Agent skill

Micropolis Command Bus

by SimHacker in SimHacker/MicropolisCore

Routes all Micropolis UI, CLI, MCP, chat, pie menu, and LLM actions through a safe command bus with preview/proposal/approval.

GPL-3.0Auto-check passedAgent Workflows

Install Micropolis Command Bus

skills CLI
$ npx skills add SimHacker/MicropolisCore --skill micropolis-command-bus -a claude-code

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

GitHub CLI
$ gh skill install SimHacker/MicropolisCore micropolis-command-bus --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/SimHacker/MicropolisCore.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/micropolis-command-bus .claude/skills/micropolis-command-bus && 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
micropolis-command-bus
GitHub stars
208
Token cost
~1.5k tokens
SKILL.md length
549 words
Files
4
Skills in repo
3
Repo updated
First seen
Licence
GPL-3.0

At a glance

Routes all Micropolis UI, CLI, MCP, chat, pie menu, and LLM actions through a safe command bus with preview/proposal/approval.

  • Works in 4 steps: GLANCE.yml — quick activation check → CARD.yml — machine-readable interface,… → SKILL.md — this operational protocol → …
  • Agents need to inspect
  • SKILL.md covers What It Is, Invariant, Semantic Image Pyramid and Files, plus 8 more sections
  • Calls npm

What it does

Micropolis Command Bus is an agent skill from SimHacker/MicropolisCore. Routes all Micropolis UI, CLI, MCP, chat, pie menu, and LLM actions through a safe command bus with preview/proposal/approval. Use when agents need to inspect, propose, approve, reject, or dispatch Micropolis commands.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `CARD.yml`, `GLANCE.yml` and `README.md`).

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Micropolis C++ Core (based on the original SimCity Classic by Maxis/EA). The licence is GPL-3.0.

When your agent uses it

  • Agents need to inspect
  • Dispatch Micropolis commands

Example prompts

  • “Use the micropolis-command-bus skill to route all Micropolis UI, CLI, MCP, chat, pie menu, and LLM actions through a safe command bus with…”
  • “/micropolis-command-bus”

Requirements

  • Pre-approved tools (allowed-tools): read_file, write_file, run_terminal_cmd

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. GLANCE.yml — quick activation check
  2. CARD.yml — machine-readable interface, advertisements, methods
  3. SKILL.md — this operational protocol
  4. README.md — deeper human-facing rationale

What it can do on your machine

Read from SKILL.md and the folder at commit 5e78c58. 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:

    • read_file
    • write_file
    • run_terminal_cmd

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use npm, 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

Micropolis Command Bus loads about 1.5k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 549 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 passed

The automated check found no risky patterns in SKILL.md.

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 SimHacker/MicropolisCore at commit 5e78c58, republished under its GPL-3.0 licence (© SimHacker). 549 words, ~1,530 tokens.

Download SKILL.mdSave it as .claude/skills/micropolis-command-bus/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
micropolis-command-bus
description
Routes all Micropolis UI, CLI, MCP, chat, pie menu, and LLM actions through a safe command bus with preview/proposal/approval. Use when agents need to inspect, propose, approve, reject, or dispatch Micropolis commands.
allowed-tools
read_file, write_file, run_terminal_cmd
license
GPL-3.0
tier
2
protocol
MICROPOLIS-COMMAND-BUS
related
micropolis, moollm, mooco, skill, card, advertisement, action-queue, protocol, github, skill-snitch, speed-of-light, planning, simulation, constructionism
tags
micropolis, command-bus, mcp, llm-actions, operator-model, sveltekit, safety

Micropolis Command Bus

"All roads to the simulator go through the bus."

What It Is

The Micropolis command bus is the shared operation layer for humans, UI widgets, pie menus, keyboard shortcuts, chat slash commands, MCP tools, CLI commands, and MOOLLM characters.

It is the Micropolis equivalent of Blender operators, extended with MOOLLM-style proposal, preview, approval, and audit semantics.

Invariant

All agent-controlled Micropolis actions must go through the command bus. Do not call simulator, view, window, workspace, or GitHub mutation APIs directly when a command exists or should exist.

Semantic Image Pyramid

Read in this order:

  1. GLANCE.yml — quick activation check
  2. CARD.yml — machine-readable interface, advertisements, methods
  3. SKILL.md — this operational protocol
  4. README.md — deeper human-facing rationale

Never load a lower layer without reading the layer above it first.

