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 1 skill · 80 tokens together
Let the agent use API keys and passwords to get work done without the plaintext ever entering the transcript. The agent references secrets as secret://vault/ and runs commands through secret-exec, which resolves the value downstream and scrubs it back out of the output.
MCP server Claude CodeCodexCursor +2
Network MCP Server for AI Agents - Connectivity testing and pcap analysis. Runs locally from the network-mcp Python package.
Skill Claude CodeCodex
Anonymizuje české právní dokumenty (smlouvy, rozsudky, žaloby, znalecké posudky) před odesláním do Claude. Nahrazuje osobní údaje pseudonymy [OSOBA1], [IČO1] apod. Po zpracování Claudem deanonymizuje výsledek zpět do originálu.
MCP server Claude CodeCodexCursor +2
Security scanner for AI agent skills — scan SKILL.md files for threats, exfiltration, and malicious patterns. Runs locally from the skillaudit npm package.
Plugin Claude Code
Bundles 9 skills, 1 MCP server · 380 tokens together
Route authorized security workflows through the local Hercules MCP server.
mirage-security/knowbe4-mcp-server
MCP server Claude CodeCodexCursor +2
MCP server for KnowBe4 Reporting REST API. Runs locally from the knowbe4-mcp-server npm package.
AIwithhassan/agentic-ai-security
MCP server Claude CodeCodexCursor +2
MCP server "secure-ai-application" as configured in AIwithhassan/agentic-ai-security. Runs locally from the secure-ai-application Python package.
Skill Claude CodeCodex
OpenFGA authorization modeling best practices for defining types and relations, writing relationship tuples, deriving can permissions, applying type restrictions and usersets, and authoring .fga.yaml check/listobjects/listusers tests. Use when authoring, reviewing, or refactoring OpenFGA models, tuples, permissions…
Plugin Claude Code
Bundles 87 skills, 7 commands, 1 plugin · 568 tokens together
Unified Security Agent Platform — 81 cybersecurity skills + 13 cs- agents that emit a typed 11-field JSON output contract, mapped to MITRE ATT&CK and NIST CSF 2.0. Runs in any LLM. Bundles 7 slash commands (usap:run, usap:fortigate, usap:orchestrate, usap:challenge, usap:compare, usap:test, usap:README) and 6 user-inv.
MCP server Claude CodeCodexCursor +2
MCP server "pci-dss-mcp" as configured in shyshlakov/pci-dss-mcp. Launched with /path/to/pci-dss-mcp.
Skill Claude Code
Manage AgentLair email channel access — edit sender allowlists and set policy. Use when the user asks to allow or block email senders, check who can reach them, or change access policy.
Jandyoverseas977/Claude-Skills-Governance-Risk-and-Compliance
Plugin Claude Code
Bundles 1 skill · 165 tokens together
End-to-end FedRAMP authorization guidance — readiness assessments, SSP narratives, POA&M management, NIST 800-53 Rev 5 control mapping, and ConMon support.
leodisa/compliance-review-skill
Plugin Claude Code
Bundles 1 skill · 238 tokens together
Build or review code for compliance with the EU AI Act, GDPR, the NIS2 Directive (EU 2022/2555), and secure-development (SSDLC) best practice. Three modes: repo gap analysis, compliance-by-design while coding, and data protection — the skill asks whether to pseudonymise (deterministic tokens, joins preserved) or…
Skill Claude Code
Scan installed agent skills, plugins, and cross-agent instruction files for prompt injection, exfiltration, malicious code, and dependency risk. Use when the user asks to audit, check, review, inventory, or verify skills for Claude Code, Codex, Cursor, Copilot, Gemini, or AGENTS.md-style project instructions.
Skill Claude CodeCodex
Static malware reverse-engineering and threat-intelligence triage for unknown files, Windows EXE/PE binaries, scripts, archives, ISOs, JavaScript, PowerShell, documents, and unpacked payloads. Use when a user provides a sample path, hash, filename, or file and asks whether it is malicious, benign, suspicious, contains…
filestack/filestack-claude-plugin
Plugin Claude Code
Bundles 5 skills, 1 command, 1 MCP server · 546 tokens together
Official Filestack plugin — upload files, build transformations, and generate security policies directly from Claude Code.
MCP server Claude CodeCodexCursor +2
MCP server "kali" as configured in Hannes221/kali-mcp. Runs dist/index.js with node.
Cyreslab-AI/phishtank-mcp-server
MCP server Claude CodeCodexCursor +2
MCP server "phishtank-mcp-server" as configured in Cyreslab-AI/phishtank-mcp-server. Runs locally from the phishtank-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Intelligent log analysis for LLMs - extract patterns, redact secrets, compress 50%+. Runs locally from the log-essence Python package.
Skill Claude CodeCodex
MCP server providing 45 tools for AI agent trust verification, identity, and reputation scoring.
MCP server Claude CodeCodexCursor +2
Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls. Runs locally from the mcp-audit-proxy npm package.
Skill Claude Code
Audit a browser fingerprint for internal contradictions with the liarjs CLI - canvas, WebGL, WebGL2, WebGPU, audio, 220 fonts, WebRTC and timezone probes, scored against the TLS/HTTP/ASN view of the same request. Use when asked to run a browser fingerprint test, see what a fingerprint looks like, check canvas or WebGL…
Skill Claude CodeCodex
This is a multi-file skill: individual entry points intentionally implement only their documented role while the package provides the workflow as a whole. Scan AI agent skills, plugins, and MCP servers for malicious code BEFORE installation — catches prompt injection, credential theft, data exfiltration, and…
Skill Claude Code
Use when the user asks about ISO/IEC 27001:2022 from an engineering perspective — building an ISMS that runs on systems and code rather than spreadsheets, instrumenting Annex A controls, designing risk registers as data, and producing evidence pipelines that hold up to a certification audit. Engineer-voice, not…
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: