holix-subagents
SolidFull Holix sub-agent lifecycle: spawn, monitor, collect results, answer ask_user questions, approve tool confirmations, and delegate to external CLIs (holix launch). Use when the user asks about subagents, /subagent-spawn, delegate_to_subagent, background workers, sub-agent questions, /subagent-reply, holix launch + coder, or running tasks without blocking the main chat. Invoke via /holix-subagents.
Install
Quality Score: 82/100
Skill Content
Details
- Author
- javded-itres
- Repository
- javded-itres/Holix
- Created
- 1 months ago
- Last Updated
- today
- Language
- Python
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
subagent
Spawn and manage autonomous background agents for parallel work
sub-agents
Execute external CLI AIs as isolated sub-agents for task delegation, parallel processing, and context separation. Use when delegating complex multi-step tasks, running parallel investigations, needing fresh context without current conversation history, or leveraging specialized agent definitions. Returns structured JSON with agent output, exit code, and execution status.
summon
Summon another AI CLI — Claude, Codex, Cursor, Gemini, or Antigravity — as a sub-agent to run a task, in parallel when useful. Use whenever the user names an agent or sub-agent to run, asks to delegate work to another AI or a specific model, wants a second opinion or a cross-vendor code review, wants to fan several models out over a task, or references an agent definition. One dispatcher over five backends returns a structured JSON result (status, parsed report, token cost, the model actually served) and supports session resume, isolated git worktrees, background and manifest-driven swarms, JSON-schema-validated output, model discovery, and per-agent model/permission config. Formerly named "sub-agents".