megaplan-setup

Configure Megaplan sprint profiles, robustness, and depth before initialization.

97|8|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/peteromallet/arnold --skill megaplan-setup
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: megaplan-setup
Source: https://github.com/peteromallet/arnold/tree/main/megaplan/data/_codex_skills/megaplan-prep
Command: npx skills add https://github.com/peteromallet/arnold --skill megaplan-setup

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you correctly size and parameterize a Megaplan sprint so the harness captures the right brief, chooses the right intelligence tier, and runs with the process rigor and thinking depth your work actually requires.

Core Features & Use Cases

  • Sprint pre-configuration: Set the work size, write a locked brief, and choose the profile (intelligence tier), robustness level, and depth before init.
  • Model-routing guidance: Align tier reasoning strength with default complexity-routed execution and understand when to pin execute to a single model.
  • Optional rigor controls: Enable prep and feedback when research-heavy or when you want a per-stage ratings artifact after completion.
  • Epics and splitting rules: Decide when to chain multiple megaplans and structure dependencies across sprints.

Quick Start

Use the megaplan-setup skill to initialize a new sprint by specifying the profile, robustness, and depth appropriate for your brief so the run starts with a correctly scoped, locked plan.

Frequently Asked Questions about megaplan-setup

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

FAQPage Schema
How do I configure a sprint before running an LLM planning pipeline?

To configure a sprint, you set the work size, lock the brief, and select the profile, robustness level, and depth dials before initialization. This ensures the execution harness captures a correctly scoped plan for your software delivery pipeline.

What is the best way to size a sprint for research-heavy software delivery?

The best way to size a research-heavy sprint is to enable optional prep and feedback controls during setup. This applies increased critique rigor and generates a per-stage ratings artifact after the sprint completes.

How do I align model routing with complexity-routed execution safeguards?

You align model routing by choosing the right intelligence tier profile during setup. This matches tier reasoning strength with default complexity-routed execution, and you can pin execution to a single model when necessary.

When should I chain multiple sprints together for a software development pipeline?

You should chain multiple sprints when your brief requires splitting into structured dependencies across runs. The setup process uses epics and splitting rules to decide when to initiate multiple sequential executions.

Does sprint setup support per-stage ratings artifacts for workflow configuration?

Yes, sprint setup supports optional feedback controls that generate a per-stage ratings artifact after completion. This is particularly useful for cases that benefit from increased critique rigor in software delivery.

Why pin execution to a single model during LLM planning initialization?

Pinning execution to a single model overrides default complexity-routed execution to maintain consistent reasoning strength. This is guided by the tier profile selection during the initial sprint setup phase.