agentmods.dev

minecraft-async

minecraft-async is a skill for Claude Code, Codex from 02loveslollipop/OpenCROW. It costs 75 tokens per session (1,395 once invoked), scanned A, original, Apache-2.0.

A controller for an installed Minecraft Java client, the desktop version of Minecraft, that can run the game offline and interact with its window, chat, commands, servers, and logs.

In plain words
What is it for?
Use it to launch or stop the client, join worlds or multiplayer servers, send chat and slash commands, take screenshots, focus the game window, and inspect logs.
Why use it?
It lets an agent operate Minecraft asynchronously instead of relying on manual keyboard input or one-off commands.

Skill for Claude CodeCodex

not rated 8 changed today A scan 75 tokens original Apache-2.0
View the source file 02loveslollipop/OpenCROW
Install

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.

agentmods
npx agentmods add skills/02loveslollipop/opencrow/minecraft-async
Any agent
npx skills add 02loveslollipop/OpenCROW --skill minecraft-async
Clone the repo
git clone --depth 1 https://github.com/02loveslollipop/OpenCROW

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-async

README.md
[![agentmods](https://agentmods.dev/badge/skills/02loveslollipop/opencrow/minecraft-async.svg)](https://agentmods.dev/skills/02loveslollipop/opencrow/minecraft-async)
Your own site
<a href="https://agentmods.dev/skills/02loveslollipop/opencrow/minecraft-async"><img src="https://agentmods.dev/badge/skills/02loveslollipop/opencrow/minecraft-async.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00075 $0.01395
Opus 5 $0.00037 $0.00698
Sonnet 5 $0.00015 $0.00279
Haiku 4.5 $0.00007 $0.00139

Measured today against content hash 4ff71873afb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

minecraft-async 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/minecraft_async.py), 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.

skills/minecraft-async/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCROW I/O - Minecraft Async

Runtime preflight

Probe required commands with command -v and Python modules with importlib.util.find_spec before use. Prefer a PATH-resolved OpenCROW MCP helper or the ctf/sage environment when available, then the managed helper or system Python. If a capability is missing, stop that path safely and report the exact missing command or module.

Prefer the opencrow-minecraft-mcp server for status, launch, chat, commands, screenshots, and log reads. Fall back to scripts/mcx only when you need to inspect or debug the backend directly.

MCP First

  • Use toolbox_info, toolbox_verify, and toolbox_capabilities first.
  • Use the typed Minecraft operations:
    • minecraft_status
    • minecraft_launch
    • minecraft_join_server
    • minecraft_join_world
    • minecraft_focus
    • minecraft_send_text
    • minecraft_chat
    • minecraft_command
    • minecraft_screenshot
    • minecraft_read_log
    • minecraft_stop
  • Treat the MCP server as the main interface and scripts/mcx as the implementation fallback.

Use scripts/mcx to control the already-installed Minecraft Java client under ~/.minecraft when you are operating outside MCP.

Workflow

  1. Check status to confirm the install, versions, X11 display, and any running session.
  2. Launch with the direct backend for offline usernames against the existing install.
  3. Use join-server or join-world when you need the client to open directly into a target.
  4. Use focus, chat, command, or send-text for fast in-game actions.
  5. Capture a screenshot when the visual state matters.
  6. Inspect latest.log and the managed launcher log when something fails.
  7. Stop the managed session explicitly when done.

Commands

# Inspect install, window, logs, and managed session state
scripts/mcx status

# Launch the existing client directly in offline mode
scripts/mcx launch --username ra13118 --version 1.21.8

# Launch and connect to a server immediately via quick play
scripts/mcx join-server --username ra13118 --server dyn-01.midnightflag.fr:13118 --version 1.21.8

# Launch directly into a local world by save-folder name
scripts/mcx join-world --username ra13118 --world NewWorld --version 1.21.8

# Focus the game window, open chat, and send text
scripts/mcx chat --text 'hello from OpenCROW'

# Focus the game window, open slash-command mode, and run a command
scripts/mcx command --text 'tp @s 0 100 0'

# Type raw text into the currently focused field
scripts/mcx send-text --text 'seed?'

# Capture the current game window to a PNG
scripts/mcx screenshot --output /tmp/minecraft-state.png

# Read the latest Minecraft log
scripts/mcx read-log --which latest --tail 80

# Confirm the running game uses the requested offline username
scripts/mcx verify-identity --session world-demo --username ra13118

# Stop the managed session
scripts/mcx stop

Read the full file on GitHub · 155 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. today Changed · +3 lines 4ff71873afb0
  2. 5d ago First seen · 152 lines · 75 tokens per session scan A d15e7b9ef7d3

Subscribe to this mod's changes

minecraft-async is a skill published in the GitHub repository 02loveslollipop/OpenCROW (8 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 1,395 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.

Game developmentagent-orchestrationagent-runtimeagentic-aiai-agentsctfcybersecurity
Related

Other skills, from other repositories

dd-report-format

Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.

Abilityai/trinity · 27 tokens

dd-risk-scoring

Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.

Abilityai/trinity · 29 tokens

dd-synthesis

Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.

Abilityai/trinity · 33 tokens

dd-sourcing

Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.

Abilityai/trinity · 29 tokens

dd-verification

Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.

Abilityai/trinity · 35 tokens

skill-lab

Canonical Runx skill-authoring implementation. Use for designing, creating, updating, improving, or adding harness coverage to a Runx skill package; it combines bounded agent judgment with native file writes, inspection, and safe harness validation. When a host skill-creator also triggers, use its general guidance but…

runxhq/runx · 72 tokens