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.
Skill Claude CodeCodex
Audits a codebase and its infrastructure config for HIPAA Security Rule compliance — locates PHI in data models, logs, error trackers, analytics, and outbound LLM/API calls, then reports findings graded against §164.312's technical safeguards with file:line evidence. Use when the user asks to audit an app for HIPAA…
Skill Claude CodeCodex needs its repo
Run OAuth 2.0 device-code and illicit-consent phishing against Microsoft Entra ID to steal access and refresh tokens, bypass MFA, and pivot across Microsoft 365 services.
Skill Claude CodeCodex
Enforce the ACKit docs-first, task-first workflow with one active checklist item and evidence-based completion.
Skill Codex
Audit an app, website, metadata, SDKs, and marketing for privacy, security, AI transparency, consumer claims, subscriptions, content rights, user-generated content, children, health, financial, export, and platform-policy risks. Use before TestFlight, submission, release, paid marketing, or after adding tracking…
Skill Claude Code
Decompose requirements into roadmap tasks. Must run in isolated context/subagent. Protocol-invoked only; do not auto-trigger from casual user requests.
Plugin Claude Code
Bundles 4 skills, 6 commands · 402 tokens together
Run adversarial / security tests against your local AI agent. Detects your FastAPI server, exposes it via ngrok, you author bot-config.json with your endpoints / auth / payload, the plugin dispatches via the humanbound MCP — results delivered by email (or run /humanbound-test:resume to watch the polling loop and f.
jonaslejon/linux-security-audit-plugin
Plugin Claude Code
Bundles 1 skill · 149 tokens together
Audit a Linux host's security hardening posture and produce a risk-ranked report, using both passive config inspection and active service probing. Runs against a live host, a mounted image (--root), or a container.
Plugin Claude Code
Plugin marketplace listing 1 plugin: secure-sdlc-agents.
Skill Claude CodeCodex
Authorized penetration tester persona — offensive security specialist for network, web app, cloud, and Active Directory assessments. Requires explicit authorization.
MCP server Claude CodeCodexCursor +2
Website & Server Diagnostics MCP Server. DNS, SSL, HTTP headers, security scan, performance audit. Runs locally from the mcp-diagnostics npm package.
MCP server Claude CodeCodexCursor +2
MCP server for the CrowdStrike Falcon platform. Runs locally from the crowdstrike-mcp Python package.
MCP server Claude CodeCodexCursor +2
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval. Remote server at mcp.tap.human.tech.
Plugin Claude Code
Bundles 24 skills, 24 commands, 7 agents, 3 hooks · 1,318 tokens together
Disciplined workflow skills, security review, learning system, and cross-platform tooling for Claude Code.
Skill Claude Code
Nuclei CLI parameter reference and usage patterns - YAML-template vulnerability scanning, target input modes, template filters, output formats, rate limits, ProjectDiscovery dashboard upload, and common scan commands.
Skill Claude CodeCodex
Scaffold a complete, responsive page layout with @allxsmith/bestax-bulma — app shells/dashboards, marketing/landing pages, centered auth/settings pages, and card-grid catalogs. Use when building a full page or overall app layout (not a single component).
CrowdStrike/crowdstrike-mcp-skills
Plugin Claude Code
Bundles 1 skill · 47 tokens together
Configure the CrowdStrike Falcon MCP server with OAuth2 authentication using client credentials.
Skill Claude CodeCodex
A guide for working with files protected by enterprise encryption software when an AI agent’s normal file tools show unreadable text.
Onome-AJ/security-sweep-plugin
Plugin Claude Code
Bundles 1 skill · 43 tokens together
Comprehensive security scanner for codebases — finds hardcoded secrets, injection flaws, auth issues, misconfigurations, AI-specific vulnerabilities, and more. Covers OWASP Top 10, Mobile Top 10, and LLM Top 10.
MCP server Claude CodeCodexCursor +2
Manage AdGuard Home through AI assistants. Runs locally from the @samik081/mcp-adguard-home npm package. Needs 3 environment variables to run.
Skill Claude CodeCodex
A Capture The Flag, or CTF, security-competition assistant covering web attacks, binary exploitation, reverse engineering, cryptography, forensics, blockchain, and cloud security.
RedHatProductSecurity/agentic-threat-modeling
Skill Claude Code
Core threat analysis engine. Takes a system context profile and applies one or more threat modeling frameworks (STRIDE, PASTA, LINDDUN, VAST, Attack Trees, OCTAVE) with automatic threat actor profiling.
Skill Claude CodeCodex needs its repo
Use when executing implementation plans with independent tasks in the current session.
MCP server Claude CodeCodexCursor +2
Open-source governance for MCP agents: useful autonomy without unlimited authority. Runs locally from the @gethelio/proxy npm package.
Skill Claude Code
Checks AI coding agent setups, leaked keys and the computer itself for security problems, using the Bulwark scanner installed on this machine. Use when the user asks whether a repository, their agent configuration or their machine is safe; before trusting a freshly cloned repository; when an agent was given broad…
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: