Help us improve
Share bugs, ideas, or general feedback.
From development-planning
Refines development plans through multi-round discussions among 3-10 specialized agents selected by domain like frontend, backend, security. Builds consensus on recommendations and trade-offs.
npx claudepluginhub uniswap/ai-toolkit --plugin development-planningHow this skill is triggered — by the user, by Claude, or both
Slash command
/development-planning:plan-swarmopusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Refine plans through collaborative multi-agent expert discussion.
Performs multi-agent review of implementation plans using PoLL consensus protocol. Independent expert panels surface diverse issues and blind spots before coding.
Spawns 2-3 agent roles (reviewer, fixer, architect) to debate a topic from different expertise angles. Helps explore tradeoffs or get multiple perspectives on a question.
Convenes parallel role-specialized agents (principal engineer, platform, integration, test, QA, security) to debate cross-domain technical decisions or audit codebases in real time. The invoking Claude acts as CEO, routing peer DMs and producing a one-page decision log.
Share bugs, ideas, or general feedback.
Refine plans through collaborative multi-agent expert discussion.
⚠️ Cost Warning: This skill uses the Opus model and spawns 3-10 agents for multi-round discussions. A typical plan-swarm session consumes 5-20x more tokens than a standard skill invocation. Consider using
review-planfor simpler validation needs.
| Plan Complexity | Agents |
|---|---|
| Simple | 3-4 |
| Medium | 5-7 |
| Complex | 8-10 |
Generates refinement document with:
Agents are encouraged to: