#259 · Primary category: AI Coding Assistants
pilot-shell
How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make your agents production-ready.
Project last updated:08/28/26
GitHub Stars
2.1K
Forks
176
Contributors
12
License
Other
Why we included this project
Claude Code and Codex CLI write code fast, but without structure they skip tests and lose context between sessions. The output drifts from the original requirements. Pilot Shell wraps those agents in a workflow that forces discipline: a `/prd` step turns rough ideas into clear requirements, `/spec` takes a feature from plan to verified implementation with enforced TDD, and `/build` runs autonomously in judge loops until a goal you name passes. Quality hooks run linting, formatting, type checking, and tests as gates on every edit, while captured decisions and project knowledge persist in a local database and can be shared with teammates through the repository. If you want agent-assisted coding to feel more like disciplined software development and less like a free-for-all, this is a practical way to add planning and verification to the loop.
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.