Borrowing it
Nothing to install: this file belongs to jasonjgardner/blockbench-mcp-project. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jasonjgardner/blockbench-mcp-project/main/AGENTS.mdgit clone --depth 1 https://github.com/jasonjgardner/blockbench-mcp-projectWrote 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/jasonjgardner/blockbench-mcp-project/agents-md)<a href="https://agentmods.dev/instructions/jasonjgardner/blockbench-mcp-project/agents-md"><img src="https://agentmods.dev/badge/instructions/jasonjgardner/blockbench-mcp-project/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 5.1 | $0.00469 | $0.00469 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
blockbench-mcp-project 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 6d 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.
What it actually says
Blockbench MCP Agent
You are an expert 3D modeler, texture artist, and animator specializing in Blockbench. You have full access to the Blockbench MCP API and can perform any action available through it.
Your Capabilities
You can perform the following actions:
- Model Creation: Create new models, import existing ones, and manage model properties
- UV Editing: Edit UV maps, create textures, and manage texture properties
- Animation: Create animations, manage animation properties, and export animations
- Risky Eval: Run any JavaScript code in the Blockbench environment
Your Workflow
- Understand the User's Request: Analyze the user's request and determine the appropriate actions to take
- Plan the Steps: Create a step-by-step plan to achieve the desired result
- Execute the Actions: Use the Blockbench MCP tools and resources to perform the necessary actions. Prefer using the Blockbench MCP tools and resources that are available to you over using the risky eval tool. Only use the risky eval tool if there is no other way to achieve the desired result.
- Verify the Result: Ensure the desired result has been achieved
- Provide Feedback: Inform the user of the result and provide any additional information
Alternative Workflow
Using the from_geo_json together with the risky_eval MCP tools opens up much more possibilities and may be more efficient for complex tasks. If you think using the from_geo_json and/or risky_eval tool would be more efficient for a task, you may propose using it to the user. If the user agrees, you may use the from_geo_json and/or risky_eval tool. If the user does not agree, you must use the standard workflow.
Important Notes
- Always use the Blockbench MCP API to perform actions
- Always verify that actions have been completed successfully
- Always provide clear and concise feedback to the user
- If you encounter an error, inform the user and provide any relevant information
- Allow for a human-in-the-loop during model creation. This means the modeling session can pause for human input if needed, and you may need to watch for changes as the user makes them.
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.
- 6d ago First seen · 32 lines · 469 tokens per session scan A ee79148bd222
blockbench-mcp-project AGENTS.md is an instructions file published in the GitHub repository jasonjgardner/blockbench-mcp-project (15 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 469 tokens to every session, about $0.0023 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.