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 instructions/ra100/blender-claude-plugin/agents-mdgit clone --depth 1 https://github.com/ra100/blender-claude-pluginWrote 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/instructions/ra100/blender-claude-plugin/agents-md)<a href="https://agentmods.dev/instructions/ra100/blender-claude-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/ra100/blender-claude-plugin/agents-md.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 | $0.01060 | $0.01060 |
| Opus 5 | $0.00530 | $0.00530 |
| Sonnet 5 | $0.00212 | $0.00212 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
blender-claude-plugin AGENTS.md 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 4d 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.
AGENTS.md
This file provides guidance to AI coding agents when working with code in this repository.
What This Is
A skill plugin containing 8 expert skills for Blender 5.x Python scripting (targeting 5.0 and 5.1). This is a content-only repo — no build system, no tests, no code to run. All files are Markdown and JSON.
Architecture
This is a skill plugin. The plugin system works as follows:
.claude-plugin/plugin.json— Plugin metadata (name, description, version). This is what the host agent reads to discover the plugin..claude-plugin/marketplace.json— Marketplace listing for shared discovery.skills/<skill-name>/SKILL.md— The main skill file. Must have YAML frontmatter withnameanddescriptionfields. Thedescriptionis used to decide when to activate the skill.skills/<skill-name>/references/*.md— Supporting reference files that SKILL.md points to. These are read on-demand when the skill is active.docs/blender-mcp-setup.md— User-facing setup guide for the official Blender MCP Server. Skills link here from their MCP-First section.
Blender MCP Server (target integration)
Skills target the official Blender MCP Server by Blender Lab — https://www.blender.org/lab/mcp-server/, source https://projects.blender.org/lab/blender_mcp.
Architecture:
Claude Code ──MCP (stdio/http)──► blender-mcp ──TCP localhost:9876──► Blender Add-on (bpy)
Public tools (use these names verbatim in skill content):
- Action:
execute_blender_code - Inspection:
get_objects_summary,get_object_detail_summary,get_blendfile_summary_datablocks,get_blendfile_summary_missing_files,get_blendfile_summary_of_linked_libraries,get_blendfile_summary_path_info,get_blendfile_summary_usage_guess - Docs:
search_api_docs,get_python_api_docs,search_manual_docs - UI:
get_screenshot_of_window_as_image,get_screenshot_of_window_as_json,get_screenshot_of_area_as_image,jump_to_tab_by_name,jump_to_tab_by_space_type,jump_to_view3d_object_by_name,jump_to_view3d_object_data_by_name - Render:
render_thumbnail_to_path,render_viewport_to_path
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.
- 4d ago First seen · 84 lines · 1,060 tokens per session scan A a172a0a04dff
blender-claude-plugin AGENTS.md is an instructions file published in the GitHub repository ra100/blender-claude-plugin (11 stars, last pushed 4mo ago), licensed MIT. It adds 1,060 tokens to every session, about $0.0053 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 instructions, from other repositories
linkedin-content-engine CLAUDE.md
Claude Code instructions for mdbailin/linkedin-content-engine, covering claude implementation brief, goal, architecture constraints, required mcp tools and readbrandprofile.
docvideoer CLAUDE.md
Instructions for coding-ax/docvideoer, covering claude.md — docvideoer, 触发方式, 外部 skill 依赖, 工作目录 and 核心流水线（6 步）.
ai-workflow-kit CLAUDE.md
Claude Code instructions for bezael/ai-workflow-kit, covering claude.md — ai workflow kit, what this repo is, where each tool reads skills from, available skills and specialized agents.
video-mcp CLAUDE.md
Claude Code instructions for Zoean-z/video-mcp, a project described as: 让agent学会理解视频，无需复杂依赖和额外花费.
glm-image-mcp-server CLAUDE.md
Claude Code instructions for ex-takashima/glm-image-mcp-server, covering claude.md - development guide, project overview, build & run commands, install dependencies and build typescript.
ukulele-companion CLAUDE.md
Claude Code instructions for baijum/ukulele-companion, a project described as: An offline app for learning ukulele — on Android and iOS. Chords, scales, music theory, composition tools, and more.