27,008 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.
pr3m/claude-code-bash-smart-approve
Plugin Claude Code
Bundles 8 skills, 1 hook · 428 tokens together
Auto-approves Claude Code Bash commands via AST-based allowlist. Handles pipes, subshells, compound commands, and env-var prefixes that literal Bash(...) prefix rules can't match.
Plugin Claude Code
Bundles 1 skill, 4 commands, 1 hook · 151 tokens together
Auto-detects API keys and secrets in your prompts, saves them to chmod-600 files in /.claude/secrets/, blocks the original prompt, and re-submits a sanitized version via OS-level paste automation. Cross-platform (macOS, Linux, Windows). Zero-friction secret hygiene for Claude Code.
ReviewToolkits/cpython-security-toolkit
Command Claude Code
Protocol validation coverage analysis. Checks whether security-sensitive values in CPython's HTTP, cookie, WSGI, and URL handling modules are validated consistently across all code paths — including update methods, operator overloads, unpickling, and template substitution paths.
kousthubha-sky/indian-law-plugin
Cursor rule Cursor
Indian law compliance audit (DPDP, IT Act, CERT-In, RBI, accessibility).
makigjuro/cloudstack-ai-plugins
Plugin Claude Code
Bundles 8 skills, 1 agent · 375 tokens together
Cloud layer of the cloudstack reference architecture — Terraform/Terragrunt for Azure Container Apps (or AKS + Helm), with linting, trivy security scans, plan-before-apply, and infrastructure review.
Plugin Claude Code
Bundles 28 skills, 41 agents, 3 hooks · 3,410 tokens together
AI development team environment. TDD workflow, security audit, pattern learning, and phase-boundary compaction.
Plugin Claude Code
Bundles 1 skill · 151 tokens together
Audit a private git repo's full history (every branch, tag, and PR ref) for secrets and PII before making it public, then carry out the cleanup.
Plugin Claude Code
Bundles 3 skills, 1 command, 18 agents · 940 tokens together
Local pentest sandbox for black-box, greybox, and white-box security audits inside a per-engagement Kali Docker container.
joshuafuller/claude-spill-scrub
Plugin Claude Code
Bundles 1 skill · 102 tokens together
Find and scrub credentials that leaked into Claude Code's own local logs. Scan is read-only, scrub is gated, and every run ends on a rotation checklist.
Skill Claude CodeCodex
The Dependency Auditor is a comprehensive toolkit for analyzing, auditing, and managing dependencies across multi-language software projects. This skill provides deep visibility into your project's dependency ecosystem, enabling teams to identify vulnerabilities, ensure license compliance, optimize dependency trees…
Cursor rule Cursor
Supabase Postgres SQL RLS Row Level Security Guide.
Agent Claude Code
Use this agent when you need to actively test applications, APIs, infrastructure, or code for exploitable vulnerabilities. This agent thinks like an attacker and finds entry points before real attackers do. It complements the security-master agent through practical attack simulation. This agent should be used…
Plugin Claude Code
Context-aware safety guard for Claude Code tool calls.
OnyxynO/plugin-claude-npm-bun-guard
Plugin Claude Code
Modèle de garde-fou d'installation npm/bun : refuse les paquets malveillants connus (arbre transitif inclus) et met en quarantaine les versions publiées depuis moins de 3 jours.
virtualsms-io/cursor-rules-sms-verification
Cursor rule Cursor
Real-SIM SMS verification, number rentals, matching-country proxies and cloud browser sessions for AI agents via VirtualSMS MCP. Apply when the user asks for a phone number, SMS code, OTP, account verification (WhatsApp, Telegram, Tinder, Discord, Google, etc.), two-factor auth flow, number rental, proxy, or anything…
Skill Claude CodeCodex needs its repo
A deliberately malicious demo Skill that tries to exfiltrate secrets over the network and read /.ssh/idrsa. Used to show Capsule blocking the calls at the call site.
Plugin Claude Code
Bundles 1 skill, 5 agents · 170 tokens together
Evidence-first source security scan workflow for human-written and AI-generated code.
Skill Claude CodeCodex
Use when performing strict read-only SSH inspections of Ubuntu/Linux servers for security review, EU cybersecurity compliance evidence, server readiness, operational disorder, waste, drift, CIS-style hardening gaps, runtime visibility, identity/access, network exposure, backups, observability, and unknowns. Requires…
Skill Claude CodeCodex
Use when a project needs the OpenSpec + Superpowers sdd-tdd (spec-to-plan-to-TDD) workflow checked, installed, and configured -- or cleanly removed -- in any coding agent (Codex, Claude Code, Cursor, Antigravity, OpenCode, Gemini CLI, Copilot CLI, or others).
Skill Claude CodeCodex
A PASS/FAIL/N/A checklist covering injection, authorization, secrets handling, dependency risk, and input validation for reviewing a diff or codebase.
Settings file Claude Code
One of 3 in settings.json
Agent settings declaring 2 hook events (PreToolUse, PostToolUse).
Skill Claude CodeCodex
The user runs /vapt auth or this skill is triggered as part of Wave 3 during /vapt audit.
Plugin Claude Code
Bundles 1 skill · 99 tokens together
Check MCP servers against the PolicyLayer registry before connecting to them.
Skill Claude CodeCodex
Turn requirements into validated, executable plans. C31-brainstorm defines WHAT; C31-plan defines HOW — with coverage gates, wave analysis, and threat modeling.
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: