# Codex Dynamic Workflows [Codex Dynamic Workflows](https://github.com/DannyMac180/skills/tree/main/codex-dynamic-workflows) is a [[Codex CLI]] skill by [DannyMac180](https://github.com/DannyMac180) that turns large, ambiguous tasks into supervised AI-agent work. Instead of executing directly, the skill forces planning, delegation, and verification before anything risky happens. ## What it does The skill kicks in when a task benefits from explicit orchestration rather than one-shot execution. Triggers include parallel tracks (research, coding, QA, docs), high-risk operations (deploys, secrets, large repo changes), the need for a separate verification pass, or an explicit user ask for swarm / subagents / dynamic workflows. Small tasks are deliberately left alone. ## How it works A run goes through seven stages: 1. **Planning** — restate goals, success criteria, and risks. 2. **Orchestration** — create a workflow artifact describing the strategy. 3. **Delegation** — split work into disjoint packets, each with clear ownership. 4. **Execution** — run packets sequentially or spawn subagents for parallel work. 5. **Integration** — synthesize results, resolve conflicts. 6. **Verification** — checks scaled to task risk. 7. **Archival** — save reusable recipes for the next similar job. ## Key mechanics - **Workflow artifacts** live in `.workflow/<slug>/` and hold state, plans, and results. - **Work packets** are self-contained units with objective, context, owner, and success metric. - **Approval gates** pause before destructive, external, or high-risk steps. - **Goal mode** enables sustained multi-turn execution when the runner supports it. - **Subagent simulation** falls back to sequential packet processing when no real runner is available. ## Why it's interesting It is one of the cleaner public examples of treating "agentic work" as a contract — explicit packets, owners, gates, and verification — rather than a vibe. The same shape maps onto how OSK already handles agent chains, panels, and councils, and it's a useful reference for designing reusable skill pipelines. ## Related — Pi implementation [Michaelliv](https://github.com/Michaelliv) is exploring the same pattern inside [[Pi Mono]] with [pi-dynamic-workflows](https://github.com/Michaelliv/pi-dynamic-workflows). The Pi extension lets the model write a JavaScript workflow script that the `workflow` tool runs in a sandboxed Node VM, spawning isolated Pi subagent sessions via `agent()` calls — with `parallel()` and `pipeline()` for concurrent fan-out, JSON-Schema-validated structured output, live phase tracking, Esc-to-abort, and determinism safeguards (no `Date.now()`, `Math.random()`, `require`, or template interpolation). It is still prototype-stage — no persisted or resumable runs yet — but it is a clean Pi-side counterpart to the Codex skill. ## References - [DannyMac180/skills — codex-dynamic-workflows](https://github.com/DannyMac180/skills/tree/main/codex-dynamic-workflows) - [Michaelliv/pi-dynamic-workflows](https://github.com/Michaelliv/pi-dynamic-workflows) - [[Codex CLI]] - [[Pi Mono]]