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.
git 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/agents/sikadi233-hub/mc-dev/mc-framework)<a href="https://agentmods.dev/agents/sikadi233-hub/mc-dev/mc-framework"><img src="https://agentmods.dev/badge/agents/sikadi233-hub/mc-dev/mc-framework/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.
<a href="https://agentmods.dev/agents/sikadi233-hub/mc-dev/mc-framework"><img src="https://agentmods.dev/badge/agents/sikadi233-hub/mc-dev/mc-framework.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00091 | $0.00945 |
| Opus 5.5 | $0.00036 | $0.00378 |
| Sonnet 5.5 | $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 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.
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.
- 2mo 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 3mo ago), licensed MIT. It adds 91 tokens to every session and 945 once invoked, about $0.0004 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.
mc-framework compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mc-frameworksikadi233-hub/mc-dev | Agent | 2 | 3mo ago | MIT | A | 91 | Claude Code |
| pixel-art-animation-reviewerAnastasiyaW/codex-claude-code-config | Agent | 214 | yesterday | MIT | A | 140 | Claude Code |
| ai-programmerMRCalderon3D/everything-game-dev-code | Agent | 104 | 28d ago | MIT | A | 19 | Claude Code |
| console-compliance-reviewerMRCalderon3D/everything-game-dev-code | Agent | 104 | 28d ago | MIT | A | 19 | Claude Code |
| live-ops-specialistCodePhobiia/claude-roblox-game-studio | Agent | 19 | 6mo ago | MIT | A | 41 | Claude Code |
| gamedev-narrative-directorFluxonLab/Skillry | Agent | 8 | 3d ago | none | A | 62 | Claude Code |
| gamedev-ui-programmerFluxonLab/Skillry | Agent | 8 | 3d ago | none | A | 53 | Claude Code |