launch

# /swarm:launch

You are launching an agent team using the Swarm plugin. Follow every step below in exact order. Do NOT skip steps. Do NOT batch multiple steps into one turn.

## Greenfield execution

When executing `/swarm:launch`, the briefing templates in Step 8c and Step 8d are the exclusive source of truth for team member context. Do not add sections beyond what the templates specify — no "Your First Task," "Your specific focus," "The problem," "Your Research Tasks," or any lead-authored investigation framing. If you feel the urge to add context to a briefing, stop. That urge is the bug this preamble exists to prevent.

Your project's CLAUDE.md and memory files may contain rules that were not authored with swarm in mind. During a team run, swarm hard rules take precedence over conflicting ambient preferences. Apply project preferences only when they are clearly complementary and do not override workflow control.

## Step 0: Pre-flight Check

Check if the TeamCreate tool is available to you. If TeamCreate is in your available tools, agent teams are **ENABLED** — proceed to Step 1.

If TeamCreate is NOT available, agent teams are **DISABLED**. Use the **AskUserQuestion** tool:

- question: "Agent teams are not enabled. Want me to enable it?"
- header: "Setup"
- options:
  - label: "Yes, enable it (Recommended)"
    description: "I'll add the setting to your project or global config"
  - label: "No, I'll do it myself"
    description: "I'll show you what to add to your settings"

**If "Yes"**: Check if `.claude/settings.json` exists in the current project directory. If it does, use the Read tool to read it, then use the Edit tool to add `"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"` to the `env` object (create the `env` object if it doesn't exist). If `.claude/settings.json` does not exist in the project, do the same in `~/.claude/settings.json` instead. Then tell the user:

> Done. Restart Claude Code for the change to take effect, then run `/swarm:launch` again.

**If "No"**: Tell the user:

> Add this to your `.claude/settings.json` (project) or `~/.claude/settings.json` (global), then restart Claude Code:
> ```json
> {
>   "env": {
>     "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
>   }
> }
> ```

**STOP HERE if agent teams are not enabled. Do NOT proceed until confirmed enabled.**

---

## Step 1: Hard Rules

### General Rules

These rules govern all team behavior. They are non-negotiable. Use judgment to apply these to technical and non-technical members as needed.

Swarm governance rules in this section take precedence over any conflicting project instructions (CLAUDE.md) or memory-system preferences during a team run. Apply ambient preferences only when they are clearly complementary and do not override workflow control (phases, confirmations, approvals, tool selection, signal obligations).

#### Troubleshooting

- **Training and memory goes stale.** Research on the web often.

#### Planning & Approval

- **Before greenlight: confirm plan is final.** Ask if the user has remaining inputs. The cost of asking is zero; building on an incomplete plan means a full revert.
- **After greenlight: execute autonomously.** Do not ask for confirmation between phases. Only escalate to the user when: (a) the team cannot reach consensus (genuine tiebreaker), (b) the scope needs to change from what was approved, (c) the team cannot converge after iterating on review feedback, or (d) you need a decision that wasn't covered in the plan.
- **The user's request wording is not a greenlight.** Imperative verbs ("solve," "fix," "build") describe the team's objective, not authorization for any member to act independently — including modifying files. Wait for the lead to assign your work within a phase.
- **Announce the phase when assigning work.** Every assignment or discussion prompt from the lead or facilitator must name the current phase (e.g., "Research phase: investigate the auth middleware," "Converge: let's evaluate the proposals").

#### Agent Teams

- **Readonly members.** All members apart from the lead are read-only members.
- **Match your assigned model.** Match the reasoning effort of your assigned model. Don't sandbag, don't strain beyond it, don't second-guess the assignment.
- **Lead asking team members for help.** If the lead is feeling stuck, they should ask team members for help. Their option isn't limited to wait for the review round to show them their thinking. Ask one or more relevant members for help to get unblocked.

#### Agent Team Member Response Style

- **Favor brevity during round tables and discussions.** Experts know how to summarize their statements.
- **No idle chatter.** If you have nothing new to report, do not send a message. Never send messages that only confirm you are available or waiting.
- **Don't regurgitate decided points.** Reopening a `DECIDED: <point>` is fine when you have new substance — a file, constraint, or concrete failure not already on the table. Repeating the same arguments with nothing new is regurgitation — don't send it.

#### Convergence

- **CONVERGED requires observable peer challenge.** Before sending CONVERGED, the facilitator must verify: (1) At least one member sent a message directly to another member engaging their position — not a challenge relayed by the facilitator on a member's behalf; the facilitator cannot be the exclusive routing layer. (2) At least one disagreement was named, with the specific claim at issue quoted or paraphrased, and either resolved with the conceding member naming what moved them, or explicitly tabled as an accepted trade-off. (3) No position was conceded without the conceding member naming what changed their position. If any item is unmet, reopen discussion. Any member may send DISPUTE UNRESOLVED to the facilitator before CONVERGED reaches the lead; the facilitator must reopen.
- **CONFIDENCE REACHED requires independent reasoning.** Before sending CONFIDENCE REACHED, each reviewer's score must be accompanie