Agent skill

Minecraft Harness

by shepherdjerred in shepherdjerred/monorepo

Drive disposable Minecraft (Paper 26.2) sandboxes through toolkit mc — run console commands, edit with WorldEdit, read exact block states, snapshot and restore regions, playtest with Citizens…

GPL-3.0Auto-check: notes

Install Minecraft Harness

skills CLI
$ npx skills add shepherdjerred/monorepo --skill minecraft-harness -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shepherdjerred/monorepo minecraft-harness --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/minecraft-harness .claude/skills/minecraft-harness && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
minecraft-harness
GitHub stars
112
Token cost
~858 tokens
SKILL.md length
344 words
Files
5 (incl. references)
Skills in repo
63
Repo updated
First seen
Licence
GPL-3.0

At a glance

Drive disposable Minecraft (Paper 26.2) sandboxes through toolkit mc — run console commands, edit with WorldEdit, read exact block states, snapshot and restore regions, playtest with Citizens…

  • Try out a plugin change
  • SKILL.md covers Safety, Start, Routing and Clean up
  • Calls mise and kubectl
  • Prototype a build

What it does

Minecraft Harness is an agent skill from shepherdjerred/monorepo. Drive disposable Minecraft (Paper 26.2) sandboxes through toolkit mc — run console commands, edit with WorldEdit, read exact block states, snapshot and restore regions, playtest with Citizens actors, and watch events and logs — and make guarded, journaled, undoable changes on live tsmc with --target live. Use to try out a plugin change, prototype a build, validate a gameplay idea, or apply an agreed change to The Storm.

Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `agents/openai.yaml`, `references/actors-playtests.md` and `references/commands.md`).

The repository describes itself as: Monorepo for all of my projects. The licence is GPL-3.0.

When your agent uses it

  • Try out a plugin change
  • Prototype a build
  • Validate a gameplay idea
  • Apply an agreed change to The Storm

Example prompts

  • “/minecraft-harness”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Read

What it can do on your machine

Read from SKILL.md and the folder at commit da14ae9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • mise
    • kubectl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use kubectl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Minecraft Harness loads about 858 tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 111 tokens; SKILL.md has 344 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~858
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shepherdjerred/monorepo at commit da14ae9, republished under its GPL-3.0 licence (© shepherdjerred). 344 words, ~858 tokens.

Download SKILL.mdSave it as .claude/skills/minecraft-harness/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
minecraft-harness
description
Drive disposable Minecraft (Paper 26.2) sandboxes through `toolkit mc` — run console commands, edit with WorldEdit, read exact block states, snapshot and restore regions, playtest with Citizens actors, and watch events and logs — and make guarded, journaled, undoable changes on live tsmc with `--target live`. Use to try out a plugin change, prototype a build, validate a gameplay idea, or apply an agreed change to The Storm.
allowed-tools
Bash, Read

Minecraft harness

toolkit mc talks to the mc-harness daemon, which runs Paper 26.2 sandboxes with WorldEdit and the repo's MCBridge plugin. Every world operation goes through MCBridge, so reads return exact 26.2 block states and WorldEdit runs as a named actor (agent:<session>) with its own undo history. Package detail: packages/mc-harness/README.md.

Safety

  • Sandboxes by default. Live tsmc is reached only with an explicit --target live; read references/live.md first.
  • A sandbox is disposable: it is removed at its TTL (default 2h) or when the daemon stops, unless created with --keep.
  • Ports are bound to 127.0.0.1. Never print the bridge token or RCON password from ~/.toolkit/mc/sandboxes/*/record.json.

Start

bash
mise exec -- gradle -p packages/the-storm/plugin :bridge:assemble   # build MCBridge.jar
toolkit mc sandbox up --world void      # or --world flat; auto-starts the daemon
toolkit mc info                          # versions, worlds, plugins, capabilities

sandbox up prints the sandbox id and the game port, so a person can join with a 26.2 client at 127.0.0.1:<port> (offline mode). With one sandbox running, commands target it automatically; otherwise pass --target <id>.

--provider kubernetes runs the sandbox as a pod in the cluster's mc-sandbox namespace (ports reach you through kubectl port-forward; TTL at most 8h). --profile storm-prod / storm-candidate boot the published the-storm-server image at its production / candidate pin and default to the cluster; use them to check behavior as live tsmc runs it.

Routing

TaskRead
WorldEdit edits, region reads, snapshots, consolereferences/commands.md
Actors and repeatable playtestsreferences/actors-playtests.md
A user-requested change on live tsmcreferences/live.md
A build that should end up in a real placethe minecraft-building skill

Key rules from those references:

  • Each we call carries its own world and selection; trust its changed N, not WorldEdit's "blocks affected" text. Negative coordinates work as plain arguments; toolkit mc <command> --help shows usage.
  • Take a snapshot before a large edit; we-undo only covers WorldEdit history.
  • Actors cannot see chat or drive client UI; assert effects, not ok: true.
  • On live, every write needs --reason; never scale the StatefulSet or touch mc-router annotations or the mining-reset lock.

Clean up

Stop what you started: toolkit mc sandbox down --all, then toolkit mc daemon stop if the daemon was started for this task. Report which sandbox id and profile the evidence came from; a sandbox result is not production behavior.

© shepherdjerred, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in .agents/skills/minecraft-harness of shepherdjerred/monorepo.

