Agent Ops Playbook Pro — MCP Server

Production operations prompts for AI agents. Available via Model Context Protocol.

By ClawGear — the skill layer for autonomous AI agents.

What this does

Exposes 7 production-grade prompts that agents can call during operations:

| Prompt | What it gives you | |--------|-------------------| | session-startup | Mandatory startup protocol — what to read, in what order | | memory-sync-check | Run after every work block — ensures state is written before exiting | | sub-agent-decision | When to spawn a sub-agent vs handle work in the main session | | safety-boundaries | What agents can do freely vs what requires explicit approval | | memory-architecture | The three-layer memory system (MEMORY.md / daily notes / heartbeat state) | | heartbeat-protocol | Full heartbeat loop for autonomous scheduled agents | | blocker-discipline | How to name, track, and escalate blockers without going silent |

Install

{
  "mcpServers": {
    "agent-ops": {
      "command": "npx",
      "args": ["-y", "agent-ops-playbook-pro"]
    }
  }
}

Usage

Once configured, your AI assistant can call any prompt by name:

• session-startup — wire into your agent's startup context
• memory-sync-check — run after any significant work block
• sub-agent-decision — when deciding whether to delegate

These prompts are extracted from Agent Ops Playbook Pro — a production guide built from running a fully autonomous AI company (ClawGear) over several months.

Full version

The full Agent Ops Playbook Pro includes:

• Memory sync validator script + pre-commit hooks
• Multi-project isolation scaffolding
• Real failure post-mortems with root cause analysis
• Copy-paste starter templates (AGENTS.md, SOUL.md, USER.md, HEARTBEAT.md)
• Extended guidance on cron vs event-triggered heartbeat patterns

Available on ClawMart ($29).

Free skills on SkillDepot

• Agent Ops Playbook Pro
• ClawGear Persona
• Sub-Agent Orchestrator
• GitHub PR Gate
• CDP Browser Automation

License

MIT