Menu
Compatibility alias for delegation-first workflows. Prefer `delegation-usage` as the canonical skill.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Primary entrypoint for Codex Orchestrator usage: route tasks to the right pipeline, mode, and supporting skills with minimal, auditable steps.
Manage non-trivial tasks via focused collab subagents to save context and improve throughput. Use when work spans multiple files/components, can be split into independent streams, needs separate validation/review, or risks context bloat. Favor direct execution for trivial one-shot tasks.
Ship a signed tag + GitHub Release + npm publish for @kbediako/codex-orchestrator with low-friction, agent-first steps (PR -> watch-merge -> tag -> watch publish -> downstream smoke).
Use when operating the Codex delegation MCP server and tools (delegate.spawn, delegate.question.*, delegate.cancel, github.merge confirmation flow), or when configuring delegation mode/tool_profile with delegation MCP enabled by default.
Use for required periodic cross-check reviews during implementation and before handoff using `codex review`.
Control and inspect Chrome via the Chrome DevTools MCP server (navigate, interact, screenshots, console, network, perf).
| name | delegate-early |
| description | Compatibility alias for delegation-first workflows. Prefer `delegation-usage` as the canonical skill. |
delegate-early is kept for backward compatibility. The canonical delegation workflow now lives in delegation-usage.
delegation-usage for setup, spawn semantics, question queue handling, confirmation flow, and manifest usage.delegation-usage.delegation-usage as the source of truth.If guidance in this file conflicts with delegation-usage, follow delegation-usage.
delegation-usage: canonical delegation control-plane workflow and source of truth.collab-subagents-first: role-split stream planning for bounded parallel execution.long-poll-wait: patience-first monitoring for delegated long-running streams.