by pegasi-ai · Codex Skill · ★ 383
🪢 Reins Security controls for AI agents. github.com/pegasi-ai/reins = 18.0.0" In Greek myth, Athena gave Bellerophon the golden bridle — reins included — that let him guide Pegasus. Reins applies the same idea to AI agents: raw power is not enough — what matters is making it controllable. Reins enforces deterministic security policies on every agent action, scans your configs for OWASP ASI10 vulnerabilities, and tracks drift over time. Policies evaluate in under 50ms. Works with Claude Code PreToolUse and PostToolUse hooks, OpenClaw, and any MCP-compatible agent.
| Stars | 383 |
| Forks | 50 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 65.5385219087921/100 |
| Open Issues | 10 |
| Last Updated | 2026-04-14 |
| Created | 2023-04-13 |
| Platforms | browser, python |
| Est. Tokens | ~3518k |
Explore other popular codex skill tools:
clawreins is Runtime security for OpenClaw agents. Scan, fix, monitor.. It is categorized as a Codex Skill with 383 GitHub stars.
clawreins is primarily written in Python. It covers topics such as agent-security, ai-safety, audit-trail.
You can find installation instructions and usage details in the clawreins GitHub repository at github.com/pegasi-ai/clawreins. The project has 383 stars and 50 forks, indicating an active community.
clawreins is released under the Apache-2.0 license, making it free to use and modify according to the license terms.