Agent skill · AI & Agents

gobby-agents

This skill should be used when the user asks to "/gobby-agents", "spawn agent", "start agent", "list agents". Manage subagent spawning - start, cancel, list, and check results of autonomous agents.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill gobby-agents --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/agent/gobby-agents/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# /gobby-agents - Agent Management Skill This skill manages subagent spawning via the gobby-agents MCP server. Parse the user's input to determine which subcommand to execute. ## Session Context **IMPORTANT**: Use the `session_id` from your SessionStart hook context for agent calls. Look for it in your system context: ``` session_id: fd59c8fc-... ``` ## Subcommands ### `/gobby-agents start <prompt>` - Start a new agent Call `gobby-agents.start_agent` with: - `prompt`: (required) Task description for the agent - `mode`: Execution mode - "terminal" (default), "headless", or "embedded" - `workflow`: Optional workflow to activate (plan-execute, test-driven, etc.) - `agent`: Named agent definition to use (e.g., "validation-runner") - `session_context`: Context injection sources - `task`: Task ID to associate with the agent - `terminal`: Terminal type for terminal mode - `provider`: LLM provider override - `model`: Model override - `worktree_id`: Run in specific worktree - `timeout`: Max runtime - `max_turns`: Max conversation turns - `parent_session_id`: Parent session for tracking Modes: - `terminal` - Opens in new terminal window (default) - `headless` - Runs in background, no UI - `e

What's inside
Steps it walks through
  1. Session Context
  2. Subcommands
  3. /gobby-agents start <prompt> - Start a new agent
  4. /gobby-agents result <run-id> - Get agent result
  5. /gobby-agents cancel <run-id> - Cancel a running agent
  6. /gobby-agents list - List agent runs for a session
  7. /gobby-agents running - List currently running agents
  8. /gobby-agents can-spawn - Check if agent can be spawned
  9. /gobby-agents stats - Get running agent statistics
  10. Response Format
  11. Agent Safety
  12. Error Handling
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the gobby-agents skill do?

This skill should be used when the user asks to "/gobby-agents", "spawn agent", "start agent", "list agents". Manage subagent spawning - start, cancel, list, and check results of autonomous agents.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill gobby-agents --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going