Agents Manager

# Agents Manager

Manage all Clawdbot agents centrally: discover available agents, profile their capabilities, define routing hierarchy (who can assign to whom, who reports to whom), and intelligently route new tasks through the escalation chain.

## 🤖 For Agents

### System Prompt (Copy-Paste)
Give this prompt to any agent to teach them this skill:
> "You have access to the `agents-manager` skill. Use it to discover peers (`scan_agents`), check permissions (`can_assign.js`), and route tasks. Always follow the Handshake Protocol: Check `requires_approval` before assigning. If true, ask me first."

### Core Rules
1. **Discovery:** Always check `scan_agents.js` before assuming an agent exists.
2. **Permission:** Never assign a task without checking `can_assign.js` or `agent-registry.md`.
3. **protocol:**
   - IF `requires_approval` is FALSE -> Assign directly.
   - IF `requires_approval` is TRUE -> Ask supervisor (Human or Agent).

## 👤 For Humans

### Quick Start
| Goal | Command |
|------|---------|
| **Setup** | `node scripts/setup_wizard.js` (Run this first!) |
| **List** | `node scripts/scan_agents.js` |
| **Health** | `node scripts/health_check.js` |
| **Stats** | `node scripts/log_analyzer.js` |

### 1. Agent Discovery & Profiling
List and profile all agents to understand their capabilities and routing configuration.

```bash
# List all agents
node {baseDir}/scripts/scan_agents.js

# Profile specific agent
node {baseDir}/scripts/generate_card.js <agent_id>
```

### 2. Validation & Health
Ensure your agent ecosystem is healthy and valid.

```bash
# Validate registry integrity
node {baseDir}/scripts/validate_registry.js

# Check permissions (Agent A -> Agent B)
node {baseDir}/scripts/can_assign.js <source_id> <target_id>

# Visualize hierarchy
node {baseDir}/scripts/visualize_agents.js
```

### 3. Task Routing & Escalation
Define how tasks flow between agents using `references/task-routing-rules.md`.

- **Direct:** Agent → Agent (if `can_assign_to` allows)
- **...

# Agents Manager

🕵️ Manage Clawdbot agents: discover, profile, track capabilities, define routing hierarchy, and assign tasks.

## Features

- ✅ **Central Registry**: Standardized `agent-registry.md` to track all agents.
- ✅ **Strict Hierarchy**: Define `reports_to` and `can_assign_to` rules.
- ✅ **Approval Protocol**: Handshake mechanism for secure task delegation.
- ✅ **Agent Cards**: Standardized JSON capability cards for discovery.
- ✅ **Visualization**: Generate Mermaid.js graphs of your agent web.
- ✅ **Health & Stats**: Monitor agent uptime `health_check.js` and performance `log_analyzer.js`.
- ✅ **Zero-Config**: Use `setup_wizard.js` to get started in seconds.

## Usage

### 1. Zero-Config Setup ⚡
The easiest way to start:

```bash
node scripts/setup_wizard.js
```

### 2. Discovery
Find out what agents are available and what they can do.

```bash
node scripts/scan_agents.js
```

### 2. Validation
Make sure your registry is valid and hierarchy is sound.

```bash
node scripts/validate_registry.js
```

### 3. Hierarchy Check
Check if `Agent A` allows tasks from `Agent B`.

```bash
node scripts/can_assign.js agentA agentB
```

## Configuration

Edit `references/agent-registry.md` to configure your agents.
See `references/agent-profile-schema.md` for the full schema options including:
- `requires_approval`: Toggle manual approval.
- `auto_accept_from`: Whitelist trusted agents.

## Visualization

Generate a visual graph of your agent hierarchy:

```bash
node scripts/visualize_agents.js
```