#12 · Primary category: AI Coding Assistants
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Project last updated:08/07/26
GitHub Stars
116.4K
Forks
6.3K
Contributors
64
License
MIT
Why we included this project
Most coding agents default to building too much, and Ponytail is a skill that pushes back. You drop it into Claude Code or another agent runtime and it steers the model toward the smallest change that works, the one line instead of the fifty-line abstraction. The YAGNI mindset gets encoded as a reusable skill, so every session starts with the same bias toward minimal, maintainable code without you having to re-prompt. The repo includes benchmarks you can reproduce, measured on real Claude Code sessions, so you can see whether the effect holds on your own workloads. It's a prompt and workflow layer rather than a model or framework.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.