46-orchestrate

46-orchestrate is an Agent task delegation & fan-out skill for AI agents, published by scdenney in the open-science-skills repository on GitHub. Skillspace rates 46-orchestrate C (70/100) and it passed the safety scan; the rating is based on static analysis only.

Orchestrate complex work as the Codex lead on the GPT-5.6 family. Default — a gpt-5.6-sol lead at xhigh effort owns decomposition, integration, and verification; it routes bounded work down to gpt-5.6-terra through out-of-band codex exec one-shots when the session permits them, and reaches a genuine cross-vendor peer (Claude Fable 5, via claude-peer.sh) for a real decorrelated check on high-stakes calls, mirroring the Codex peer fable-orchestrate and opus-orchestrate use in the other direction. Use gpt-5.6-luna only for tightly specified mechanical work with objective checks. Native spawn_agent children inherit the lead's model and effort, so they are not Terra/Luna delegation. Use when the user explicitly asks to orchestrate, delegate, fan out, parallelize, assign subagents, obtain independent checks, or have Codex act as tech lead.

Grade

C

Quality

70 / 100

Safety

Passed

GitHub stars

32

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.