blender-agent-studio AGENTS.md

blender-agent-studio AGENTS.md is an instructions file for Codex, OpenCode from ifBars/blender-agent-studio. It costs 140 tokens per session, scanned A, original, MIT.

Project instructions for Blender Agent Studio, a coding-agent add-on for repeatable Blender modelling, validation, animation, tool integration, and agent benchmarking.

In plain words
What is it for?
Use them when changing the TypeScript, tool, scoring, benchmark, metadata, marketplace, or documentation parts of the project.
Why use it?
They keep project changes and tests consistent while limiting unsafe Blender execution and avoiding misleading conclusions from small benchmark runs.

Instructions file for CodexOpenCode

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 instructions/ifbars/blender-agent-studio/agents-md
Clone the repo
git clone --depth 1 https://github.com/ifBars/blender-agent-studio

Made for: Codex, OpenCode.

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-agent-studio AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ifbars/blender-agent-studio/agents-md.svg)](https://agentmods.dev/instructions/ifbars/blender-agent-studio/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ifbars/blender-agent-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/ifbars/blender-agent-studio/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 140 This file is loaded in full into every session.
When invoked 140 The same file — it is already loaded in full.
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 $0.00140 $0.00140
Opus 5 $0.00070 $0.00070
Sonnet 5 $0.00028 $0.00028
Haiku 4.5 $0.00014 $0.00014

Measured 3d ago against content hash 36af3b375d39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blender-agent-studio 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 3d 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.

AGENTS.md · 10 lines

What it actually says

Repository Instructions

  • Use Bun for package scripts and dependency management.
  • Run bun run test after changing TypeScript, MCP, scoring, or benchmark code.
  • Run bun run check after changing plugin metadata, skills, marketplace files, or documentation.
  • Keep the plugin name aligned across .agents/plugins/marketplace.json, the plugin folder, and .codex-plugin/plugin.json.
  • Do not commit generated Blender models, exports, renders, benchmark runs, agent traces, or local .tmp output.
  • Keep Blender execution bounded. Do not add a generic arbitrary-Python MCP tool.
  • Treat one benchmark generation per condition as directional evidence, not a universal capability claim.
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 · 10 lines · 140 tokens per session scan A 36af3b375d39

Subscribe to this mod's changes

blender-agent-studio AGENTS.md is an instructions file published in the GitHub repository ifBars/blender-agent-studio (6 stars, last pushed 16d ago), licensed MIT. It adds 140 tokens to every session, about $0.0007 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.

Related

Other instructions, from other repositories