16 Specialized Agents
Architects, testers, reviewers, SREs, and security auditors — a team that self-organizes around your work.
Summon is a drop-in framework for Claude Code. It installs agent definitions, slash commands, and process docs into your project. No runtime. No dependencies. Just markdown.
Agent marketplaces offer hundreds of AI agents. Install them, and you get… a pile of tools. No one decides what to build first. No one catches the bad architecture before you’ve built on top of it.
You don’t need more agents. You need a team that works like a team.
16 Specialized Agents
Architects, testers, reviewers, SREs, and security auditors — a team that self-organizes around your work.
23 Slash Commands
From /kickoff to /handoff — every phase of development has a command that drives it.
7-Phase Methodology
Not just agents — a complete workflow with enforced gates, reviews, and sprint boundaries.
Real Accountability
Security veto. Test coverage veto. 15-item done gate. The team says no when it should.
You’re the product owner and the final decision-maker. The team handles the engineering discipline.
npx summon-team my-projectcd my-project# Open in Claude Code, then run /quickstartTwo commands to install. One command to launch your team.
| Agent Marketplaces | Summon | |
|---|---|---|
| Agents | 100-1000+ independent tools | 16 agents that know each other |
| Process | None | 7-phase methodology with gates |
| Architecture | No guardrails | Mandatory ADRs before code |
| Testing | Optional | TDD enforced — tests before code |
| Code Review | Single-pass or none | Three parallel lenses |
| Sprint Management | None | Velocity tracking, retros, handoffs |
| Accountability | Agents don’t say no | Veto authority on security + tests |
npx summon-team my-project