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 code-onigiri/mc-modding-skill --skill 1211-neoforge-moddinggit clone --depth 1 https://github.com/code-onigiri/mc-modding-skillWrote 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/code-onigiri/mc-modding-skill/1211-neoforge-modding)<a href="https://agentmods.dev/skills/code-onigiri/mc-modding-skill/1211-neoforge-modding"><img src="https://agentmods.dev/badge/skills/code-onigiri/mc-modding-skill/1211-neoforge-modding.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 | $0.00127 | $0.02515 |
| Opus 5 | $0.00063 | $0.01257 |
| Sonnet 5 | $0.00025 | $0.00503 |
| Haiku 4.5 | $0.00013 | $0.00251 |
Grade A, and why
1211-neoforge-modding 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
概要
このSkillは Minecraft 1.21.1 NeoForge 向けMod開発の標準パターンと落とし穴をまとめたものです。
✅ やるべきこと
- DeferredRegister + DeferredHolder(または型付きAPI)を使う —
DeferredRegister.createBlocks(MODID),DeferredRegister.createItems(MODID)などの型付きAPIが利用可能。 - DataGen を使う — 手書きJSONはミスとメンテナンスコストが爆発する。
- Parchmentでパラメータ名を補完 —
neoForge { parchment { ... } }で設定。無効でも動作するが可読性が下がる。 - すべてのDeferredRegisterをメインModクラスのコンストラクタで
modBusにregisterする — コンストラクタ引数IEventBus modEventBusを使う。 - Block登録時はBlockItemも登録する —
DeferredRegister.Items.registerSimpleBlockItem("name", BLOCK)で簡易化可能。 ResourceLocation.fromNamespaceAndPath(MODID, "path")を使う —new ResourceLocation(...)は非推奨。level.isClientSide()で論理サイド判定 — メソッド呼び出し形式(1.21.1以降)。- Networkingのハンドラでは
context.enqueueWork()でメインスレッドに戻す — ネットワークスレッドでワールド変更を行うとクラッシュ。 - Capability取得は直接メソッド呼び出し —
LazyOptionalは廃止。level.getCapability(...)/entity.getCapability(...)で直接取得。 - BlockEntityのデータ変更時は
setChanged()+level.sendBlockUpdated()を呼ぶ — どちらか欠けると保存/同期されない。 - Data ComponentsをItemStackのデータに使う —
persistent(Codec)+networkSynchronized(StreamCodec)の両方を提供する。 - Data AttachmentはBlockEntity/Entity/Chunk用 — ItemStackには使えない。ItemStackにはData Componentを使う。
sourceSets.main.resources { srcDir 'src/generated/resources' }を忘れない — DataGenの出力が読み込まれなくなる。@EventBusSubscriberでbus自動検出 —busの明示が不要になったが、特定バスに限定したい場合bus = Bus.MODまたはBus.GAMEを指定。
❌ やってはいけないこと
@OnlyInをModコードで使わない — NeoForge内部専用。クライアント限定は@Mod(value = MODID, dist = Dist.CLIENT)またはFMLClientSetupEventで分離。new ResourceLocation(...)を使わない —ResourceLocation.fromNamespaceAndPath()を使うこと。- CapabilityにLazyOptionalを使わない — 1.21.1では廃止。
getCapability()は直接呼び出し。 - Data AttachmentをItemStackに使わない — ItemStackにはData Componentを使う。
mods.tomlではなくneoforge.mods.toml— ファイル名を間違えるとModが認識されない。- ModDevGradleの
dependencies {}にminecraftやneoforgeを書かない —neoForge { version = ... }ブロックで解決される。 - runClientクラッシュ後は
./gradlew --stop— Daemonがポートを占有していることがある。 - Data Componentの
Codec/StreamCodecを忘れない — ないとコンパイルエラーまたは実行時エラーになる。
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ADVANCED.md 4.9 KB
- references/BLOCKS_AND_ITEMS.md 9.9 KB
- references/CI_RELEASE.md 3.2 KB
- references/COMMANDS.md 2.4 KB
- references/CORE_CONCEPTS.md 5.7 KB
- references/DATA.md 7.3 KB
- references/DATAPACK.md 10 KB
- references/GAMETEST.md 2.5 KB
- references/IMAGEGEN.md 3.7 KB
- references/NETWORKING.md 3.3 KB
- references/QUICK_REFERENCE.md 4.7 KB
- references/RESOURCE_PACK.md 7.6 KB
- references/SETUP.md 7.2 KB
- references/TROUBLESHOOTING.md 5.8 KB
- references/WORLDGEN.md 1.8 KB
- scripts/check-build.sh 4.5 KB runs code
- scripts/scaffold-asset-brief.sh 5.2 KB runs code
- scripts/validate-datapack.sh 4.1 KB runs code
- scripts/validate-resource-pack.sh 7.3 KB runs code
- scripts/validate-test-layout.sh 3.6 KB runs code
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 · 125 lines · 127 tokens per session scan A f270fd1c58dd
1211-neoforge-modding is a skill published in the GitHub repository code-onigiri/mc-modding-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 2,515 once invoked, about $0.0006 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 skills, from other repositories
setup-fabric
Step 1 of 4 of the Minecraft Java MCP setup. Install Minecraft Java Edition with the Fabric loader — either a single-player client or a headless dedicated server — as the foundation the MCP mod runs inside. Use when the user wants to set up Minecraft Java for AI/MCP control from scratch, or asks how to get Fabric…
setup-mod
Step 2 of 4 of the Minecraft Java MCP setup. Download the minecraft-java MCP mod jar and its matching Fabric API jar and install both into the Minecraft mods folder. Use when the user has Minecraft Java with the Fabric loader ready and needs the MCP mod and Fabric API installed.
survey-research
Researches real-world buildings, cities, landmarks, vehicles, and mechanisms so they can be represented faithfully as Minecraft structures. Use when a build request references a real or historical thing and the exec-plan or exec-blueprint skill needs accurate proportions, layouts, materials, or details. Part of the…
setup-connect
Step 4 of 4 of the Minecraft Java MCP setup. Register the running minecraft-java MCP server (the Fabric mod) with Claude (Claude Code or Claude Desktop) so the Java world tools become available, then verify the connection with a live test call. Use when the user has the MCP server running and needs to connect Claude…
setup-server
Step 3 of 4 of the Minecraft Java MCP setup. Configure the MCP mod's config.json (host, port, auth, tool categories), launch Minecraft or the dedicated server, verify the embedded MCP server is listening on /healthz, and capture the bearer token for remote setups. Use when the user has the MCP mod and Fabric API…
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).