Claude Agents Coordination

Claude Code Agents Coordination

Production-grade multi-agent coordination system with tiered delegation, institutional memory, and explicit tech-debt tracking.

This repository provides reusable configuration layers for Claude Code that enable sophisticated agent orchestration across projects—from solo development to enterprise-scale workflows.

What This Solves

Three critical problems in Claude Code agent usage:

1. Context Amnesia: Agents forget prior work within 15-20 minutes
2. Coordination Chaos: Multiple agents overwrite each other's work
3. Delegation Limits: Manual oversight required for every decision

Solution: A tiered delegation architecture with persistent memory (registry + tech-debt tracking) that extends productive context windows to 2+ hours while enabling the Main Agent to consistently apply documented engineering criteria.

Core Architecture

Tiered Agent System

Dual-Registry Model

_registry.md — What was done
- Tracks completed work, deliverables, and outcomes
- Main agent reads this for context before starting new tasks
- Updated after every significant task completion

_tech-debt.md — What was deferred
- Explicit tracking of shortcuts, workarounds, and deferred improvements
- Links each debt item to its source (commit, report, or incident)
- Prevents silent degradation of code quality

4-Step Coordination Protocol

1. Registry Check → Main agent reads prior work
2. Context Injection → Relevant context distributed to specialized agents
3. Sequencing → Sequential or parallel execution based on dependencies
4. Verification → Quality gates ensure standards are met

Quick Start

1. Install User-Level Configuration

This installs:
- Tiered agent set (orchestrators + specialists + on-demand experts)
- Standard workflows (/review-full, /ci, /debt,…