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 skills/hakurei-git/minecraft-codex-companion/play-minecraftnpx skills add Hakurei-git/minecraft-codex-companion --skill play-minecraftgit clone --depth 1 https://github.com/Hakurei-git/minecraft-codex-companionWrote 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/hakurei-git/minecraft-codex-companion/play-minecraft)<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="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 | $0.00081 | $0.01821 |
| Opus 5 | $0.00041 | $0.00911 |
| Sonnet 5 | $0.00016 | $0.00364 |
| Haiku 4.5 | $0.00008 | $0.00182 |
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 5d 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 — 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
- Call
mc_list_companionsand choose a connected companion with the required capability. - For high-level survival requests, prefer the local Agent v2 route: call
mc_submit_goal, inspectmc_get_plan, then callmc_advance_goal. This creates a recoverable WorkGraph with local knowledge and facility memory. - For immediate control, safety, or one-step work, call
mc_acquire_controlwith a stable owner name. Never force takeover unless the user explicitly requests it. - Call
mc_observebefore assigning direct work and again whenever the world may have changed materially. - Call
mc_assign_taskonly for one typed low-level task, or whenmc_advance_goalhas queued the next task for you. Keep direct tasks small enough to monitor and recover. - Poll
mc_get_taskonly when the caller explicitly needs a manual status check. Long tasks keep running locally and send terminal progress back to Minecraft. - Use
mc_chatfor concise progress and questions in the player's current language; default to Simplified Chinese when the language is unclear. - Call
mc_release_controlwhen 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:
mc_submit_goalwith a shorttitle, the full playerobjective,requestedBy,source,mode, constraints, and optionaldeliverTo. Do not include API keys, local file paths, screenshots, logs, or provider prompts.- Inspect the returned plan. If it contains
await_planblocked, ask a concise clarifying question or fall back to a safe direct typed task only when the user's intent is unambiguous. - Call
mc_advance_goalto run local-only nodes and queue the next real task through the single-writer executor. - Use
mc_get_goal/mc_get_planfor status. Usemc_pause_goal,mc_resume_goal, ormc_cancel_goalwhen the player says pause, continue, stop, or replace the objective. - Use
mc_query_knowledgefor local gameplay facts andmc_list_facilitiesfor remembered homes, workstations, farms, ranches, mines, storage, builds, redstone facilities, and dragon landing areas.
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.
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.
- 5d ago First seen · 79 lines · 81 tokens per session scan A 8c27780cdc9f
play-minecraft is a skill published in the GitHub repository Hakurei-git/minecraft-codex-companion (1 stars, last pushed 7d ago), licensed MIT. It adds 81 tokens to every session and 1,821 once invoked, about $0.0004 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
ai-behavior-trees-utility-ai
Build a production behavior-tree runtime (Blackboard, action/condition leaves, sequence/selector/parallel composites, decorators) and a Utility AI system (response curves — linear, exponential, sigmoid, quadratic — considerations, and action evaluators), plus hybrid BT-drives-Utility agents. Use when implementing a…
camera-systems
Build game cameras that feel good — 2D follow with a deadzone, look-ahead, smoothing, and level-bounds clamping; 3D third-person orbit with collision and first-person look; plus multi-target framing and a shake hook. Engine-neutral techniques that pair with the engine's camera node and rigs like Unity Cinemachine or…
create-game-assets
Plan, generate, source, normalize, and validate cohesive visual game assets. Use for art direction, style bibles, sprites, tilesets, backgrounds, UI art, icons, textures, concept art, or 3D asset briefs.
game-ai
Design NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A pathfinding — engine-neutral algorithms that pair with the detected engine's navigation API. Use when building enemy AI, an FSM or behavior tree, steering/flocking, or pathfinding, or when the user mentions state…
game-feel
Add "juice" and game feel that makes actions satisfying — screen shake, hit-stop/freeze frames, tweened/eased motion, squash & stretch, knockback, and layered audio-visual feedback — as engine-neutral techniques that pair with the detected engine's tween, particle, and camera APIs. Use when the user mentions game…
game-ui-ux
Design and build game UI/UX — HUDs, menus, and overlays — that survive every screen: anchor- based responsive layout, resolution/aspect scaling and safe areas, keyboard/gamepad focus navigation, a screen/menu state stack, and event-driven (not polled) HUD updates. Engine- neutral patterns that pair with the detected…