Stats
Actions
Tags
How this command is triggered — by the user, by Claude, or both
Slash command
/claude-auto-agents:spawnThe summary Claude sees in its command listing — used to decide when to auto-load this command
# /spawn - Launch Agent Spawn a specific type of agent to handle a task. ## Usage ## Available Agents | Agent | Tools | Model | Use Case | |-------|-------|-------|----------| | `developer` | Bash,Read,Write,Edit,Glob,Grep,Task | sonnet | Feature implementation | | `reviewer` | Bash,Read,Glob,Grep | sonnet | Code review (read-only) | | `fixer` | Bash,Read,Write,Edit,Glob,Grep | sonnet | Fix issues/failures | | `orchestrator` | All + Task | opus | Autonomous control | | `explorer` | Read,Glob,Grep | haiku | Codebase exploration | | `pr-shepherd` | All + Task | sonnet | PR management | ...
Spawn a specific type of agent to handle a task.
/spawn developer "implement user authentication"
/spawn reviewer # Review current changes
/spawn fixer "fix failing test in auth.test.ts"
/spawn explorer "find where database connections are created"
| Agent | Tools | Model | Use Case |
|---|---|---|---|
developer | Bash,Read,Write,Edit,Glob,Grep,Task | sonnet | Feature implementation |
reviewer | Bash,Read,Glob,Grep | sonnet | Code review (read-only) |
fixer | Bash,Read,Write,Edit,Glob,Grep | sonnet | Fix issues/failures |
orchestrator | All + Task | opus | Autonomous control |
explorer | Read,Glob,Grep | haiku | Codebase exploration |
pr-shepherd | All + Task | sonnet | PR management |
conflict-resolver | Bash,Read,Write,Edit | sonnet | Merge conflicts |
/spawn developer "add password reset functionality with email verification"
/spawn reviewer "review the authentication changes"
/spawn fixer "fix the race condition in user session handling"
/spawn explorer "map the database schema and relationships"
/spawn pr-shepherd "create PR for current branch and monitor CI"
developer for new featuresfixer for bugs and failuresexplorer for read-only analysisnpx claudepluginhub hanibalsk/claude-marketplace --plugin claude-auto-agents/codexDelegates coding tasks to OpenAI Codex CLI for autonomous execution via natural language prompts, handling code refactoring, testing, bug fixes, explanations, features, and reviews.
/sc-workBuilds, fixes, or modifies code from a natural language description of the task, delegating to specialized agents for research, analysis, architecture, and review.
/implementExecutes a single task through implementation, quality gates, and PR creation. Accepts plan documents, GitHub issues, or free-form descriptions.
/prExecutes full PR workflow: think strategically, implement and test code, push detailed PR, auto-handle feedback and fixes, then review code quality.
/spawnOrchestrates complex multi-domain tasks: decomposes into hierarchical subtasks, coordinates execution with sequential/parallel/adaptive strategies, monitors dependencies, and delivers integrated results summary.
/spawnDecomposes complex tasks into subtasks with dependency mapping, executes sequentially or in parallel, monitors progress, and validates results using TodoWrite and file tools.