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/ronaldbunk/minestom-mcp/agents-mdgit clone --depth 1 https://github.com/RonaldBunk/minestom-mcpWrote 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/ronaldbunk/minestom-mcp/agents-md)<a href="https://agentmods.dev/instructions/ronaldbunk/minestom-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ronaldbunk/minestom-mcp/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 | $0.00369 | $0.00369 |
| Opus 5 | $0.00185 | $0.00185 |
| Sonnet 5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
minestom-mcp 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 5d 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
Agent Guide
- Start with
README.md,CHANGELOG.md,docs/tools.md, andMEMORY.md. - Fetch first and keep local
mainanddevelopaligned withoriginbefore starting new work when it is safe to do so. - Use a dedicated branch or worktree per session. Do not reuse a dirty checkout.
- Keep changes small and preserve the current structure:
src/server.tswires the MCP serversrc/tools.tsis the public tool registrysrc/minestom/*.tsholds the tool logicdocs/tools.mdis the primary tool reference
- Prefer local docs and code, then Minestom docs and javadocs, then web search. Do not guess Minestom APIs or JVM build behavior.
- Preserve the current public contract unless the task explicitly changes it:
- npm package and primary invocation:
minestom-mcp - supported Node.js baseline:
>=22 - public tools must stay documented in
docs/tools.md
- npm package and primary invocation:
- If you change a tool name, schema, or behavior, update the implementation,
src/tools.ts, and the related docs in the same pass. - Keep
README.mdconcise and put detailed tool behavior indocs/tools.md. - Use
MEMORY.mdfor AI-facing knowledge and notes: progress, decisions, blockers, ownership, pending work, and other context worth reusing later. - Run
pnpm checkfor normal verification. There is nopnpm testscript right now, so note that instead of inventing one. - Use
CHANGELOG.mdonly for concrete project changes after checks pass. Keep it brief and user-facing, and do not put memory-style notes there.
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.
- 5d ago First seen · 21 lines · 369 tokens per session scan A 33dcec20e507
minestom-mcp AGENTS.md is an instructions file published in the GitHub repository RonaldBunk/minestom-mcp (6 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 369 tokens to every session, about $0.0018 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.
Other instructions, from other repositories
ashfox AGENTS.md
AGENTS.md instructions for sigee-min/ashfox, a project described as: Powerful Blockbench MCP server and AI-native low-poly workbench for modeling, pixel texturing, rigging, animation, and game-ready exports from a prompt.
minecraft-java-fabric-claude-plugin CLAUDE.md
Instructions for chapmanjw/minecraft-java-fabric-claude-plugin, covering claude.md, commands, architecture, the three-tier, no-trivial model (0.9.0) and terrain core (tools/terrain/).
minecraft-modding-mcp AGENTS.md
AGENTS.md instructions for adhi-jp/minecraft-modding-mcp, covering agents.md, purpose and scope, core release policy, public mcp contract (must) and change coupling rules (must).
minecraft-document-mcp CLAUDE.md
Claude Code instructions for PYmili/minecraft-document-mcp, covering claude.md, 项目概述, 常用命令, 启动 mcp 服务器 and 开发模式（支持热重载）.
Unity-MCP copilot-instructions.md
Copilot instructions for IvanMurzak/Unity-MCP, covering project guidelines, critical rules, no c# reflection for private access, code review and code style.
Unity-MCP CLAUDE.md
Claude Code instructions for IvanMurzak/Unity-MCP, covering claude.md, what this is, build / run, project constitution and find detail in.