sangrokjung / 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.
Why this job: works in the areas we cover, but does not say which job it does
What it does
- loop-forge skill + command. turn a one-line repetitive task into a reusable, self-guarding slash command (5 loop shapes + auto verifier & hardstop). Skills 24 → 25, commands 33 → 34.
- Beginner-friendly README. full rewrite for non-developers (plain-language analogies, terms explained in parentheses) + 3 diagrams (what's inside / install in 3 steps / development workflow), in English & Korean.
Get started
curl -fsSL https://raw.githubusercontent.com/sangrokjung/claude-forge/main/install.sh | bash - Maintenance
- Active
- Last commit 2 months ago
- Stars
- 875
- +4 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v4.1.0
- Released 2 months ago
- Built with
- Shell
- 45% of the code
Is it looked after?
- Contributors
- 4
- Last 90 days
- Issues
- 37% closed
- 22 still open
- Pull requests
- 30 merged
- 10 waiting
- Releases
- 6
- 6 in the last year
More: languages, topics and project record
Languages
- Shell 45%
- Python 21%
- HTML 19%
- JavaScript 10%
Topics
- agents
- ai-assistant
- ai-coding
- ai-framework
- ai-pair-programming
- anthropic
- automation
- claude-code
- claude-code-agents
- cli-tools
- developer-experience
- developer-tools
Project record
- JobOther AI tools
- StatusListed
- Commits134
- Forks182
- Watching7
- Stars in 28 days+25
- CreatedFeb 23, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026