#363 · Primary category： AI Coding Assistants
claude-forge
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.
Project last updated：08/29/26
GitHub Stars
820
Forks
176
Contributors
4
License
MIT
Why we included this project
Anyone who spends real time in Claude Code's terminal ends up typing the same prompts over and over. This project bundles the fix: sixteen specialist agents, 35 slash commands, 32 saved skills, and 21 safety hooks that run before and after every action, all installed at once. The v4.0 adversarial review loop is the most interesting piece. A second agent checks each behavioral change without ever seeing the first agent's reasoning, which gives teams a maker-versus-checker gate on AI-generated edits. Setup is one install script or a plugin command, and updates come through a git pull, so it works for a solo developer or a small team that wants everyone's Claude Code to behave the same way. It is a configuration and workflow layer, not a model or framework, so you pair it with an existing Claude Code install rather than run it on its own.
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.