by jturntdev · Codex Skill · ★ 95
Krypton Current version: Stop AI agents from shipping plausible wrong work. Krypton is the goal-based planning and proof gate for running Claude Code, Codex, and other AI coding agents against production-grade codebases. The failure mode Krypton is built for is not bad syntax. It is the right-looking feature that compiles while living on the wrong layer, inventing a second source of truth, skipping cutover, or claiming success without proof from the real path.
| Stars | 95 |
| Forks | 1 |
| Language | Shell |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 68.2935734627158/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-30 |
| Created | 2026-05-30 |
| Platforms | claude-code, cli, codex |
| Est. Tokens | ~7k |
These tools work well together with krypton for enhanced workflows:
Explore other popular codex skill tools:
krypton is Goal-based planning and proof gate for AI coding agents. It is categorized as a Codex Skill with 95 GitHub stars.
krypton is primarily written in Shell. It covers topics such as acceptance-evidence, agent-skills, agentic-coding.
You can find installation instructions and usage details in the krypton GitHub repository at github.com/jturntdev/krypton. The project has 95 stars and 1 forks, indicating an active community.
krypton is released under the MIT license, making it free to use and modify according to the license terms.