhat 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 | $0.00061 | $0.02652 |
| Opus 5 | $0.00030 | $0.01326 |
| Sonnet 5 | $0.00012 | $0.00530 |
| Haiku 4.5 | $0.00006 | $0.00265 |
Grade A, and why
blender-python-scripting 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 2d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Python Scripting Expert
Overview
This skill provides expert guidance for Blender 5.x Python scripting: writing custom operators, building UI panels, developing add-ons, managing context, using handlers and timers, working with the property system, batch processing, and accessing Blender's data model. The reference files contain complete templates and the data model hierarchy.
MCP-First Approach
Prefer the official Blender MCP Server (Blender Lab, Blender 5.1+) for executing scripts, inspecting datablocks, mutating scene state directly in a running Blender session. Fall back to emitting Python scripts only when the MCP server is not connected.
Detection: at session start, look for tools whose names match execute_blender_code, get_objects_summary, or search_api_docs — these belong to the official blender-mcp server. If any are present, MCP is available.
Tools used by this skill:
execute_blender_code— runbpyPython in the live session (primary action)get_objects_summary,get_object_detail_summary— inspect scene state before mutatingget_blendfile_summary_datablocks/_missing_files/_of_linked_libraries/_path_info/_usage_guess— inventory the filesearch_api_docs,get_python_api_docs,search_manual_docs— confirm correct API/operator names before calling themget_screenshot_of_window_as_image/_as_json,get_screenshot_of_area_as_image— verify visual resultsjump_to_tab_by_name,jump_to_tab_by_space_type,jump_to_view3d_object_by_name,jump_to_view3d_object_data_by_name— drive the UI to make changes visiblerender_thumbnail_to_path,render_viewport_to_path— capture quick visual feedback
Workflow: inspect with a get_* / search_* tool → mutate via execute_blender_code → verify with a screenshot or summary tool. Keep code blocks small and idempotent so failures are easy to localize.
Setup: see docs/blender-mcp-setup.md.
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.
- 2d ago First seen · 262 lines · 61 tokens per session scan A a76bfac8451d
blender-python-scripting is a skill published in the GitHub repository ra100/blender-claude-plugin (12 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 2,652 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…