planner

Convert high-level goals into a deterministic planning DAG for OmegaOS.

10|3|Updated May 26, 2026
One-click install
npx skills add https://github.com/agentik-os/OmegaOS --skill planner-agentik-os
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: planner
Source: https://github.com/agentik-os/OmegaOS/tree/main/skills/planner
Command: npx skills add https://github.com/agentik-os/OmegaOS --skill planner-agentik-os

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OmegaOS-native implementation planner reads Vision/PRD/CLAUDE.md, decomposes the work into a DAG of single-worker-dispatch steps, and emits a typed .planner/tracker.json that the Rust engine omega plan-run executes with structural can't-skip enforcement (Gate) and independent verify-command proof (Guardian). Replaces the prose-only VPS planner: sequential execution is enforced by the engine, not by instructions.

Core Features & Use Cases

  • Decomposes goals into discrete, verifiable steps aligned with Vision/PRD requirements.
  • Emits a ready-to-run tracker JSON for omega plan-run with explicit dependencies and file-touch scopes.
  • Supports multi-language prompts and re-usable planning templates for consistent handoffs.

Quick Start

Describe Vision/PRD goals and let the planner generate a .planner/tracker.json to drive omega plan-run.

Frequently Asked Questions about planner

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert high-level project goals into an executable planning DAG?

To convert goals into a planning DAG, the planner reads Vision/PRD/CLAUDE.md files and decomposes them into single-worker tasks, emitting a typed .planner/tracker.json with phases, dependencies, and touch-file metadata.

How does deterministic workflow planning enforce sequential execution?

Deterministic workflow planning enforces sequential execution by emitting a tracker JSON that the omega plan-run engine orchestrates, applying structural Gate enforcement and independent Guardian verify-command proofs rather than relying on prose instructions.

What do I need to generate a tracker JSON for automated task decomposition?

To generate a tracker JSON for task decomposition, you need existing Vision, PRD, or CLAUDE.md files describing your goals. The planner reads these inputs to produce the ready-to-run .planner/tracker.json file.

Does the planner work with multi-language prompts and reusable planning templates?

Yes, the planner supports multi-language prompts and reusable planning templates. This allows you to decompose goals into verifiable steps aligned with Vision/PRD requirements while maintaining consistent handoffs.

Why use a DAG-based task planner instead of a prose-only planning approach?

A DAG-based task planner replaces prose-only approaches by shifting sequential execution enforcement from instructions to the execution engine. It provides structural can't-skip enforcement and independent verification proof for every single-worker task.

Can I use the generated tracker JSON to orchestrate execution with verification gates?

Yes, the generated .planner/tracker.json drives the omega plan-run engine to orchestrate execution with Gate and Guardian verification. It includes explicit dependencies and file-touch scopes for structural enforcement.