Files

FileRole
apps/micropolis/src/lib/CommandBus.tsCore bus: commands, dispatch, preview, undo, proposals
apps/micropolis/src/lib/micropolisCommands.tsMicropolis command registry
apps/micropolis/src/lib/CommandMcpService.tsMCP-style service wrapper
apps/micropolis/cli/bus/index.tsUnified CLI command-bus branch
skills/micropolis-command-bus/CARD.ymlMOOLLM card interface
skills/micropolis-command-bus/GLANCE.ymlTiny mipmap summary

Command Shape

Commands are data objects:

ts
{
  id: string;
  label: string;
  icon?: string;
  context?: string | string[];
  enabled?: boolean | ((context) => boolean);
  run: (context) => result;
  preview?: (context) => preview;
  undo?: (context) => undo;
  policy?: {
    risk: "safe" | "reversible" | "destructive" | "external";
    allowLLM?: boolean;
    requiresApproval?: boolean | ((context) => boolean);
  };
}

All surfaces dispatch the same command IDs:

  • Pie menus
  • Keyboard shortcuts
  • Buttons
  • Chat slash commands
  • MCP tools
  • CLI commands
  • LLM proposals
  • Future tab/window/workspace controls

Safety Policy

RiskLLM Behavior
safeMay dispatch directly when useful
reversiblePrefer proposal unless user explicitly approved direct execution
destructiveMust preview and propose; user approval required
externalMust preview and propose; explicit user approval required

LLM Workflow

  1. List available commands.
  2. Preview the intended command.
  3. Propose actions when the source is llm, especially if not safe.
  4. Wait for approval or rejection.
  5. Dispatch only after approval or when policy allows direct execution.
  6. Log the result in the conversation or session log when available.

CLI

Run from MicropolisCore/micropolis:

bash
npm run micropolis -- bus list --format yaml
npm run micropolis -- bus preview <command-id> --args '{"key":"value"}' --actor llm --reason "why" --format yaml
npm run micropolis -- bus propose <command-id> --args '{}' --actor llm --reason "why" --format yaml
npm run micropolis -- bus proposals --status pending --format yaml
npm run micropolis -- bus approve <proposal-id> --actor user --format yaml
npm run micropolis -- bus reject <proposal-id> --reason "why" --format yaml

The command-bus branch is one module of the unified CLI. --help, about, and api are the terminal-facing documentation.

MCP Service

CommandMcpService.ts exposes MCP-style tools:

  • command_list
  • command_preview
  • command_propose
  • command_dispatch
  • command_proposal_list
  • command_proposal_approve
  • command_proposal_reject

This is not yet a standalone MCP server process. It is the service layer that a future mooco or MCP adapter can export.

Show full SKILL.md (211 more words)Show less

MOOLLM Composition

This skill deliberately composes with:

SkillHow
micropolisDomain model, simulation, Git multiverse, educational purpose
micropolisUnified CLI and module surface
tool-calling-protocolwhy/reason discipline and safe tool execution
action-queuePending command proposals are action-queue entries
advertisementCommands advertise capabilities and map naturally to pie menus
cardCARD.yml declares methods, ads, K-lines, and interface
githubFuture external commands for issues, PRs, commits, branches
skill-snitchAudit command declarations against actual dispatch behavior
moocoFuture orchestrator can operationalize MCP service and proposal state
speed-of-lightMultiple AI tutors can debate proposals inside one LLM call
constructionismStudents learn by previewing, proposing, running, undoing actions

Design Intent

UI surfaces should not own behavior. They invoke named operations with context.

The bus gives Micropolis a single, inspectable, replayable command vocabulary. That vocabulary can drive the simulator today and later drive tabbed windows, spatial outlines, GitHub-as-MMORPG workflows, role presets, AI tutors, and multiplayer governance.

Upgrade Path

  1. Persist CLI proposal state so proposals survive separate processes.
  2. Add event logging compatible with MOOLLM session-log.
  3. Add command advertisements to pie-menu construction.
  4. Route chat slash commands through the bus.
  5. Export a real MCP server adapter.
  6. Add skill-snitch checks: every mutating code path should correspond to a command.
  7. Add GitHub commands as external-risk proposals.

