11 plugins in our Security & Governance shelf (Guards, audits and policy.), ordered by what we can actually measure: our editor's picks first, then GitHub stars (checked 2026-10-26). Archived repos go to the bottom.
Stars measure popularity, not quality or safety. We haven't installed or audited these; every description is the project's own. Read the code before you install anything. Paid placements never affect this order.
Most-starred right now: Agent Guard by JeongJaeSoon.
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.
★ 34 · by JeongJaeSoon#2Coverage, security and code quality for coding agents.
★ 157 · by supercorp-ai#3Intent-based security for Codex with MCP plan registration, policy gating, CSRG cryptographic proofs, and audit logging on `bash` and `apply_patch`.
★ 7 · by armoriq#4Versioned Skill Registry of code-review skills driven by a perspective-based review agent (code, security, performance, architecture, testing, adversarial) that verifies findings against the diff.
★ 7 · by s977043#5Bridge Burp Suite traffic, replay, rewrite rules, and evidence export into Codex through MCP for WSL, Windows, and macOS workflows.
★ 4 · by 6jeffr3y#6Runtime 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.
★ 3 · by getaxonflow#7Read-only audit of AGENTS.md/CLAUDE.md scope, hooks, MCP config, skills, secret references, and validation notes before Codex edits migrated projects.
★ 1 · by unitedideas#8Security-focused Codex plugin that connects to the local Claude Code CLI through MCP with login, status checks, safe-mode prompts, and no credential storage.
★ 1 · by davidq888#9Start authorized autonomous AI pentest runs, poll status, list campaigns and read findings on your own self-hosted Darkmoon Pro through MCP.
★ 0 · by ASCIT31#10Pre-flight GitHub bounty security scanner and on-chain Proof-of-Escrow MCP verifier that classifies open bounties before AI agents invest compute.
★ n/a · by doomsday-network#11Persistent security case tracking for bug bounties, CTFs, and security audits.
★ 10 · by x4cc3