by LuD1161 · Codex Skill · ★ 91
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.
| Stars | 91 |
| Forks | 6 |
| Language | Go |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 55.8201107655644/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-08 |
| Created | 2026-06-04 |
| Platforms | claude-code, codex, go |
| Est. Tokens | ~15k |
Looking for a agentjail alternative? If you're comparing agentjail 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.
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,
See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
Stop your AI agent from shipping insecure IaC. ops0 CLI sits between Claude Code, Codex or Gemini and your clo
The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime obs
The governance floor for AI coding agents: install, guard, prove. Guards, git hooks, an executable contract an
Explore other popular codex skill tools:
agentjail is Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.. It is categorized as a Codex Skill with 91 GitHub stars.
agentjail is primarily written in Go. It covers topics such as agent-security, ai-agents, claude-code.
You can find installation instructions and usage details in the agentjail GitHub repository at github.com/LuD1161/agentjail. The project has 91 stars and 6 forks, indicating an active community.
agentjail is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to agentjail on Agent Skills Hub include rampart, mcp-audit, agent-security-scanner-mcp. 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: