phase-protocol

Enforce entry and exit gates with durable TODO anchoring across development phases.

3|Updated Jan 18, 2026
One-click install
npx skills add https://github.com/HankLiu447/SuperSpec --skill phase-protocol
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: phase-protocol
Source: https://github.com/HankLiu447/SuperSpec/tree/main/skills/phase-protocol
Command: npx skills add https://github.com/HankLiu447/SuperSpec --skill phase-protocol

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill standardizes how teams manage context across long-running development sessions by enforcing an Entry Gate, TODO anchoring, and an Exit Gate to prevent AI drift.

Core Features & Use Cases

  • Entry Gate: Forces context refresh at the start of each phase.
  • TODO Anchoring: Creates a durable TODO item that survives context compression.
  • Exit Gate: Re-reads the protocol before the next phase begins.
  • Use Case: During a multi-phase feature development, the protocol ensures every phase begins with a clean context and ends with a ready handoff to Phase N+1.

Quick Start

Use this skill to establish phase boundaries, create initial TODOs, and set up gate checks for the next sprint.

Frequently Asked Questions about phase-protocol

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

FAQPage Schema
How do I maintain AI context across long-running development phases?

To maintain AI context across development phases, you can use a phase protocol that enforces entry and exit gates alongside a durable TODO anchor. This prevents AI drift by standardizing context refreshes and handoffs between sessions.

What is a phase protocol for AI workflow management?

A phase protocol for AI workflows is a structured process that uses entry gates, exit gates, and TODO anchoring to manage context. It ensures AI begins each development phase with a clean context and ends with a ready handoff.

How do I prevent AI context drift during multi-phase feature development?

You prevent AI context drift by applying gate verification and TODO anchoring at phase transitions. This approach forces a context refresh at the start and re-reads the protocol before the next phase begins.

Do I need external tools to set up gate verification for AI workflows?

No external tools are required to set up gate verification for AI workflows. The phase protocol operates independently to enforce entry and exit gates and maintain a durable TODO without external dependencies.

When should I use entry and exit gates in AI-assisted development?

You should use entry and exit gates during multi-phase feature development to ensure seamless handoffs. They are applied at phase transitions to force context refreshes and verify protocol adherence before proceeding.

How does TODO anchoring survive context compression in AI sessions?

TODO anchoring survives context compression by creating a durable TODO item that persists across long-running sessions. This anchors the work and prevents loss of task awareness during AI context window compression.