gsd:milestone-sprint

Automate milestone execution with autonomous planning, execution, and auditing.

1|1|Updated Jan 17, 2026
One-click install
npx skills add https://github.com/LucaDeLeo/ASTN --skill gsd-milestone-sprint
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gsd:milestone-sprint
Source: https://github.com/LucaDeLeo/ASTN/tree/main/.claude/skills/gsd-milestone-sprint
Command: npx skills add https://github.com/LucaDeLeo/ASTN --skill gsd-milestone-sprint

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Milestone Sprint automates end-to-end milestone execution in AI safety projects by auto-detecting the current milestone, coordinating autonomous planning, execution, and auditing, and generating contextual decisions.

Core Features & Use Cases

  • Auto-discuss phase decisions via Claude ↔ Codex dialogue and CONTEXT.md generation.
  • Autonomous planning and execution with per-phase summaries, diagnostics, and verification.
  • Built-in auditing and optional completion/archiving of milestones, with resume support for interrupted runs.

Quick Start

Start a milestone sprint to automatically detect the current milestone and execute all phases.

Frequently Asked Questions about gsd:milestone-sprint

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

FAQPage Schema
How do I automate milestone sprint planning and execution for AI projects?

Milestone sprint automation auto-detects the current milestone and coordinates autonomous planning, execution, and auditing using Claude and Codex. It generates contextual decisions and phase-by-phase progress with verification checks.

Can I resume an interrupted milestone sprint after stopping the process?

Yes, milestone sprint supports resume functionality for interrupted runs. The orchestration process saves phase-level signals and CONTEXT.md handoffs to seamlessly continue autonomous execution from the last completed phase.

How does Claude and Codex orchestration work for milestone auditing?

Claude and Codex dialogue orchestrates milestone auditing by auto-discussing phase decisions and generating contextual CONTEXT.md files. The AI models coordinate planning, automate execution, and verify phase-level progress before optional archiving.

What is the best way to track phase-by-phase progress in complex AI safety milestones?

Tracking complex AI safety milestones uses autonomous sprint orchestration to generate per-phase summaries, diagnostics, and verification. The system applies phase-level signals and audit checks to ensure contextual milestone completion.

Do I need external dependencies to run autonomous sprint orchestration and milestone auditing?

No external dependencies are required for autonomous sprint orchestration and milestone auditing. The system relies entirely on internal scripts to coordinate Claude and Codex for planning, execution, verification, and optional archiving.

When should I avoid using automated milestone sprints for project planning?

Avoid automated milestone sprints when a project requires manual intervention for complex contextual decisions or lacks defined phases. The autonomous orchestration is optimized for structured AI safety milestones needing phase-by-phase progress and verification.