# Agent Protocols

This directory contains **protocol runbooks** — structured, human-readable procedural documents that kaizen-agentic agents reference during structured assessments or remediation work.

Protocols are distinct from agent prompts:
- **Agent prompts** (`agents/agent-*.md`) shape AI behaviour
- **Protocols** (`agents/protocols/<agent>/<slug>.md`) are procedural checklists for humans and agents to execute

See [ADR-003](../../docs/adr/ADR-003-protocols-artifact-convention.md) for the full convention.

## Structure

```
agents/protocols/
  <agent-name>/
    <slug>.md    ← one file per protocol
```

## Available Protocols

| Agent | Protocol | Description |
|-------|----------|-------------|
| sys-medic | [k3s-node-health-assessment](sys-medic/k3s-node-health-assessment.md) | Structured k3s node health check covering kubelet, pods, resources, networking, and storage |

## Usage

**From the CLI:**

```bash
kaizen-agentic protocols list                     # List all protocols
kaizen-agentic protocols list sys-medic           # List sys-medic protocols
kaizen-agentic protocols show sys-medic k3s-node-health-assessment
```

**From an agent session:**

When an agent references a protocol, it will say something like:
> *"Use the k3s-node-health-assessment protocol at `agents/protocols/sys-medic/k3s-node-health-assessment.md` for this assessment."*

Protocols can also be read and executed directly without an AI agent.