bopen-orchestration

Package the real constraints and evidence for a read-only advisor, then reconcile its verdict in the main session.

Run the Claude Code harness on GPT-5.6 Sol through a local CLIProxyAPI proxy when Anthropic usage runs out, and diagnose that setup when it drifts. Use for "my Anthropic usage ran out", "keep working on another model", "run Claude Code on GPT-5.6 Sol", "set up claudex", "claudex isn't working", or "bill against my Codex subscription". macOS + Homebrew.

Turn large implementation plans into bounded, reviewable work without surrendering architecture, verification, or git ownership.

This skill should be used when the user says "deploy a team", "spin up agents to work on this", "use all our agents", "coordinate specialists", or wants to break a large task into parallel sub-tasks handled by multiple domain experts simultaneously. Orchestrates Claude Code's experimental agent team system using the full bopen-tools specialist roster.

Coordinate native specialist agents, external implementation workers such as Grok, and an independent advisor such as Fable from a capable main session. Use for "orchestrate this", "use Grok workers", "use Fable as advisor", "Codex main with workers", "delegate implementation but keep control here", or cross-model workflows. Never replaces the user's current main model.

Design or harden a software factory: an agentic loop that iterates toward a goal with a verification gate, persistent state, and a stop condition. Use for "build a loop", "agentic loop", "self-iterating agent", "/loop", "/goal", "Ralph loop", "maker-checker", "agentic SDLC", "ADW", or when picking a verification gate or bounding a loop's blast radius.

Dispatch many subagents in coordinated waves with per-wave review. Use for "fan out agents", "wave dispatch", "batch agents", "generate N variations", or any fan-out beyond about five parallel subagents that needs batching, ordering, and result reconciliation.