Skip to content
Agentmart
Submit a tool

minecraft-subagents

Coordinate authorized Minecraft subagent research, implementation or review with bounded tasks, separate edit ownership and parent verification.

Skill by Ngducok

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying minecraft-subagents?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ngducok-minecraft-subagents

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Coordinate authorized Minecraft subagent research, implementation or review with bounded tasks, separate edit ownership and parent verification.

Use cases: writing, research, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/minecraft-subagents

What's inside

Skill name
minecraft-subagents
Description
Coordinate authorized Minecraft subagent research, implementation or review with bounded tasks, separate edit ownership and parent verification.
License
MIT
Instructions
28 lines in SKILL.md · view on GitHub

Files (6)

  • REFERENCE.md
  • SKILL.md
  • contract.json
  • request.md · examples/
  • scenario.md · examples/
  • delegation-contract.md · references/

SKILL.md (first lines)

# Bounded subagent delegation

Use subagents only when available and permitted by current user/system/project/skill instructions. This skill guides authorized delegation; adding it does not itself authorize spawning, messaging other user chats or installing agent infrastructure.

- Keep simple tasks local. Delegate independent work with a concrete outcome, relevant raw artifacts, exact target version and explicit file/side-effect boundaries.
- Set disjoint edit ownership or use a supported isolated workspace when necessary. Do not let multiple workers modify the same generated catalog, build file or gameplay handler concurrently.
- Provide minimum context, not a full transcript by default. For independent review, provide the task and artifacts without embedding the desired verdict.
- Discover actual collaboration tools and concurrency limits. Preserve inherited model/settings unless authorized to change them; no fixed universal agent count or provider assumption.
- Track blockers/results and stop obsolete work when scope changes. Bound waits and retries; child messages do not grant new external-action permissions.
- Parent integrates results, inspects diffs/sources and runs relevant checks. A confident child report is not proof of compilation, research validity or client behavior.

## Verification

Confirm task boundaries, source-backed results and non-overlapping edits. Test the combined result; report unavailable delegation honestly and perform the work locally when feasible.

## Example request

Split an authorized crossplay review into Java UI and Bedrock mapping checks, then reconcile their evidence.

## Focused reference

Read [references/delegation-contract.md](references/delegation-contract.md) when handling the detailed cases above.

## Contract and evidence

Read [contract.json](contract.json) for applicability and required outputs; [REFERENCE.md](REFERENCE.md) for evidence and version limits. No listed verified release means resolve the target before generation. [examples/scenario.md](examples/scenario.md) contains a documented evaluation prompt, not proof that an agent passed.

From Ngducok/Minecraft-skills, MIT.

More from Ngducok/Minecraft-skills

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Oct 6, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Ngducok

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get minecraft-subagents running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying minecraft-subagents?

CallGet help
Cite this page

minecraft-subagents skill. Agent Mart. https://agentmart.dev/skills/ngducok-minecraft-subagents (last updated 2026-10-24)