minecraft-agent-skills: Skill for Claude Code

.agents/skills/minecraft-datapack/SKILL.md

minecraft-datapack is a skill for Claude Code, Codex from Jahrome907/minecraft-agent-skills. It costs 60 tokens per session (2,901 once invoked), scanned A, original, MIT.

A guide for creating and debugging vanilla Minecraft 26.x and 1.21.x datapacks, which are file-based additions that use Minecraft's built-in systems. It covers the datapack files and JSON or command-based content without Java or loader APIs.

In plain words
What is it for?
Use it to create or edit functions, advancements, recipes, loot tables, predicates, tags, and pack metadata. It is intended for datapack file trees rather than standalone command snippets or loader-based mods.
Why use it?
It helps keep datapack work compatible with the target Minecraft version and separates it from tasks that require Java mods. It also provides the relevant metadata format for different releases.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is Jahrome907/minecraft-agent-skills's own configuration. It tells Claude Code and Codex how to work on minecraft-agent-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything minecraft-agent-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Jahrome907/minecraft-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Jahrome907/minecraft-agent-skills/main/.agents/skills/minecraft-datapack/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Jahrome907/minecraft-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for minecraft-datapack

README.md
[![agentmods](https://agentmods.dev/badge/skills/jahrome907/minecraft-agent-skills/minecraft-datapack/github.svg)](https://agentmods.dev/skills/jahrome907/minecraft-agent-skills/minecraft-datapack)
Your own site
<a href="https://agentmods.dev/skills/jahrome907/minecraft-agent-skills/minecraft-datapack"><img src="https://agentmods.dev/badge/skills/jahrome907/minecraft-agent-skills/minecraft-datapack/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.

agentmods 80×15 button for minecraft-datapack

Your own site · 80×15
<a href="https://agentmods.dev/skills/jahrome907/minecraft-agent-skills/minecraft-datapack"><img src="https://agentmods.dev/badge/skills/jahrome907/minecraft-agent-skills/minecraft-datapack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,901 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.02901
Opus 5 $0.00030 $0.01451
Sonnet 5 $0.00012 $0.00580
Haiku 4.5 $0.00006 $0.00290

Measured 3d ago against content hash 9d48b7c3096c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

minecraft-datapack 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/jq-shim.mjs, scripts/validate-datapack.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/minecraft-datapack/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Minecraft Datapack Skill

Inspect pack.mcmeta and the target Minecraft version before editing. Preserve an existing target unless migration is requested; metadata numbers alone do not make older command or registry schemas compatible. Complete the requested pack changes, then use static checks and the available game environment proportionately.

Skill Scope

Routing Boundaries

  • Use when: the deliverable is datapack files (pack.mcmeta, data/...) and .mcfunction/JSON content.
  • Do not use when: the request is command-only snippets not tied to a datapack file tree (minecraft-commands-scripting).
  • Do not use when: the request requires loader APIs, Java code, or runtime mod behavior (minecraft-modding).

Pack Metadata

Minecraft Version Preferred pack metadata
1.21 / 1.21.1 pack_format: 48
1.21.2 / 1.21.3 pack_format: 57
1.21.4 pack_format: 61
1.21.5 pack_format: 71
1.21.6 pack_format: 80
1.21.7 / 1.21.8 pack_format: 81
1.21.9 / 1.21.10 min_format: [88, 0], max_format: [88, 0]
1.21.11 min_format: [94, 1], max_format: [94, 1]
26.1 min_format: [101, 1], max_format: [101, 1]
26.2 min_format: [107, 1], max_format: [107, 1]

Use pack_format for a legacy-only target through data pack format 81. Starting with data pack format 82 in 1.21.9, define both explicit min_format and max_format values. A range that includes a legacy format below 82 must also retain pack_format and supported_formats; do not include supported_formats for a modern-only range. For a legacy-compatible range, supported_formats may be one integer, a two-integer inclusive range, or an object with integer min_inclusive and max_inclusive fields. For exact patch targeting, use [major, minor] arrays for both min_format and max_format, including .0 versions such as [88, 0]. A single integer is equivalent to [major, 0] for min_format, while a single integer in max_format allows any minor version on that major line. Do not write decimal JSON numbers such as 94.1.

Read the full file on GitHub · 347 lines

Files

What ships with it

3 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.

Changes

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.

  1. 3d ago Changed · -188 lines 9d48b7c3096c
  2. 11d ago First seen · 535 lines · 60 tokens per session scan A 5d71a1f2c88d

Subscribe to this mod's changes

minecraft-datapack is a skill published in the GitHub repository Jahrome907/minecraft-agent-skills (136 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 2,901 once invoked, about $0.0003 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 2026-08-30.