29,002 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.
Instructions file GitHub Copilot
Copilot instructions for SCStelz/security-investigator, covering github copilot - security investigation integration, 📑 table of contents, ⚠️ critical workflow rules - read first ⚠️, 🔧 environment configuration and prerequisites.
wiz-sec-public/secure-rules-files
Cursor rule Cursor
Enforce secure infrastructure-as-code best practices for HCL/Terraform configurations to prevent common cloud security misconfigurations.
Instructions file CodexOpenCode
AGENTS.md instructions for coconut-svsm/svsm, covering directory structure, building and testing, build recipes, igvm and formal verification with verus.
Instructions file CodexOpenCode
AGENTS.md instructions for Hoylon/peerbridge-mcp, a project described as: Local-first, auditable multi-agent control room for coding, review, evidence, and private remote work.
ProgrammerAnthony/Expert-Coding-Harness
Skill Cursor
A security guide for AI agents—software that follows instructions and can use tools or data. It covers threats such as prompt injection, data leaks, unsafe code execution, unauthorized access, and compliance issues.
Skill Claude CodeCodex
Search the Tor dark web, fetch .onion hidden service pages, rotate Tor identity, and run structured OSINT investigations. Use when user asks to search dark web, investigate .onion sites, find if data appeared on dark web, conduct Tor-based OSINT, look up dark web leaks, fetch any .onion URL, check for leaked…
erikdarlingdata/PerformanceStudio
Skill Claude Code
Quarterly maintenance pass (every 1-3 months) — dependency/security audit, build health, and repo hygiene for PerformanceMonitor and PerformanceStudio.
Instructions file Claude Code
A security testing guide for SecSkills, a library of practical penetration-testing techniques and reference material.
Skill Claude CodeCodex
Python-based threat modeling using pytm library for programmatic STRIDE analysis, data flow diagram generation, and automated security threat identification. Use when: (1) Creating threat models programmatically using Python code, (2) Generating data flow diagrams (DFDs) with automatic STRIDE threat identification…
Skill Claude CodeCodex
Validate ActiveStorage attachments (content type, file size, file extension) with the activestorage-validator gem's blob validator. Use when adding validations to hasoneattached / hasmanyattached attributes.
Instructions file Claude Code
Claude Code instructions for grisuno/LazyOwn, covering claude.md — lazyown redteam framework, 0. what lazyown is, 0.1 security contracts, security hardening sprint (sdd+tdd+bdd) and 0.2 non-negotiable: user input is hostile.
Instructions file Claude Code
Instructions for bhavsec/autopentest-ai, covering autopentest: automated web application penetration testing, available mcp servers, wstg pentest mcp server (wstg-pentest), reference guides (read on demand during testing) and portswigger technique reference guides.
Skill Codex
Use when analyzing packet captures or live network traffic with Wireshark MCP; choose the right workflow for triage, security hunting, incident response, or troubleshooting, then produce evidence-backed findings with exact filters, streams, frames, and next steps.
Agent Claude Code
Distills a past security report into a reusable agentgg agent that catches the same anti-pattern if it recurs in this codebase.
Agent Claude Code
Use this agent for proactive security code review, vulnerability detection, and security best practices guidance. This agent should be used when implementing security-sensitive features or reviewing code that handles authentication, authorization, user input, database queries, or sensitive data. Examples:\n\n…
Esonhugh/pydoll-cf-waf-bypasser-skills
Settings file Claude Code
Agent settings configuring skills.
AgriciDaniel/claude-cybersecurity
Plugin Claude Code
Bundles 1 skill · 201 tokens together
AI-powered cybersecurity code review with 8 specialist agents, OWASP Top 10:2021, CWE Top 25:2024, MITRE ATT&CK v15, and framework-aware false-positive suppression.
Plugin Claude Code
Bundles 1 skill · 165 tokens together
Autonomous, looping, multi-altitude security vulnerability hunt for a codebase — the RAPTOR 'Karpathy auto-research' generate -> adversarially-judge -> verify loop that finds far more bugs than a single-pass scan.
Skill Codex
Guided workflow for authorized penetration testing, vulnerability validation, security reporting, CTF/local sandbox reverse engineering, and user-directed vulnerability research. Use when Codex is asked to run or plan a security assessment, triage a target or artifact, maintain pentest state, produce interim/final…
Skill Claude CodeCodex
Configure rate limiting, manage auth secrets, set up CSRF protection, define trusted origins, secure sessions and cookies, encrypt OAuth tokens, track IP addresses, and implement audit logging for Better Auth. Use when users need to secure their auth setup, prevent brute force attacks, or harden a Better Auth…
Plugin Claude Code
Bundles 2 skills · 266 tokens together
Development guide for the jwt JSON Web Token library for Go: signing and verifying tokens, claims and expiry, algorithm choice (HMAC/RSA/RSA-PSS/ECDSA/EdDSA), kid-based key rotation, JWKS fetch/refresh/publish, blocklisting and testing.
Skill Claude CodeCodex
Expert guidance for ffuf web fuzzing during penetration testing, including authenticated fuzzing with raw requests, auto-calibration, and result analysis.
OpenZeppelin/openzeppelin-skills
Plugin Claude Code
Bundles 11 skills · 1,093 tokens together
Skills for secure smart contract development with OpenZeppelin Contracts libraries.
Skill Claude CodeCodex
The Inescapable Auditor. Runs the full Feynman Auditor (Stage 1) and full State Inconsistency Auditor (Stage 2) as primary steps, then fuses their outputs in a feedback loop (Stage 3) to find bugs at the intersection that neither alone would catch. Language-agnostic. Triggers on /nemesis or nemesis audit.
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: