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 skills add dcd887/mc-modpack-mcp --skill mc-modpack-helpergit clone --depth 1 https://github.com/dcd887/mc-modpack-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/skills/dcd887/mc-modpack-mcp/mc-modpack-helper)<a href="https://agentmods.dev/skills/dcd887/mc-modpack-mcp/mc-modpack-helper"><img src="https://agentmods.dev/badge/skills/dcd887/mc-modpack-mcp/mc-modpack-helper.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 | $0.00075 | $0.03486 |
| Opus 5 | $0.00037 | $0.01743 |
| Sonnet 5 | $0.00015 | $0.00697 |
| Haiku 4.5 | $0.00007 | $0.00349 |
Grade A, and why
mc-modpack-helper scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. 生成下载命令（PowerShell / curl） How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MC Modpack Helper
自动化诊断 Minecraft Fabric/Forge 整合包和模组开发问题，覆盖从配置检查到崩溃分析的全流程。
When To Use
在以下情况时主动执行本 skill：
- 用户发送"有报错"、"查看日志"、"崩溃了"、"exit code 1"等
- 用户发送崩溃报告 zip 文件或
latest.log/ PCL 启动器日志 - 用户说"帮我检查这个整合包"、"看看有什么冲突"
- 用户添加或更新模组后需要验证兼容性
- 用户在制作整合包时询问最佳实践
Inputs
| 输入 | 说明 | 来源 |
|---|---|---|
mc_dir |
.minecraft 根目录 | 自动探测或用户指定 |
version_name |
实例名称（如 rpg） |
自动探测或用户指定 |
launcher |
Launcher 类型 | 自动探测：PCL / Prism / HMCL |
| 崩溃报告 | crash report 文件内容 | 用户粘贴或文件路径 |
| 日志片段 | latest.log 相关内容 | 用户粘贴 |
Workflow
Phase 1 — 信息收集
- 探测
.minecraft目录（通过 MCP 工具get_version_info自动查找，或由用户提供） - 读取版本 JSON（
versions/<name>/<name>.json），提取：javaVersion.component+majorVersionarguments.game（命令行参数）arguments.jvm（JVM 参数）id（MC 版本号）
- 列出
versions/<name>/mods/下的所有文件 - 读取
versions/<name>/logs/latest.log（如存在） - 读取
versions/<name>/logs/server.log（如存在） - 探测 Launcher 配置：
- PCL：
AppData\Roaming\PCL\config.json - Prism：
AppData\Roaming\PrismLauncher\instances\<name>\prism.ini
- PCL：
- 扫描崩溃报告：
versions/<name>/crash-reports/最新文件
Phase 2 — Java 版本检查（最高优先级）
关键判断逻辑：
- 从版本 JSON 提取
javaVersion.majorVersion - 从系统探测已安装 Java 路径（按 PCL/Prism 配置顺序）
- 确认 Launcher 实际使用的 Java 版本
- 对比推荐版本表：
| MC 版本 | Loader | 必须 Java | 常见错误 |
|---|---|---|---|
| 1.20.1 | Fabric 0.15+ | 17 | Java 21 → exit code 1 |
| 1.20.1 | Forge 47+ | 17 | — |
| 1.20.4 | Fabric | 17 | — |
| 1.20.6 | Fabric | 21 | — |
| 1.21+ | Fabric/Forge | 21 | — |
| 1.19.4 | Fabric | 17 | — |
| 1.18.2 | Fabric/Forge | 17 | — |
| 1.16.5 | Forge | 8 | — |
修复动作（仅当用户确认）：
- 调整 Launcher 配置中 Java 列表顺序
- PCL：将正确版本移到
JavaList第一位 - 同时更新版本 JSON 的
javaVersion字段
Phase 3 — 模组冲突检测
扫描 mods/ 目录，检测以下已知冲突组：
| 冲突模式 | 检测方法 | 建议 |
|---|---|---|
sodium-* + embeddium-* |
文件名匹配 | 保留 Embeddium，移除 Sodium |
graves-* + gravestones-* |
文件名匹配 | 保留其中一个 |
player-corpse-* + 其他尸体 |
文件名匹配 | 保留其中一个 |
| 多个 UI Lib 变体 | 文件名包含 ui.lib 或 uilib |
只保留一个 |
| 多个 JEI 变体 | 文件名包含 jei |
只保留一个 |
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.
- 7d ago First seen · 295 lines · 75 tokens per session scan A 92a75ed0e017
mc-modpack-helper is a skill published in the GitHub repository dcd887/mc-modpack-mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 75 tokens to every session and 3,486 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
graphics-api-hooking
Guide for graphics API interception, overlay rendering, and render-pipeline analysis across DirectX, OpenGL, and Vulkan. Use this skill when working with Present or SwapBuffers hooks, DXGI swap chains, shader or draw-call interception, screenshot-sensitive overlays, or graphics debugging in game security research.
console-get-logs
Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.
editor-application-get-state
Return the current state of UnityEditor.EditorApplication — playmode, paused state, compilation state, and related flags.
console-clear-logs
Clear the MCP log cache (used by 'console-get-logs') and the Unity Editor Console window. Useful for isolating logs to a specific action by clearing the slate first.
profiler-start
Enable Unity's runtime profiler and open the Profiler window. Idempotent: calling when already enabled returns the current enabled state without error.