© SimHacker, 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 3 other files in skills/micropolis-command-bus of SimHacker/MicropolisCore.

  • SKILL.md
  • CARD.yml
  • GLANCE.yml
  • README.md

Open the folder on GitHubat commit 5e78c58

Compare with similar skills

Micropolis Command Bus 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.

Micropolis Command Bus compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Micropolis Command Bus this skillSimHacker/MicropolisCore208—~1.5kAutomated safety check: PassGPL-3.0
Agentforce GenerateSalesforceAIResearch/agentforce-adlc1141 repos~7.4kAutomated safety check: PassCustom licence
Setup Open IndexDrDroidLab/open-index112—~855Automated safety check: PassMIT
Integrationsindranilbanerjee/digital-marketing-pro8551 repos~1.1kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • Agentforce Generate

    SalesforceAIResearch/agentforce-adlc

    Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script.

    114 GitHub starsUsed in 1 repo~7.4k tokens
    Agent WorkflowsAuto-check passed
  • Setup Open Index

    DrDroidLab/open-index

    Install and configure Open Index as the read/write context layer for a domain-specialized agent.

    112 GitHub stars~855 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Integrations

    indranilbanerjee/digital-marketing-pro

    Show the MCP integration status dashboard — which connectors are connected, which are available but not yet configured, the skills each one unlocks, per-category coverage, and the top three…

    855 GitHub starsUsed in 1 repo~1.1k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

More from SimHacker/MicropolisCore

  • Micropolis

    SimHacker/MicropolisCore

    Parent MicropolisCore skill exposing the unified CLI, C++/WASM simulator, save-file tools, renderer/content workflows, command bus, and MOOLLM integration protocols.

    208 GitHub stars~5.2k tokensUpdated today
    Auto-check passed
  • Screen Angel

    SimHacker/MicropolisCore

    Read and act on a live desktop through its accessibility tree.

    208 GitHub stars~6.2k tokensUpdated today
    Auto-check passed

Questions about Micropolis Command Bus

What does Micropolis Command Bus do?

Routes all Micropolis UI, CLI, MCP, chat, pie menu, and LLM actions through a safe command bus with preview/proposal/approval. Micropolis Command Bus is an agent skill from SimHacker/MicropolisCore. Routes all Micropolis UI, CLI, MCP, chat, pie menu, and LLM actions through a safe command bus with preview/proposal/approval.

When should I use Micropolis Command Bus?

Micropolis Command Bus fits situations like: agents need to inspect; dispatch Micropolis commands.

How do I install Micropolis Command Bus in Claude Code?

Run `npx skills add SimHacker/MicropolisCore --skill micropolis-command-bus -a claude-code`. Or copy the skill folder (skills/micropolis-command-bus in SimHacker/MicropolisCore) into .claude/skills/micropolis-command-bus in your project. Claude Code loads it when a task matches its description.

How do I install Micropolis Command Bus in Codex?

Run `npx skills add SimHacker/MicropolisCore --skill micropolis-command-bus -a codex`. Or copy the skill folder (skills/micropolis-command-bus in SimHacker/MicropolisCore) into .agents/skills/micropolis-command-bus in your project. Codex loads it when a task matches its description.

Can I use Micropolis Command Bus 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 SimHacker/MicropolisCore --skill micropolis-command-bus -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/micropolis-command-bus, .gemini/skills/micropolis-command-bus, .github/skills/micropolis-command-bus and .opencode/skills/micropolis-command-bus in your project.

What does Micropolis Command Bus need to run?

Going by SKILL.md and its folder, Micropolis Command Bus needs the command-line tools its instructions call (npm). Its frontmatter pre-approves these tools: read_file, write_file, run_terminal_cmd.

Does Micropolis Command Bus access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Micropolis Command Bus safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Micropolis Command Bus use?

Micropolis Command Bus is published under the GPL-3.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Micropolis Command Bus use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Micropolis Command Bus?

Skills that share tags, products or a category with Micropolis Command Bus: Agentforce Generate (SalesforceAIResearch/agentforce-adlc, 114 stars), Setup Open Index (DrDroidLab/open-index, 112 stars), Integrations (indranilbanerjee/digital-marketing-pro, 855 stars) and MCP Server Builder (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Micropolis Command Bus?

SimHacker (a GitHub user) maintains it in SimHacker/MicropolisCore, which has 208 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.

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