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.
Plugin Claude Code
Bundles 7 skills, 5 commands, 15 agents · 1,551 tokens together
Full penetration testing framework - 63 attack categories across 11 domains covering OWASP, injection, authentication, cloud, and more.
Skill Claude CodeCodex
A security-audit skill for AI agents that examines seven attack areas, including user input, memory, tool calls, plugins, permissions, collaboration between agents, and monitoring.
Skill Claude CodeCodex
A Chinese-language assistant for IDA Pro, a program used to analyze compiled files such as Windows executables, libraries, and firmware.
Skill Claude CodeCodex
Use when preparing for a security audit, performing reconnaissance on a new codebase, or creating a protocol overview. Generates a structured pre-audit readiness report covering architecture overview, threat model, cross-linked protocol invariants, entry point classification and flow paths, composability analysis…
Skill Claude CodeCodex
Pre-submit hygiene check for AI-agent-authored pull requests. Use this skill whenever you are about to open or update a pull request: it runs the codex-guard CLI locally, verifies the diff contains no leftover TODO/FIXME/XXX markers and no hardcoded secrets, checks that commit subjects follow conventional commits, and…
Plugin Claude Code
Bundles 19 skills · 2,167 tokens together
Conjunto modular e orquestrado de skills para Claude que cobre, ponta-a-ponta, conformidade com a LGPD (Lei 13.709/2018), resoluções da ANPD aplicáveis e o ECA Digital (Lei 15.211/2025). Inclui 1 skill maestro (lgpd-audit) que orquestra 18 sub-skills especializadas: base legal, mapeamento de dados, ROPA, RIPD…
Cursor rule Cursor
Defensive invariants — when a check may be deleted — Deleting a defensive check because a proof says it cannot fire is the most expensive class of mistake made in this codebase. Canonical file is .agents/rules/defensive-invariants.md.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 35 tokens together
AI-powered smart contract security auditor with parallel hunt lanes, Devil's Advocate verification, static analysis (Slither, Aderyn), fuzz testing (Echidna, Medusa), symbolic execution (Halmos), Solodit intelligence, and interactive Map-Hunt-Attack methodology.
jrenaldi79/harness-engineering
Plugin Claude Code
Bundles 2 skills, 1 agent, 1 hook, 1 plugin · 199 tokens together
Analyze and enforce best practices for AI coding agent projects. Assess codebase readiness across 8 pillars with /readiness, then scaffold enforcement with /setup: TDD, secret scanning, file size limits, auto-generated docs, and git hooks.
Plugin Claude Code
Bundles 6 skills · 365 tokens together
6 skill hygiene tools: health report, auto-fix + prune, value (honest token split + usage), security scan (prompt injection + malicious patterns), discover (search + precheck), swipe (interactive triage).
Plugin Claude Code
Bundles 5 skills, 4 commands, 1 agent, 1 hook, 1 MCP server · 546 tokens together
SQL validation, formatting, linting, injection scanning and analysis for Claude Code, powered by the GoSQLX parser (multi-dialect).
sinewaveai/agent-security-scanner-mcp
Skill Claude CodeCodex
Scan prompts and code for security threats using agent-security-scanner-mcp. Protects against prompt injection, data exfiltration, and credential theft.
Plugin Claude Code
Bundles 45 skills, 16 commands, 13 agents, 3 hooks, 2 MCP servers · 2,579 tokens together
Claude Code plugin — 41 tools, 45 skills, 13 agents. Currency Guard keeps Claude on current docs, not stale training data. Elite SEO strategy with AI traffic tracking, IndexNow, GSC-GA4 cross-reference, CTR anomalies, brand filtering, keyword intelligence, index doctor, codebase index, pentest, ship, launch, grow…
MCP server Claude CodeCodexCursor +2
Model Context Protocol implementation for Frida. Runs locally from the frida-mcp Python package.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 78 tokens together
Runtime AI-threat screening for Claude: analyze prompts, scan tool calls and outputs, and vet documents before you act, with BLOCK / CHALLENGE / ALLOW verdicts. Paid feature — needs a Pro-plan-or-higher Guardian API key.
IgorWarzocha/Opencode-Workflows
Skill OpenCode
Review Convex security audit patterns for authentication and authorization. Use for auditing query/mutation auth, row-level security, and validators. Use proactively when reviewing Convex apps (convex/ directory present). Examples: user: "Audit these Convex mutations" → check for missing ctx.auth and input validators…
Plugin Claude Code
Plugins for working with Hex-Rays IDA Pro for reverse engineering and plugin develop.
Plugin Claude Code
MalChela — A YARA & Malware Analysis Toolkit with Claude MCP integration for DFIR analysts.
revfactory/harness-engineering-with-cc
Skill Claude Code
A coordinated code-review workflow with four reviewers: one for static analysis, one for design, one for security, and one for refactoring. A pull request is a proposed set of code changes submitted for review.
Plugin Gemini CLI ✓ vendor
Manage your Auth0 tenants, apps and APIs.
MCP server Claude CodeCodexCursor +2
MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF. Runs locally from the @kryptosai/mcp-observatory npm package.
Agent Claude Code
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
Clear-Capabilities/agentic-security
Plugin Claude Code
Bundles 7 skills, 17 commands, 9 agents, 5 hooks, 1 MCP server · 1,291 tokens together
Agentic-Security is a powerful Claude Code plugin that automatically performs Application Security Testing (SAST, SCA, secrets detection, and more). Think of it as the easy button for making your Claude-generated code safe and secure.
Skill Claude CodeCodex
Use when working in any FaasJS repo and no narrower FaasJS skill is already selected, or when a task spans project conventions, validation gates, security boundaries, and multiple FaasJS subsystems. For focused work, also load the relevant FaasJS skill: faasjs-project-workflow, faasjs-react-ant-design…
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: