Leaderboard/Agent Orchestration/gentle-shell
Last commit on September 12, 2026·Created on May 10, 2026

Gentleman-Programming/gentle-shell

A harness for transforming AI agents into senior architects through spec-driven development.
Combined rank
#360
across all skills
In Agent Orchestration
#21
category rank
Stars
852
+28.5% in last 7d
Forks
122
Watchers
2
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR

Gentle Shell provides a disciplined framework for AI agents to operate with the rigor of senior architects. It emphasizes clarifying requirements first, preserving OpenSpec artifacts, and utilizing strict test-driven development to ensure structural integrity.

The system helps automation builders standardize review guardrails by managing cognitive load. It enforces a structured approach to contributions, ensuring that changes are grounded in design documents and verified through evidence.

WHO IT'S FOR
AI agent / automation builders
implementing senior-architect harness discipline for agents
Technical leads / architects
standardizing spec-driven development and review guardrails
Platform / DevEx teams
automating issue triage and PR workflow guardrails
Engineering managers
improving team collaboration and review communication
Repository contents

13 skill files

Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Want to install it?
Clone to Claude · Clone to Codex · Manual CopyRepository instructions