Aport Guardrails
Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks unauthorized commands, dangerous file operations, and policy violations. All evaluation runs locally by default - zero network calls, works offline. Open-source (Apache 2.0). Includes three skills: - /aport-guardrails:claude-code — Set up guardrails and create a passport - /aport-guardrails:status — Check guardrail status and
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Security — see all ranked ›
Work: Agent configuration
Who it is for: Agent operator
- tashan score: 49.0
- Adoption: 1 repos
- Health: active
- GitHub stars: 25
- Contributors: 1
- License: NOASSERTION
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · plugin:aporthq/aport-agent-guardrails/aport-guardrails
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›