d3x293/code-crew

# Agent Manager - Custom Agent Creation

Manages project-specific custom agents that extend the built-in CodeCrew team.

## When to Activate

- User runs `/crew agent create|list|remove`

## Storage

Custom agents are stored in `.claude/crew-agents/` (project-local directory, NOT in the plugin's `agents/` directory). This keeps custom agents project-specific and avoids conflicts with plugin updates.

## Subcommands

# Codebase Index - 3-Layer Memory Optimizer

Build and maintain a progressive disclosure index that prevents agents from reading entire files when they only need a function signature or a specific line range.

## When to Activate

- During `/crew init` (full build)
- During `/crew reindex` (full rebuild)
- When an agent needs to find code but the index exists (consult mode)
- After file edits (incremental update mode via index-updater skill)

## Three-Layer Architecture

### Layer 1 - Compact Index (`.claude/crew-index.json`, ~2-5KB)

# Crew Config - User Configuration Manager

Reads and writes `.claude/crew-config.json` to customize CodeCrew behavior.

## When to Activate

- User runs `/crew config show|set|reset`
- Other skills check for config overrides at startup

## Config File

**Location**: `.claude/crew-config.json` (created on first `set` command)

**Default values** (used when file doesn't exist):

# Crew Init - Project Analysis & Team Setup

Full project initialization that transforms any codebase into a CodeCrew workspace with indexed code, profiled architecture, and a configured agent team.

## When to Activate

- User runs `/crew init`
- User runs `/crew` with `init` argument
- First time using CodeCrew in a project

## Initialization Pipeline

### Phase 1: Project Discovery

# Execution Orchestrator - Smart Hybrid Dispatch

Executes the task plan generated by the task-router by spawning agents with the right models, collecting results, and coordinating integration.

## When to Activate

- Called by task-router after generating an execution plan
- When re-executing after a conflict resolution

## Core Principle

**Each agent is self-contained.** When spawning an agent via the Agent tool:
- Include ALL context the agent needs in its prompt
- Include the Index-First Protocol

# Index Updater - Incremental Index Maintenance

Keeps `.claude/crew-index.json` and `.claude/crew-symbols.json` up-to-date after code changes without rebuilding the entire index.

## When to Activate

- After any agent makes file edits (triggered by afterFileEdit hook or agent self-reporting)
- When an agent notices the index is stale (hash mismatch)
- Manually via `/crew reindex` for full rebuild

## Incremental Update Process

### Step 1: Identify changed files
The agent that made changes should report which files were modified. Alternatively, check file hashes:

# Lite Router - Task Router (No Opus)

Performs task classification and routing WITHOUT spawning the CEO (Opus) agent. All classification happens in the current session context (Sonnet-level), and agents are dispatched using only Sonnet and Haiku tiers.

## When to Activate

- User runs `/crew lite "description"`
- User runs `/crew task --lite "description"` (backward compatible)

## Prerequisites

These files MUST exist (run `/crew init` first):
- `.claude/crew-profile.md` — project context
- `.claude/crew-team.json` — agent configuration

# Skill Injector - Smart Skill Selection

Maps task signals to skills from the everything-claude-code catalog and injects only the relevant ones into each agent's prompt. Prevents context bloat by being selective.

## When to Activate

- During task routing (called by task-router skill)
- When an agent needs additional skill guidance mid-task

## Skill Selection Algorithm

### Input
- Task classification (type + complexity) from task-router
- Agent role being dispatched

# Task History - Execution History Viewer

Displays past task executions with filtering and cost analysis.

## When to Activate

- User runs `/crew history [flags]`

## Prerequisites

- `.claude/crew-history.json` must exist (created after first task execution)
- If missing: display "No history yet. Run /crew task to start."

## Process

# Task Rollback - Undo Last Task

Reverts file changes made by the most recent `/crew task` execution using git.

## When to Activate

- User runs `/crew rollback`

## Prerequisites

- `.claude/crew-history.json` must exist with at least one entry
- Project must be a git repository
- The `gitRefBefore` field should be present in the last history entry (captured by execution-orchestrator before task execution)

# Task Router - CEO's Decision Engine

The brain of CodeCrew. When a task comes in, this skill classifies it, picks the right agents, decides the execution strategy, and kicks off the work.

## When to Activate

- User runs `/crew task "description"`
- CEO agent needs to route a subtask

## Prerequisites

These files MUST exist (run `/crew init` first):
- `.claude/crew-profile.md` — project context
- `.claude/crew-team.json` — agent configuration

# Team Status - Crew Dashboard

Shows the current state of CodeCrew for the active project.

## When to Activate

- User runs `/crew status`

## Status Report Sections

### 1. Project Overview

Read `.claude/crew-profile.md` and display:
```