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.
oscal-compass/agentic-agile-authoring
Skill Claude Code
Convert a compliance-document PDF (law, regulation, industry standard) into a validated OSCAL Catalog JSON. Use when the user wants to turn a compliance PDF into an OSCAL Catalog, ingest a new framework into the OSCAL ecosystem, or regenerate a catalog from a revised PDF while keeping control IDs stable.
Agent Claude Code
Use when you need a dedicated security audit. Checks for OWASP top 10, injection flaws, auth issues, secrets in code, and insecure dependencies. Invoke before any security-sensitive release.
Skill Claude CodeCodex
Adaptive zero-refusal jailbreak pipeline with static, BPJ, PAIR, TAP, and crescendo strategies + multi-judge scoring + self-improving arsenal.
Plugin Claude Code
Bundles 11 skills · 1,435 tokens together
A leveling-up arcade of Claude Code skills for AppSec and security engineering.
MCP server Claude CodeCodexCursor +2
MCP server "cisco-ise-mcp" as configured in TheOtherBrad/cisco-ise-mcp. Runs locally from the cisco-ise-mcp Python package.
MCP server Claude CodeCodexCursor +2
npm MCP server: registry tools for package metadata, security audits, dependency trees, and write ops (deprecate, dist-tag, owner). Runs locally from the @yawlabs/npmjs-mcp npm package.
Skill Claude CodeCodex
Build communication features with Twilio: SMS messaging, voice calls, WhatsApp Business API, and user verification (2FA). Covers the full spectrum from simple notifications to complex IVR systems and multi-channel authentication.
Plugin Cursor
Tiered AI code-review: triage -> relevant specialist reviewers -> synthesis. Reviews AI-written code using AI agents.
Skill Claude CodeCodex needs its repo
Execute a local task register with requirement tracing, verification, review, and refinement.
Skill Codex
Check whether an MCP server, a published package, or a GitHub repo is safe to connect to or install. AgentAvow answers Safe to connect, Review before you connect, or Do not connect, with the reason, a signed 0-100 trust score and an adoption score. Use when the user asks whether a specific tool, package, repo, or MCP…
Plugin Cursor
Bundles 1 skill, 1 MCP server · 61 tokens together
Checks AI-written code against your rules as it is written, and keeps a record of what it found.
MCP server Claude CodeCodexCursor +2
Agent network intelligence for AI agents. Trust scoring, broker discovery, and Ed25519 identity. Runs locally from the moltbridge npm package. Needs 3 environment variables to run.
Plugin Claude Code
Bundles 20 skills · 1,645 tokens together
Agent skills for Cerbos authorization: author and test policies, distribute them through Cerbos Hub, and enforce them in applications, gateways and AI agents.
Plugin Claude Code
Bundles 1 skill, 5 hooks · 73 tokens together
Signed, offline-verifiable records of the permission decisions Claude Code makes about your agent's tool calls: auto-mode denials, calls that were asked about and then ran, and checks and consequential commands that ran without a prompt. Recalls recent denials at session start.
MCP server Claude CodeCodexCursor +2
Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log. Runs locally from the midplane npm package. Needs 4 environment variables to run.
Skill Claude CodeCodex
Read the user's Oura Ring readiness, sleep, HRV and activity through the local oura MCP server. Use when the user asks about Oura data, readiness score, sleep quality, HRV or resting heart rate trends, or a daily or weekly Oura brief. Starts with connection status, uses synthetic demo data before OAuth, and never asks…
hashgraph-online/hol-guard-plugin
Plugin Claude Code
Bundles 1 skill, 2 commands, 1 MCP server, 1 plugin · 38 tokens together
Install and operate HOL Guard local security for AI coding agents, MCP, skills, plugins, and package actions.
Plugin Claude Code
Bundles 1 skill · 130 tokens together
Sonatype Guide MCP server for software supply chain intelligence and dependency security analysis. Scan dependencies for vulnerabilities, get version recommendations, and check component quality metrics.
Skill Claude CodeCodex
A local encrypted vault for storing passwords, API keys, tokens, and other access details under account or key aliases. It can inject those values into a command’s environment without exposing the plain text to the AI.
MCP server Claude CodeCodexCursor +2
Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing. Runs locally from the @leakferret/mcp npm package.
Agent Claude Code
CTF Coordinator — Triages CTF challenges by category and delegates to specialized agents (web, crypto, forensics, binary, reversing, misc, bonus). user-invocable: true argument-hint: 'Challenge info — e.g.
vignesh2027/claude-best-practice
Agent Claude Code
Use for code review, PR review, security review. Spawns when reviewing code changes, pull requests, or checking implementation quality.
Plugin Claude Code
Bundles 3 skills, 4 commands · 418 tokens together
Offensive hotspot-driven hunt workflow for bugs, pain points, and inefficiencies — 13 analysis lenses, a zero-dependency toolkit (deterministic hotspots, structured findings, fingerprinted dedupe, baseline diffing, SARIF/HTML/markdown reports, CI exit codes), enforceable verification and coverage in CI, a fast…
OutlineDriven/odin-gemini-cli-extension
Skill Claude Code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
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: