/spawn
Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session.
One skill from claude-skills.
shell
$ npx -y skills add alirezarezvani/claude-skills --skill spawn --agent claude-codeInstalls just this skill. Get the whole plugin for auto-invocation.
How it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/spawn
Context preview
The summary Claude sees to decide when to auto-load this skill.
Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session.
Stats
Stars23,060
Forks3,139
LanguagePython
LicenseMIT
Ships with claude-skills
SKILL.md
spawn.SKILL.md
--- name: "spawn" description: "Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session." command: /hub:spawn --- # /hub:spawn โ Launch Parallel Agents Spawn N subagents that work on the same task in parallel, each in an isolated git worktree. ## Usage ``` /hub:spawn # Spawn agents for the latest session /hub:spawn 20260317-143022 # Spawn agents for a specific session /hub:spawn --template optimizer # Use optimizer template for dispatch prompts /hub:spawn --template refactorer # Use refactorer template ``` ## Templates When `--template <name>` is provided, use the dispatch prompt from `../agenthub/references/agent-templates.md` instead of the default prompt below. Available templates: | Template | Pattern | Use Case | |----------|---------|----------| | `optimizer` | Edit โ eval โ keep/discard โ repeat x10 | Performance, latency, size reduction | | `refactorer` | Restructure โ test โ iterate until green | Code quality, tech debt | | `test-writer` | Write tests โ measure coverage โ repeat | Test coverage gaps | | `bug-fixer` | Reproduce โ diagnose โ fix โ verify | Bug fix with competing approaches |
