Spawning Plan

Spawning Plan

Design the optimal agent team for the task. Performant, precise, minimal.

> Note: This skill requires Claude Code with Agent Teams support (TeamCreate, TaskCreate, SendMessage tools).

Task: $ARGUMENTS

Step 1: Context Gathering (Silent -- no user interaction)

A) Read environment:

• CLAUDE.md -- workflow rules, conventions, constraints
• Project manifests -- package.json, pyproject.toml, Cargo.toml, go.mod, etc.
• Directory structure -- src/, app/, packages/, test dirs, monorepo indicators

B) Inventory existing agents:

• Scan ~/.claude/agents/*.md -- reuse matching agents instead of creating duplicates

C) Analyze task complexity:

• Work type: research, implementation, review, debugging, refactoring
• Scope: single-layer vs cross-layer
• Parallelism: can work split into independent streams?
• Complexity -> team size: simple (2 agents), medium (3-4), complex cross-cutting (5-6, max 8)

Step 2: Ask Team Questions (AskUserQuestion Tool)

Ask 3-5 questions based on Step 1 findings. Not all apply every time -- pick what matters.

1. Team Composition -- "For this [work type] on [stack], I'm thinking [N] agents: [role list]. What would you change?"

Options: Perfect / Add role / Remove role / Different approach

1. Coordination -- "How should agents work together?"

Options: Independent (no messaging) / Team (peer messaging) / Hub-spoke (lead coordinates)

1. Dependencies -- "Work order?"

Options: All parallel / Sequential (A->B->C) / Mixed

1. Models -- "Model allocation: opus (research), sonnet (implementation), haiku (scanning). Adjust?"

Options: As suggested / All opus / All sonnet / Custom

1. Agent Reuse (only if matching agents found in Step 1B) -- "Found existing [agent-name] that handles [capability]. Reuse it?"

Options: Reuse / Create fresh / Both

Step 3: Output & Approval

Present clean TEAM PLAN:

## TEAM PLAN

Task: [description]
Pattern: [independent | team | hub-spoke]
Work Order: [parallel | sequential | mixed]
Agents: [count]

### Teammates

- Teammate 1: [Name] ([Role])
  Description: [1-2 line expertise and specialization]
  Model: [opus|sonnet|haiku]
  Type: [general-purpose | feature-dev:code-X | reuse ~/.claude/agents/X.md]
  Responsible for: [specific deliverable]
  Depends on: [-- | Teammate N]

- Teammate 2: [Name] ([Role])
  Description: [1-2 line expertise and specialization]
  Model: [opus|sonnet|haiku]
  Type: [general-purpose | feature-dev:code-X]
  Responsible for: [specific deliverable]
  Depends on: [-- | Teammate N]

- ...

### Research (injected into agent prompts)
- [key finding or best practice 1]
- [key finding or best practice 2]

Final Approval (AskUserQuestion Tool)

"Launch this team?"
- Deploy & Simplify -- spawn agents, then auto-run /simplify on all changes
- Deploy & Save -- spawn agents and save as reusable skill
- Deploy Once -- spawn agents, one-time
- Adjust -- change something (iterate plan)
- Cancel -- abort

Deploy & Simplify -> spawn agents, wait for all to complete, then automatically run /simplify to review and fix code quality, reuse, and efficiency issues across all agent output. Best for implementation tasks.

Deploy & Save -> save team as skill at ~/.claude/skills//SKILL.md for future use via / [task]. Saved skill skips planning, bakes in agent definitions, uses $ARGUMENTS for task input.

Adjust -> ask what to change -> regenerate plan -> ask again. Loop until approved.

Deploy Once -> spawn immediately, no save.

Cancel -> stop.

Spawning Execution

Based on chosen pattern:

• Independent: parallel Task tool calls, one per agent
• Team: TeamCreate -> TaskCreate per agent -> Task tool with team_name -> TaskUpdate for dependencies
• Hub-spoke: TeamCreate with lead agent (opus) that delegates via SendMessage

For detailed agent prompt structure, see [references/agent-prompts.md](references/agent-prompts.md).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: citedy
• Source: citedy/skills
• License: MIT

Install and usage instructions live in the source repository linked above.