by KbWen · Claude Skill · ★ 213
Agentic OS "Done." — your AI coding agent, about code it didn't test. A rules file asks your agent to behave. Agentic OS checks that it did — leaked secrets and a green check over zero tests fail your git hooks and CI; a skipped review or phase shows up when the validator reads the work trail. Backstops you control, not the agent's own word. A governance-first layer for AI coding agents — guardrails and a gated workflow for Claude Code, Codex, Cursor, Copilot, Antigravity, or any Markdown-reading agent. · <a href="docs/READMEz
| Stars | 213 |
| Forks | 44 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 40.05/100 |
| Open Issues | 11 |
| Last Updated | 2026-10-18 |
| Created | 2026-04-12 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~222k |
These tools work well together with agentic-os for enhanced workflows:
Explore other popular claude skill tools:
agentic-os is Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for C. It is categorized as a Claude Skill with 213 GitHub stars.
agentic-os is primarily written in Python. It covers topics such as agent-framework, agent-orchestration, agentic-development.
You can find installation instructions and usage details in the agentic-os GitHub repository at github.com/KbWen/agentic-os. The project has 213 stars and 44 forks, indicating an active community.
agentic-os is released under the MIT license, making it free to use and modify according to the license terms.