minecraft-build

minecraft-build is a command for Claude Code from intellegix/intellegix-code-agent-toolkit. It costs 0 tokens per session (1,037 once invoked), scanned A, original, MIT.

A placeholder command for building structures in Minecraft Bedrock, a version of Minecraft that supports cross-device play. It describes a planned research-based process but is not wired up for use.

In plain words
What is it for?
The intended job is to research real-world architecture, create a build plan, and place blocks through Minecraft tools, but this version does not perform those steps.
Why use it?
It makes clear that the documented workflow is unfinished and should not be treated as an active building command.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit The intended job is to research real-world architecture, create a build plan, and place blocks through Minecraft tools, but this version does not perform those steps.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/intellegix/intellegix-code-agent-toolkit/minecraft-build
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.

Clone the repo
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkit

Made for: Claude Code.

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-build

README.md
[![agentmods](https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/minecraft-build/github.svg)](https://agentmods.dev/commands/intellegix/intellegix-code-agent-toolkit/minecraft-build)
Your own site
<a href="https://agentmods.dev/commands/intellegix/intellegix-code-agent-toolkit/minecraft-build"><img src="https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/minecraft-build/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 minecraft-build

Your own site · 80×15
<a href="https://agentmods.dev/commands/intellegix/intellegix-code-agent-toolkit/minecraft-build"><img src="https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/minecraft-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,037 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 $0.00000 $0.01037
Opus 5.5 $0.00000 $0.00415
Sonnet 5.5 $0.00000 $0.00207
Haiku 4.5 $0.00000 $0.00104

Measured 1mo ago against content hash a446d0acd012, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

minecraft-build 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 1mo 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.

commands/minecraft-build.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/minecraft-build — Research-Grounded Minecraft Build (v2 SCAFFOLD — NOT YET WIRED)

⚠️ v2 SCAFFOLD — NOT ACTIVE FOR v1. This skill is a placeholder describing the intended research-grounded build flow. It is not yet wired to the minecraft MCP server and must not be invoked as a working command yet. For v1, drive builds directly via the minecraft MCP tools (connect_status, setblock, fill, run_command) plus knowledge/building-principles.md. Remove this banner when the flow below is implemented and tested.

Build a structure in Minecraft Bedrock by grounding the design in real-world architectural references (via Perplexity) before placing a single block.


Input

$ARGUMENTS = a natural-language build request, e.g. a medieval stone watchtower or a cozy 2-story oak cottage.


Intended flow (v2)

  1. Research the design. Call research_query (Perplexity) for design references for the requested build — real-world proportions, material/color palette, and construction technique (e.g. "typical proportions and stone palette of a medieval watchtower; wall-to-height ratio, crenellation spacing, window placement").
  2. Translate to a parametric plan. Claude converts the research into a concrete parametric plan using mcp-servers/minecraft/knowledge/building-principles.md — footprint dimensions, palette (primary/secondary/accent/trim), the footprint → walls → openings → roof → towers → battlements → details/lighting decomposition, and exact block ids/states.
  3. Execute via the minecraft MCP tools. connect_status first (abort if no client connected), then emit the plan as ordered setblock/fill calls. Use relative_to_player for "build here" (no absolute coords needed); auto-chunk any fill over the 32768-block cap.
  4. Verify. Read each tool's command response to confirm blocks placed (and re-issue any failed step), then summarize the finished build.

Not-active checklist (before flipping to active)

Read the full file on GitHub · 62 lines

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. 1mo ago First seen · 62 lines · 0 tokens per session scan A a446d0acd012

Subscribe to this mod's changes

minecraft-build is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,037 tokens. 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 2026-08-30.