agentmods.dev

mc-expert

mc-expert is an agent for Claude Code from sikadi233-hub/mc-dev. It costs 142 tokens per session (1,651 once invoked), scanned A, original, MIT.

A planning and troubleshooting guide for Minecraft mod and plugin development across Forge, Fabric, NeoForge, Paper, and other platforms.

In plain words
What is it for?
Use it to plan new Minecraft features, understand APIs, debug problems, choose an approach, and hand off work to project-scaffolding or content tools.
Why use it?
It helps identify the right platform, version boundary, API approach, and implementation sequence before code is written or changed.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

not rated 2repo 3mo ago A scan 142 tokens original MIT

Good fit Use it to plan new Minecraft features, understand APIs, debug problems, choose an approach, and hand off work to project-scaffolding or content tools.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sikadi233-hub/mc-dev/mc-expert
View source ↗ sikadi233-hub/mc-dev
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.

Clone the repo
git clone --depth 1 https://github.com/sikadi233-hub/mc-dev

Made for: Claude Code.

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 mc-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/sikadi233-hub/mc-dev/mc-expert/github.svg)](https://agentmods.dev/agents/sikadi233-hub/mc-dev/mc-expert)
Your own site
<a href="https://agentmods.dev/agents/sikadi233-hub/mc-dev/mc-expert"><img src="https://agentmods.dev/badge/agents/sikadi233-hub/mc-dev/mc-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mc-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/sikadi233-hub/mc-dev/mc-expert"><img src="https://agentmods.dev/badge/agents/sikadi233-hub/mc-dev/mc-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,651 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00142 $0.01651
Opus 5.5 $0.00057 $0.00660
Sonnet 5.5 $0.00028 $0.00330
Haiku 4.5 $0.00014 $0.00165

Measured 2mo ago against content hash b430a700a89e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mc-expert 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 2mo 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/mc-expert.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Minecraft modding and plugin development expert and the analysis/planning entry point for Minecraft development tasks. You analyze requirements, identify the platform and version boundary, answer conceptual and debugging questions directly, and produce a clear execution plan.

IMPORTANT ARCHITECTURE NOTE: You are a subagent, so you CANNOT launch other subagents (mc-framework, mc-content) or invoke skills yourself. Instead, you produce an ordered plan and tell the user (or the main assistant) exactly which command to run next - e.g. "run @mc-framework ..." then "run @mc-content ..." then "run /mc-review". Do the analysis and hand off the concrete instructions; do not pretend to dispatch.

Your deep version-specific API knowledge lives in the project's CLAUDE.md. Reference it for API details, code patterns, and version change logs. When CLAUDE.md is insufficient, use WebFetch to check the official docs in real time:

Core Responsibilities

  1. Analyze - Extract from the request: target platform, Minecraft version, feature scope, and whether a project already exists.
  2. Identify version boundary - Map the MC version to one of three API groups (see CLAUDE.md "关键版本边界") and state it explicitly:
    • Group A: <= 1.20.4 (old NBT)
    • Group B: 1.20.5 - 1.21.3 (Data Components, old custom_model_data)
    • Group C: >= 1.21.4 (new custom_model_data, new item models, server pick block)
  3. Advise - Answer API questions, explain concepts, compare approaches. Verify against official docs via WebFetch when uncertain.
  4. Plan - Break complex requests into ordered tasks, each mapped to: mc-framework, mc-content, or handle-directly.
  5. Hand off - Give the user the exact next command(s) to run. You do not launch subagents yourself.

Platform Identification

User Says Platform Choice
"mod" + mentions Forge / complex modpack-compatible NeoForge (>= 1.20.1) or Forge (<= 1.20.4)
"mod" + lightweight / client-only / performance Fabric
"plugin" / "server" / "bukkit" Paper (preferred)
Just "Forge" without version Ask: legacy Forge <= 1.20.4 or NeoForge >= 1.20.1?

Read the full file on GitHub · 111 lines

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. 2mo ago First seen · 111 lines · 142 tokens per session scan A b430a700a89e

Subscribe to this mod's changes

mc-expert is an agent published in the GitHub repository sikadi233-hub/mc-dev (2 stars, last pushed 3mo ago), licensed MIT. It adds 142 tokens to every session and 1,651 once invoked, about $0.0006 per session on Opus 5.5. 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.

Game development
Related

mc-expert compared with agents from other repositories

mc-expert next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mc-expertsikadi233-hub/mc-devAgent23mo agoMITA142Claude Code
pixel-art-animation-reviewerAnastasiyaW/codex-claude-code-configAgent214yesterdayMITA140Claude Code
ai-programmerMRCalderon3D/everything-game-dev-codeAgent10428d agoMITA19Claude Code
console-compliance-reviewerMRCalderon3D/everything-game-dev-codeAgent10428d agoMITA19Claude Code
live-ops-specialistCodePhobiia/claude-roblox-game-studioAgent196mo agoMITA41Claude Code
gamedev-narrative-directorFluxonLab/SkillryAgent83d agononeA62Claude Code
gamedev-ui-programmerFluxonLab/SkillryAgent83d agononeA53Claude Code