swarm

Tool passed security scan

Risky tool definition detected

Privilege Escalation

Shadow Persistence

Supply Chain Compromise

Risky tool definition detected

| **Rationale:** - Workers share a worktree (per native teams semantics research) - Concurrent git add/commit from multiple workers corrupts the index - Lead-only commits ensure atomic, reviewable changesets per wave **Worker instructions:** Include in every worker prompt: "Do NOT run git add, git commit, or git push. Write your result to .agents/swarm/results/<task-id>.json, then send a short signal (under 100 tokens) via your runtime channel.

Risky tool definition detected

Malicious tool definition detected

### Message (retry/follow-up) ``` send_input(id="agent-id-1", message="Validation failed: fix tests and retry") ``` ### Cleanup ``` close_agent(id="agent-id-1") ``` --- ## Mixed Mode (Council) For `--mixed` council, spawn runtime-native judges AND Codex CLI judges in parallel: ``` # Claude native team judges (via TeamCreate — see backend-claude-teams.md) Task(subagent_type="general-purpose", team_name="council-20260217-auth", name="judge-1", prompt="...", description="Judge 1") Task(subagent_typ

Tool passed security scan

Tool passed security scan

Tool passed security scan

Tool passed security scan