space-agents

Q: How to install space-agents?

Create the agents directory: mkdir -p .claude/agents. Then add the config to .claude/agents/space-agents.md. Finally, @space-agents in Claude Code.

Q: What is space-agents best for?

space-agents is categorized under General. It covers: agent.

New

3Community RegistryGeneralby Fraser Brown

Multi-agent orchestration system for Claude Code. HOUSTON coordinates Voyages, Missions, and Objectives while fresh Pods execute work autonomously.

First seen 6/7/2026

View Source

Summary

Space Agents is a multi-agent orchestration system for Claude Code that coordinates complex workflows through a central HOUSTON controller, enabling autonomous execution of tasks by fresh Pods.

It uses Beads for persistent context tracking across sessions and supports solo, orchestrated, or background automation modes, making it ideal for large-scale codebase exploration, debugging, and planning.

Overview

code

███████╗██████╗  █████╗  ██████╗███████╗
██╔════╝██╔══██╗██╔══██╗██╔════╝██╔════╝
███████╗██████╔╝███████║██║     █████╗
╚════██║██╔═══╝ ██╔══██║██║     ██╔══╝
███████║██║     ██║  ██║╚██████╗███████╗
╚══════╝╚═╝     ╚═╝  ╚═╝ ╚═════╝╚══════╝
         █████╗  ██████╗ ███████╗███╗   ██╗████████╗███████╗
        ██╔══██╗██╔════╝ ██╔════╝████╗  ██║╚══██╔══╝██╔════╝
        ███████║██║  ███╗█████╗  ██╔██╗ ██║   ██║   ███████╗
        ██╔══██║██║   ██║██╔══╝  ██║╚██╗██║   ██║   ╚════██║
        ██║  ██║╚██████╔╝███████╗██║ ╚████║   ██║   ███████║
        ╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚═╝  ╚═══╝   ╚═╝   ╚══════╝

Agent orchestration plugin for Claude Code, powered by Beads and the Ralph loop.

Features

•Multi-session persistence: Beads tracks issues, dependencies, and context across sessions
•Structured exploration: Brainstorm ideas, create plans, review code, debug issues
•Agent orchestration: Solo (direct), Orchestrated (agents per task), or Ralph loop (background automation)
•Session logging: CAPCOM log preserves decisions and progress for future sessions

Prerequisites

•Beads CLI (npm install -g beads-cli)
•Optional: mprocs (npm install -g mprocs) for watching Ralph loop live

Install

1. Add the plugin (in Claude Code):

code

/plugin marketplace add thebrownproject/space-agents
/plugin install space-agents@thebrownproject-space-agents

2. Initialize in your project:

code

/install

This creates the .space-agents/ directory structure and initializes Beads for issue tracking. Run once per project.

Workflow

code

/launch → /exploration → /mission → /land

Command	Purpose
`/launch`	Start session, see project status
`/exploration`	Brainstorm, plan, review, or debug
`/mission`	Execute work from Beads
`/land`	End session, save context to CAPCOM

Exploration Modes

Mode	Output
`brainstorm`	Ideas and analysis in `exploration/ideas/`
`plan`	Implementation plans in `exploration/planned/`
`review`	Code review findings as Beads
`debug`	Investigation results as Beads

Mission Modes

Mode	Best for
`solo`	Small work (1-3 tasks). HOUSTON executes directly
`orchestrated`	Medium work (4-10 tasks). Agent per task
`ralph`	Large work (10+ tasks). Background automation

Multi-Agent Execution

In orchestrated and ralph modes, each task is executed by a 3-agent crew:

code

Pathfinder → Builder → Inspector

Agent	Role
Pathfinder	Explores codebase, gathers context, identifies patterns and risks
Builder	Implements the task using TDD approach
Inspector	Two-pass review: requirements verification, then quality/patterns/security

The Ralph loop spawns these as Pods with fresh context each iteration, looping until all tasks complete or a blocker halts execution. When issues are found, bugs are inserted into Beads as blockers; Ralph resolves these before continuing to the next task.

Install & Usage

Create the agents directory

mkdir -p .claude/agents

Save the agent file

Add the configuration to .claude/agents/space-agents.md

Invoke with @agent-name

@space-agents

Use Cases

Orchestrate multiple agents to brainstorm ideas, create plans, and review code across a large codebase.

Automate background debugging sessions that run independently while you continue other work.

Maintain persistent context across Claude Code sessions for long-running projects with many dependencies.

Coordinate a structured exploration of a new codebase, generating reports and summaries from multiple perspectives.

Run a Ralph loop to continuously monitor and fix issues in a repository without manual intervention.

Log all decisions and progress to a CAPCOM log for later review or handoff to another developer.

Usage Examples

/space-agents orchestrate a mission to refactor the authentication module, assigning one agent to analyze dependencies and another to propose changes.

Start a Ralph loop to automatically fix linting errors in the src/ directory and commit fixes.

Use space-agents to brainstorm and create a plan for adding a new feature, logging all decisions to the CAPCOM log.

View source on GitHub

agent

Security Audits

LicenseUnknownSourceWarnRepositoryPass

Frequently Asked Questions

What is space-agents?

Space Agents is a multi-agent orchestration system for Claude Code that coordinates complex workflows through a central HOUSTON controller, enabling autonomous execution of tasks by fresh Pods. It uses Beads for persistent context tracking across sessions and supports solo, orchestrated, or background automation modes, making it ideal for large-scale codebase exploration, debugging, and planning.

How to install space-agents?

To install space-agents: create the agents directory (mkdir -p .claude/agents), then add the config to .claude/agents/space-agents.md. Finally, @space-agents in Claude Code.

What is space-agents best for?

space-agents is a agent categorized under General. It is designed for: agent. Created by Fraser Brown.

What can I use space-agents for?

space-agents is useful for: Orchestrate multiple agents to brainstorm ideas, create plans, and review code across a large codebase.; Automate background debugging sessions that run independently while you continue other work.; Maintain persistent context across Claude Code sessions for long-running projects with many dependencies.; Coordinate a structured exploration of a new codebase, generating reports and summaries from multiple perspectives.; Run a Ralph loop to continuously monitor and fix issues in a repository without manual intervention.; Log all decisions and progress to a CAPCOM log for later review or handoff to another developer..