메뉴
Initialize a multi-agent swarm with anti-drift configuration
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Orchestrator for all 7 Laws of AI Agent Discipline. Walks an agent-emitted recommendation list top-to-bottom under the 7 Laws — restate, route per item, verify before advancing, reflect at the end, close with the mandatory three-section block. Standalone with inline fallbacks; trigger phrases are matched by the companion hook, not enumerated here.
Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline. Reviews the current diff for over-engineering (code that could reuse an existing file, a stdlib or native feature, or fewer lines) and reports trim findings without touching code, so 'it works' is never mistaken for 'it is the minimum that works'.
Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline at the deploy seam. A merge into a branch that auto-deploys is not "done" until the deploy provider reports the merged commit SHA running and a healthcheck endpoint returns 200. Companion to the vendored `finishing-a-development-branch` skill — does not replace it, runs after it for projects on Railway, Cloudflare Workers, Vercel, Netlify, Fly.io, or any other auto-deploy target.
Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.
Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Establishes git ground truth — branch, status, stashes, worktrees, ahead/behind — before any mutation, halts on protected or destructive operations, then carries the known-good state through to a landed PR: stage by filename, commit one concern, push the feature branch, verify the push landed, open the PR, and after the PR merges fast-forward the default branch and check it out.
Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline. A comprehensive verification system for agent coding sessions covering build, types, lint, tests, security, and diff with a PASS/FAIL report.
SOC 직업 분류 기준
| name | swarm-init |
| description | Initialize a multi-agent swarm with anti-drift configuration |
| argument-hint | [--topology hierarchical|mesh|ring] |
| allowed-tools | Bash(npx *) mcp__claude-flow__swarm_init mcp__claude-flow__swarm_status Agent |
Initialize a hierarchical swarm for coordinated multi-agent work.
Via MCP: mcp__claude-flow__swarm_init({ topology: "hierarchical", maxAgents: 8, strategy: "specialized" })
Or via CLI:
npx @claude-flow/cli@latest swarm init --topology hierarchical --max-agents 8 --strategy specialized
Then create a Claude Code team via TeamCreate and spawn agents using the Agent tool with isolation: "worktree" for git-safe parallel work. Use SendMessage for inter-agent coordination.
For larger teams (10+), use hierarchical-mesh topology:
npx @claude-flow/cli@latest swarm init --topology hierarchical-mesh --max-agents 15 --strategy specialized