minecraft-codex-companion: Skill for Codex

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

play-minecraft is a skill for Codex from Hakurei-git/minecraft-codex-companion. It costs 81 tokens per session (1,821 once invoked), scanned A, original, MIT.

A tool for controlling independent companion players in Minecraft through a local MCP server. It supports game activities such as movement, gathering, crafting, farming, storage, combat, and building.

In plain words
What is it for?
Choosing a connected companion, assigning survival goals or small tasks, monitoring progress, chatting in-game, and carrying out activities such as travel, resource collection, crafting, and construction.
Why use it?
It lets an agent delegate in-game work to a companion while observing the world and tracking longer tasks.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is Hakurei-git/minecraft-codex-companion's own configuration. It tells Codex how to work on minecraft-codex-companion 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-codex-companion configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Hakurei-git/minecraft-codex-companion. 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/Hakurei-git/minecraft-codex-companion/main/.agents/skills/play-minecraft/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Hakurei-git/minecraft-codex-companion

Made for: 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 play-minecraft

README.md
[![agentmods](https://agentmods.dev/badge/skills/hakurei-git/minecraft-codex-companion/play-minecraft/github.svg)](https://agentmods.dev/skills/hakurei-git/minecraft-codex-companion/play-minecraft)
Your own site
<a href="https://agentmods.dev/skills/hakurei-git/minecraft-codex-companion/play-minecraft"><img src="https://agentmods.dev/badge/skills/hakurei-git/minecraft-codex-companion/play-minecraft/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 play-minecraft

Your own site · 80×15
<a href="https://agentmods.dev/skills/hakurei-git/minecraft-codex-companion/play-minecraft"><img src="https://agentmods.dev/badge/skills/hakurei-git/minecraft-codex-companion/play-minecraft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,821 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.
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 $0.00081 $0.01821
Opus 5.5 $0.00032 $0.00728
Sonnet 5.5 $0.00016 $0.00364
Haiku 4.5 $0.00008 $0.00182

Measured 2mo ago against content hash 8c27780cdc9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

play-minecraft 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.

.agents/skills/play-minecraft/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Play Minecraft

Operate as an independent companion player. Plan and converse at human time scales; leave movement, combat reactions, navigation, and survival ticks to the local backend.

Core Workflow

  1. Call mc_list_companions and choose a connected companion with the required capability.
  2. For high-level survival requests, prefer the local Agent v2 route: call mc_submit_goal, inspect mc_get_plan, then call mc_advance_goal. This creates a recoverable WorkGraph with local knowledge and facility memory.
  3. For immediate control, safety, or one-step work, call mc_acquire_control with a stable owner name. Never force takeover unless the user explicitly requests it.
  4. Call mc_observe before assigning direct work and again whenever the world may have changed materially.
  5. Call mc_assign_task only for one typed low-level task, or when mc_advance_goal has queued the next task for you. Keep direct tasks small enough to monitor and recover.
  6. Poll mc_get_task only when the caller explicitly needs a manual status check. Long tasks keep running locally and send terminal progress back to Minecraft.
  7. Use mc_chat for concise progress and questions in the player's current language; default to Simplified Chinese when the language is unclear.
  8. Call mc_release_control when handing the companion to another controller.

Local Agent v2 Workflow

Use Agent v2 for requests that require planning, missing-material resolution, facilities, storage, mining, building, farming, ranching, or multi-step recovery. Examples: 给我做一把钻石镐, 建造田地, 去找些食物, 我要64个火把, 箱子里有铁, 停止目标回来, 一起骑龙, 继续上次失败的建造.

Recommended sequence:

  1. mc_submit_goal with a short title, the full player objective, requestedBy, source, mode, constraints, and optional deliverTo. Do not include API keys, local file paths, screenshots, logs, or provider prompts.
  2. Inspect the returned plan. If it contains await_plan blocked, ask a concise clarifying question or fall back to a safe direct typed task only when the user's intent is unambiguous.
  3. Call mc_advance_goal to run local-only nodes and queue the next real task through the single-writer executor.
  4. Use mc_get_goal / mc_get_plan for status. Use mc_pause_goal, mc_resume_goal, or mc_cancel_goal when the player says pause, continue, stop, or replace the objective.
  5. Use mc_query_knowledge for local gameplay facts and mc_list_facilities for remembered homes, workstations, farms, ranches, mines, storage, builds, redstone facilities, and dragon landing areas.

Read the full file on GitHub · 79 lines

Files

What ships with it

2 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. 2mo ago First seen · 79 lines · 81 tokens per session scan A 8c27780cdc9f

Subscribe to this mod's changes

play-minecraft is a skill published in the GitHub repository Hakurei-git/minecraft-codex-companion (1 stars, last pushed 24d ago), licensed MIT. It adds 81 tokens to every session and 1,821 once invoked, about $0.0003 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.

Related

play-minecraft compared with skills from other repositories

play-minecraft next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
play-minecraftHakurei-git/minecraft-codex-companionSkill124d agoMITA81Codex
minecraft-bukkit-prormyndharis/antigravity-skillsSkill2.0k3d agoMITA57Claude Code, Codex
godot-gdscript-patternsrmyndharis/antigravity-skillsSkill2.0k3d agoMITA47Claude Code, Codex
web-game-engine-expertroedyrustam/vibes-plugSkill125todayMITA40Cursor
battlenet-automationComposioHQ/awesome-claude-skillsSkill79k1mo agononeA30Claude Code, Codex
unity-csharp-architecture-and-ecshamzabellouch/agent-skillsSkill825d agoMITA54Claude Code, Codex
unreal-engine-cpp-blueprintshamzabellouch/agent-skillsSkill825d agoMITA50Claude Code, Codex