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/sikadi233-hub/mc-dev/claude-mdgit clone --depth 1 https://github.com/sikadi233-hub/mc-devWrote 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/sikadi233-hub/mc-dev/claude-md)<a href="https://agentmods.dev/instructions/sikadi233-hub/mc-dev/claude-md"><img src="https://agentmods.dev/badge/instructions/sikadi233-hub/mc-dev/claude-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 | $0.02254 | $0.02254 |
| Opus 5 | $0.01127 | $0.01127 |
| Sonnet 5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
mc-dev CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Minecraft 开发知识库
本文件是 mc-dev 工具链的共享知识库，mc-expert / mc-framework / mc-content / mc-review 均依赖它的版本边界与 API 速查。 最后校验：2026-07（Maven 坐标 / API 仍会过时，生成前请 WebFetch 确认最新版本）
1. 官方文档索引
| 平台 | 官方文档 |
|---|---|
| Forge | https://docs.minecraftforge.net/en/latest/ |
| NeoForge | https://neoforged.net/ |
| Fabric | https://docs.fabricmc.net/develop/ （版本化：/1.21.4/develop/） |
| Paper | https://docs.papermc.io/ |
| Spigot | https://www.spigotmc.org/wiki/spigot/ |
| 社区 Wiki | https://moddedmc.wiki/ , https://wiki.fabricmc.net/start |
2. 关键版本边界（核心）
Minecraft 1.20.5 和 1.21.4 是两个 API 断裂点。所有代码决策都从版本分组出发：
- Group A:
<= 1.20.4- 旧 NBT - Group B:
1.20.5 - 1.21.3- Data Components，旧 custom_model_data（单个 int） - Group C:
>= 1.21.4- 新 custom_model_data（list 结构）、新 item model 系统、服务端 pick block
断裂点 1：1.20.5 - Data Components 替代 NBT
旧 API (<= 1.20.4) |
新 API (>= 1.20.5) |
|---|---|
stack.getTag() / stack.getOrCreateTag() |
stack.get(DataComponentType) / stack.set(type, value) |
stack.getTag().putInt("key", val) |
stack.set(MyMod.MY_COMPONENT.get(), val) |
| NBT 手动序列化 | DataComponentType + Codec 自动序列化 |
Item.Properties#stacksTo(n) / fireResistant() |
迁移到 Data Components（如 minecraft:max_stack_size） |
| 附魔通过 NBT List | 附魔通过 minecraft:enchantments Data Component |
| 物品伤害值 NBT | minecraft:damage Data Component |
新的注册模式 (>= 1.20.5)：
// Fabric / Vanilla
DataComponentType<Integer> MY_COMP = Registry.register(
BuiltInRegistries.DATA_COMPONENT_TYPE,
ResourceLocation.fromNamespaceAndPath("modid", "my_comp"),
DataComponentType.<Integer>builder().persistent(Codec.INT).build()
);
// Forge / NeoForge: 同样使用 vanilla 的 DataComponentType 系统
public static final DeferredRegister<DataComponentType<?>> DATA_COMPONENTS =
DeferredRegister.create(BuiltInRegistries.DATA_COMPONENT_TYPE, "modid");
断裂点 2：1.21.4 - 进一步 API 重构
| 变更项 | 说明 |
|---|---|
| custom_model_data 重构 | 从单个 int -> {strings:[], floats:[], flags:[], colors:[]} 结构 |
| Item Model Definition | 新系统替代旧 model JSON；ItemColors / tint 系统被移除 |
| Pick Block 移到服务端 | ClientPickBlockCallback -> PlayerPickItemEvents#BLOCK (Fabric) |
| BuiltinItemRenderer | 被移除（Fabric API fabric-rendering-v0 删除） |
CustomIngredient#getMatchingStacks |
返回 Stream 替代 List (Fabric) |
| DataComponentIngredient | 新类型 neoforge:ingredient_type 替代旧 "type": "neoforge:components" (NeoForge) |
| Client Data Generation | Loom 新增 configureDataGeneration { client = true } (Fabric) |
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 · 173 lines · 2,254 tokens per session scan A 59bfc59ae481
mc-dev CLAUDE.md is an instructions file published in the GitHub repository sikadi233-hub/mc-dev (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,254 tokens to every session, about $0.0113 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
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.