  • SKILL.md
  • agents/openai.yaml
  • references/actors-playtests.md
  • references/commands.md
  • references/live.md

Open the folder on GitHubat commit da14ae9

Compare with similar skills

Minecraft Harness next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Minecraft Harness compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Minecraft Harness this skillshepherdjerred/monorepo112—~858Automated safety check: NotesGPL-3.0
Agent Sandboxruvnet/ruflo74k3 repos~777Automated safety check: PassMIT
Sandbox Benchvercel/next.js143k—~4.1kAutomated safety check: PassMIT
Sandboxalsk1992/CloddsBot2.9k—~341Automated safety check: PassMIT
Feishu Driveopenclaw/openclaw392k—~375Automated safety check: PassMIT
Lever Sandbox AutomationComposioHQ/awesome-claude-skills77k3 repos~753Automated safety check: PassNone

Similar skills

  • Agent Sandbox

    ruvnet/ruflo

    Agent skill for sandbox - invoke with $agent-sandbox. An agent skill from ruvnet/ruflo.

    74k GitHub starsUsed in 3 repos~777 tokens
    Auto-check passed
  • Sandbox Bench

    vercel/next.js

    Official

    Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app…

    143k GitHub stars~4.1k tokensUpdated today
    Data & AnalyticsAuto-check passed
  • Sandbox

    alsk1992/CloddsBot

    Visual HTML canvas sandbox for agent-driven UI and live previews

    2.9k GitHub stars~341 tokensUpdated 5 days ago
    Auto-check passed
  • Feishu Drive

    openclaw/openclaw

    Feishu cloud-storage and comment workflows. An agent skill from openclaw/openclaw.

    392k GitHub stars~375 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Lever Sandbox Automation

    ComposioHQ/awesome-claude-skills

    Automate Lever Sandbox tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~753 tokens
    Productivity & AutomationAuto-check passed
  • Vercel Sandbox Browser

    vercel-labs/agent-browser

    Official

    Runs agent-browser with headless Chrome inside Vercel Sandbox microVMs so Vercel-deployed apps can automate a browser without binary size limits.

    44k GitHub stars~2k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from shepherdjerred/monorepo

All 63 skills in this repo
  • Bun Runtime Best Practices

    shepherdjerred/monorepo

    Bun runtime APIs and current operational patterns for files, processes, modules, networking, databases, tests, and deployment.

    112 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Bun Test Patterns

    shepherdjerred/monorepo

    Current Bun test runner guidance for discovery, isolation, parallelism, sharding, changed tests, mocks, timers, snapshots, coverage, DOM Testing Library, and integration teardown.

    112 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Bun Workspaces

    shepherdjerred/monorepo

    Current Bun workspace guidance for isolated and hoisted linkers, catalogs, filters, scripts, dependency classes, lockfiles, lifecycle trust, caches, publishing, TypeScript package exports, and…

    112 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Deep Research

    shepherdjerred/monorepo

    This skill should be used when the user asks to "deep research", "research this topic", "investigate thoroughly", "do a deep dive on", "comprehensive research on", "find everything about", "survey…

    112 GitHub stars~4.7k tokensUpdated today
    Auto-check: notes
  • Figma Use

    shepherdjerred/monorepo

    This skill should be used when the user asks to "create a Figma design", "design in Figma", "make a Figma mockup", "create an app icon", "design UI", "render JSX to Figma", "export from Figma"…

    112 GitHub stars~946 tokensUpdated today
    Auto-check passed
  • Fish Helper

    shepherdjerred/monorepo

    Current Fish shell scripting, functions, abbreviations, completions, variables, events, configuration, plugins, testing, and safety guidance.

    112 GitHub stars~2k tokensUpdated today
    Auto-check passed

Questions about Minecraft Harness

What does Minecraft Harness do?

Drive disposable Minecraft (Paper 26.2) sandboxes through toolkit mc — run console commands, edit with WorldEdit, read exact block states, snapshot and restore regions, playtest with Citizens…. Minecraft Harness is an agent skill from shepherdjerred/monorepo.2) sandboxes through toolkit mc — run console commands, edit with WorldEdit, read exact block states, snapshot and restore regions, playtest with Citizens actors, and watch events and logs — and make guarded, journaled, undoable changes on live tsmc with --target live.

When should I use Minecraft Harness?

Minecraft Harness fits situations like: try out a plugin change; prototype a build; validate a gameplay idea; apply an agreed change to The Storm.

How do I install Minecraft Harness in Claude Code?

Run `npx skills add shepherdjerred/monorepo --skill minecraft-harness -a claude-code`. Or copy the skill folder (.agents/skills/minecraft-harness in shepherdjerred/monorepo) into .claude/skills/minecraft-harness in your project. Claude Code loads it when a task matches its description.

How do I install Minecraft Harness in Codex?

Run `npx skills add shepherdjerred/monorepo --skill minecraft-harness -a codex`. Or copy the skill folder (.agents/skills/minecraft-harness in shepherdjerred/monorepo) into .agents/skills/minecraft-harness in your project. Codex loads it when a task matches its description.

Can I use Minecraft Harness in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shepherdjerred/monorepo --skill minecraft-harness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/minecraft-harness, .gemini/skills/minecraft-harness, .github/skills/minecraft-harness and .opencode/skills/minecraft-harness in your project.

What does Minecraft Harness need to run?

Going by SKILL.md and its folder, Minecraft Harness needs the command-line tools its instructions call (mise and kubectl). Its frontmatter pre-approves these tools: Bash, Read.

Does Minecraft Harness access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Minecraft Harness safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Minecraft Harness use?

Minecraft Harness is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Minecraft Harness use?

About 858 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Minecraft Harness?

Skills that share tags, products or a category with Minecraft Harness: Agent Sandbox (ruvnet/ruflo, 74k stars), Sandbox Bench (vercel/next.js, 143k stars), Sandbox (alsk1992/CloddsBot, 2.9k stars) and Feishu Drive (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Minecraft Harness?

shepherdjerred (a GitHub user) maintains it in shepherdjerred/monorepo, which has 112 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 8, 2026.

Source: shepherdjerred/monorepo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.