Kbediako

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…

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).

Run collab/multi-agent eval scenarios (symbolic RLM, large-context, pause/resume, multi-hour checkpoints) and capture manifest-backed evidence.

Agent-first Codex Orchestrator usage playbook for downstream users: docs-first execution, delegation-first operations, non-coercive capability steering, and autonomy-preserving review guidance.

Use, even when not named, when this agent is the primary coordinator for an operative Codex Voice `realtime_delegation` handoff, including `source=transcript_tail_flush` after the live session ends, or when the user explicitly requests delegate-only Voice…

Consult ChatGPT Pro or another ChatGPT extended-reasoning mode with a faithful task-relevant context packet, reconcile its advice against local evidence, and run focused follow-ups to closure. Use when the user explicitly asks for ChatGPT Pro, GPT Pro, or…

Await or monitor external long-running jobs, operating-system processes, CI pipelines, cloud runs, remote training, or release checks until terminal status. Select an authorized observation path separately from active-turn or scheduled continuation; poll only…

Evaluate or audit Codex native Multi-Agent V2 behavior with small reproducible probes and structural rollout evidence. Use for V2 surface checks, direct-tool lifecycle behavior, bounded fanout, interruption semantics, resume behavior, or skill-invocation…

Forward-test an existing or changed Codex skill with fresh, contamination-resistant native-agent trials. Use to test whether instructions trigger, generalize, and change behavior under a fixed Sol worker condition; do not use to create or update the skill…

Choose the smallest suitable Codex workflow among solo work, bounded native-agent execution, deliberation, native-agent evaluation, skill forward-testing, and waiting. Use when the main uncertainty is which of these coordination shapes fits the task.

Coordinate bounded native Multi-Agent V2 work when the user asks for subagents, parallel agents, multi-agent implementation or review, or when an active native-agent workflow has genuinely independent streams. Use for GPT-5.6 Sol role selection, context…

Reconcile and wait for native Codex children when a child is quiet, appears hung, exceeds an estimate, or a wait window times out. Use before calling a child stalled, interrupting it, replacing it, or handing off without its final answer.