Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The English summary is being prepared. Showing the original description.
Configure and synchronize multi-harness subagents (Claude Code, Google Antigravity, OpenCode, ChatGPT Codex CLI) with optional per-harness model overrides and single source of truth in .aos/pipeline.json.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Manages and synchronizes autonomous subagent roles across all four supported execution harnesses:
.claude/agents/*.md)~/.gemini/config/agents/*.json).opencode/agents/*.md).codex/agents/*.toml & .codex/agents/*.md)Single Source of Truth: .aos/pipeline.json (compatible with AO Orchestrator Pipeline Wizard).
AOS pins no model. Agents inherit the session model on every harness. A model is written only when .aos/pipeline.json sets one for that role and harness, as a free-form string passed through verbatim. Shape, per-harness examples and the aos-doctor format check: docs/agent-models.md.
node skills/global_config/subagent-setup/scripts/setup-subagents.mjs --show
node skills/global_config/subagent-setup/scripts/setup-subagents.mjs --init-default
# Example: Set Reviewer to an external CLI harness with a lightweight model
node skills/global_config/subagent-setup/scripts/setup-subagents.mjs \
--set-role reviewer --harness codex --model <model-id>
# Example: Set Shipping to OpenCode with Free Tier
node skills/global_config/subagent-setup/scripts/setup-subagents.mjs \
--set-role godmode_shipping --harness opencode --model <model-id>
# Example: Enable or Disable a Role
node skills/global_config/subagent-setup/scripts/setup-subagents.mjs --set-role godmode_media_eventtech --enable
# Role keys are the agent slugs with "-" as "_"; the old short keys (shipping, ui_ux, ...) are still accepted and rewritten.
node skills/global_config/subagent-setup/scripts/setup-subagents.mjs --sync
aos-project-init & AO Orchestrator.aos/pipeline.json.aos-project-init: Offers subagent configuration during project interview, with no model pinned by default.The script imports the AOS installer.js module. In a repo checkout it finds it by relative path. An installed copy (~/.agents/skills/subagent-setup/scripts/) has no repo around it: set AOS_HOME to the AOS package folder (the one that contains installer.js), or install @hybridlabor-api/aos globally. Without either it exits with code 2 and lists the paths it tried.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The English summary is being prepared. Showing the original description.
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
The English summary is being prepared. Showing the original description.
Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.
The English summary is being prepared. Showing the original description.
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
The English summary is being prepared. Showing the original description.
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
The English summary is being prepared. Showing the original description.
agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.
The English summary is being prepared. Showing the original description.