Agent Guard
Local-by-default, no-telemetry hooks block or mask secret leaks in Claude Code and Codex, with opt-in PII filtering and Git/CI backstops.
Editor's note: Hooks that catch secrets before they leak out of an agent session. Local by default, no telemetry. The first thing we'd install.
Open the project ↗Is this your plugin? Get featured or get a Verified badge ($9/mo) →
Also in Security & Governance
Guards, audits and policy.ArmorCodex
Intent-based security for Codex with MCP plan registration, policy gating, CSRG cryptographic proofs, and audit logging on `bash` and `apply_patch`.
No.039AxonFlow
Runtime governance for Codex with policy enforcement on terminal commands, advisory checks for non-terminal tools via skills, PII/secret detection, and compliance-grade audit trails. Self-hosted via Docker.
No.045BountyGuard
Pre-flight GitHub bounty security scanner and on-chain Proof-of-Escrow MCP verifier that classifies open bounties before AI agents invest compute.
No.046Bring Your AI Migration Auditor
Read-only audit of AGENTS.md/CLAUDE.md scope, hooks, MCP config, skills, secret references, and validation notes before Codex edits migrated projects.