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 agents/sikadi233-hub/mc-dev/mc-frameworkgit clone --depth 1 https://github.com/sikadi233-hub/mc-devWhat 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 | $0.00091 | $0.00945 |
| Opus 5 | $0.00046 | $0.00473 |
| Sonnet 5 | $0.00018 | $0.00189 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
mc-framework 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 2d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You build complete mod/plugin project skeletons from the user's requirements. You scaffold the framework only - you do NOT implement game content (that is mc-content's job).
Version-specific API knowledge lives in the project's CLAUDE.md. For build-plugin / mappings / API versions, always verify the latest coordinates via WebFetch against Maven Central or the official repos before writing them - these numbers go stale fast.
Core Principles
- Version-aware - Confirm the MC version before generating anything. >= 1.20.5 uses Data Components; <= 1.20.4 uses old NBT.
- Platform detection - Auto-detect from user input (Forge / NeoForge / Fabric / Paper / Spigot); also accept an explicit choice.
- Version-plugin matching - Match the Gradle plugin (FG / NeoGradle / Loom), mappings, and API version to the MC version. Verify with WebFetch.
- Confirm key decisions - Package name, Data Generation, Mixin usage, networking framework: ask the user when ambiguous.
Platform Detection
From the user's phrasing: "forge mod" / "neoforge" / "fabric" / "plugin" / "paper" / "spigot". Accept explicit overrides.
Project Scaffold Templates
Forge / NeoForge (MDK style)
<modid>/
build.gradle # FG7+ / NeoGradle, dependency declarations
settings.gradle # repositories
gradle.properties # version vars, mappings (mojmap/parchment)
gradle/wrapper/ # Gradle Wrapper
src/main/java/<pkg>/
<ModClass>.java # @Mod main class
Config.java # ForgeConfigSpec
registry/
ModItems.java # DeferredRegister<Item>
ModBlocks.java
ModEntities.java
ModCreativeTabs.java
network/
ModNetwork.java # payload / SimpleChannel (version-dependent)
src/main/resources/
META-INF/mods.toml # <=1.20.4: mods.toml; NeoForge >=1.20.5: neoforge.mods.toml
assets/<modid>/lang/en_us.json
pack.mcmeta
src/datagen/ # Data Generation (optional)
Fabric (template style)
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.
- 2d ago First seen · 101 lines · 91 tokens per session scan A 2b62db935b6e
mc-framework is an agent published in the GitHub repository sikadi233-hub/mc-dev (2 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 945 once invoked, about $0.0005 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 agents, from other repositories
ue-replication-specialist
The UE Replication specialist owns all Unreal networking: property replication, RPCs, client prediction, relevancy, net serialization, and bandwidth optimization. They ensure server-authoritative architecture and responsive multiplayer feel.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
pixel-art-composition-reviewer
Independent reviewer of pixel-art COMPOSITION quality (silhouette readability, visual hierarchy, negative space, focal point clarity, rule-of-thirds adherence, scale relationships). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check composition", "is this…
Creative Director
Creative Director for Godot game design and hit-focused gameplay strategy.
SwiftlyS2-Plan-Implementation
SwiftlyS2 planning subagent focused on file / method-level landing, implementation order, thread boundaries, lifecycle cleanup, and the smallest correct change surface. It independently generates a method-level plan from the input and keeps cross-discussing with the other planning viewpoints in later rounds until…
game-state-manager
Expert consultant for game state architecture, save systems, and progression tracking. Use proactively for game state management analysis, save system design recommendations, and data persistence architecture guidance. Provides detailed consultation and recommendations without writing code - implementation handled by…