26,946 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
MCP server Claude CodeCodexCursor +2
Local STDIO MCP for DugganUSA threat intel. 1.13M IOCs. Read-only. npm: dugganusa-cli. Runs locally from the dugganusa-cli npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Audit AI agent configs for prompt injection & rogue MCP servers; vet packages. Runs locally from the zyrax-guard npm package.
MCP server Claude CodeCodexCursor +2
Zero-knowledge MCP secrets vault for AI agents: secrets injected at runtime, never seen by the model. Runs locally from the @wundervault/mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Honeypot probe data: IP reputation, scanners, CVE probing, TLS and SSH fingerprints. Remote server at mcp.honeylabs.net.
Skill Claude CodeCodex
Trust scoring, PII protection, and audit for OpenClaw agents. Strips personal data before it reaches the LLM. Blocks dangerous tools. Detects prompt injection. Audits everything.
Plugin Claude Code
Bundles 4 skills, 1 command, 2 MCP servers · 310 tokens together
Operate Scalix Cloud from Claude — 50 platform tools over one remote MCP endpoint (databases, AI inference, functions, computers, storage, KV, auth, billing), plus skills for provisioning ScalixNova Postgres, deploying serverless functions, and running AI inference.
Skill Claude CodeCodex
Verify wallets, tokens, smart contracts, AI agents and web applications before trusting them, paying per call in USDC over x402.
Plugin Claude Code
Bundles 3 skills, 1 MCP server · 74 tokens together
Sigma detection rule writing, validation, and conversion for SOC analysts and threat-intel teams. LLM-assisted draft + pySigma validation + multi-backend conversion (Splunk, Elastic, OpenSearch; Wazuh through the Elastic Lucene backend) with logsource-aware processing pipelines. Ships a 294-rule published corpus…
MCP server Claude CodeCodexCursor +2
Check if a counterparty is safe to pay: trust/risk score for AI agents. Scam/phishing screen. Remote server at vouch.futuronoti.workers.dev.
MCP server Claude CodeCodexCursor +2
Local policy wrapper for Supabase MCP with macOS Keychain-backed tokens, project allowlists, write locks, and audit logs. Runs locally from the supabase-mcp-guard npm package.
Command Claude Code
A Chinese-language code-review command for the current project. It checks code for bugs, security vulnerabilities, performance issues, and readability problems, then sorts its findings by severity.
Skill Claude CodeCodex
Use when an action could cause material, hard-to-reverse harm to production, data, security, finances, users, or external systems.
Skill Claude CodeCodex
Expert Canadian GRC and cyber law advisor covering OSFI B-10/B-13/E-21/I-CRT, FSRA, AMF/Loi 25, BCFSA, CIRO, AER Reg 84/CSA Z246.1, PIPEDA, PHIPA, PIPA BC, PIPA AB, Bill C-26, and AIDA. Use this skill whenever the user mentions any Canadian financial regulator, provincial privacy law, Alberta energy security, Canadian…
Aidress-ai/aidress-skill-find-verified-code-generation-agent
Skill Claude CodeCodex
Find a Verified Code Generation Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for software agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
softwareasg-tools/information-security-for-vibecoded-apps
Skill Claude CodeCodex
Autonomous security auditor for AI-generated applications. Provide a codebase path and it will automatically detect the stack, execute a comprehensive 12-phase security scan, identify vulnerabilities, and provide a production decision.
mertjane/awesome-claude-commands
Command Claude Code
Scans source files for hardcoded secrets, SQL injection, XSS, insecure configurations, and other common security vulnerabilities. Produces a prioritized report.
Skill Codex
Secure code review skill for application risk analysis, threat modeling, scanner tuning, and developer-focused remediation guidance.
Skill Claude CodeCodex
Audit a vibe-coded or AI-generated SaaS for security and payment failures before it ships, focused on the Next.js + Supabase + Stripe stack. Use this whenever the user is about to deploy, launch, or "ship" a web app that handles authentication, user data, or payments. Trigger on phrases like "is my app secure", "can…
Plugin Claude Code
Bundles 1 skill, 1 hook · 132 tokens together
Defensive, local-first security recon that briefs your AI coding agent on your OWN codebase. Read-only by default: facts + tailored probes + a calibrated findings ledger, code-in / artifacts-out, no LLM / no server / no running app. Live probes are opt-in against a TEST instance you own; production is out of scope.
Skill Claude Code
Project-wide security rules for handling untrusted input, secrets, and database access.
CarolMonroe22/supabase-db-supervisor
Skill Claude CodeCodex
Fresh-eyes supervision pass for any database work an AI agent just built (schema, RLS policies, migrations, edge functions touching the database, storage policies). The builder never grades its own homework - a separate agent plays the "Investigate" role, proves who-can-see-what with real queries, and gives an…
Plugin Claude Code
Bundles 36 skills, 2 agents · 2,910 tokens together
Web application security review skills: architecture recon, 33 vulnerability-class detectors, and a consolidated severity-ranked report.
Agent Claude Code
Read-only reviewer for JWT login, password hashing, and /auth routes in this tracker. Use when the user asks to review auth.py, registration, login tokens, or getcurrentuser. Use after changes to auth helpers or auth routes. Do not use for session/cost exploration or for implementing features.
aniruddhavasudev/ai-debt-audit
Plugin Claude Code
Bundles 1 skill · 108 tokens together
Catches the garbage your AI assistant left behind — security shortcuts, secrets buried in git history, code nobody understands. One 0-100 score, 100% local, no LLM in the loop.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: