Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by GenseeAI · Codex Skill · ★ 123
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is gensee-crate safe to install? View the security audit →
Gensee Crate Full-stack, long-horizon runtime safety for AI coding agents. Gensee Crate watches system events, user requests, agent tool calls, skills and memory behind unmodified coding agents such as Claude Code, Codex, and Omnigent. It follows long-horizon agent behavior across requests and sessions and runs as a low-latency sidecar beside the agents on native hosts like macOS. Real-time enforcement happens within chat interface of the coding agents, while offline event tracking, lineage, and provenance can be viewed in a web dashboard and command line. gensee.ai · Docs · Join Discord <img src="docs/gensee-crate-defense-in-depth.png" alt="Gensee C
| Stars | 123 |
| Forks | 12 |
| Language | Rust |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 67.0728735459828/100 |
| Last Updated | 2026-09-07 |
| Created | 2026-06-23 |
| Platforms | claude-code, codex, rust |
| Est. Tokens | ~25k |
Looking for a gensee-crate alternative? If you're comparing gensee-crate with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
Security audit tool for Claude Desktop and Claude Code on macOS — single-command visibility into MCP servers,
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
The AI agent that works while you don't watch. Lives in your menu bar, finds you when needed.
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,
Explore other popular codex skill tools:
gensee-crate is Operation-bound protection for autonomous AI agents: contain and verify operations before committing changes, understand intent and risk across long-running work, and detect threats across agent and s. It is categorized as a Codex Skill with 123 GitHub stars.
gensee-crate is primarily written in Rust. It covers topics such as agent-safety, agent-security, ai-agent.
You can find installation instructions and usage details in the gensee-crate GitHub repository at github.com/GenseeAI/gensee-crate. The project has 123 stars and 12 forks, indicating an active community.
gensee-crate is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to gensee-crate on Agent Skills Hub include deterministic-agent-control-protocol, compose-skill, claudit-sec. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: