Agent Plugins Marketplace

Recently added

Plugins grouped by the day they were added to the directory, newest first.

Aug 9, 2026

  1. Detects signature replay vulnerabilities in smart contracts — the vulnerability class affecting 19.63% of signature-using contracts. Covers same-chain, cross-chain, and cross-contract replay attacks, EIP-712 domain separator verification, nonce management analysis, ecrecover edge cases, permit/permit2 safety, and meta-transaction security.

    Claude Code1 skill
  2. Detects logic vulnerabilities in smart contracts by analyzing guard-state consistency patterns. Uses the Consistency Principle to find functions that bypass security checks (require, modifiers) established by the contract's own patterns.

    Claude Code1 skill
  3. Systematic detection of all reentrancy variants in smart contracts — classic, cross-function, cross-contract, and read-only reentrancy. Verifies CEI pattern compliance, traces external call positions relative to state changes, and detects callback-based attack vectors through ERC-777/ERC-1155 hooks.

    Claude Code1 skill
  4. Detects vulnerabilities in upgradeable proxy smart contracts — storage layout collisions, uninitialized implementations, function selector clashing, and upgrade path safety issues. Covers Transparent, UUPS, Beacon, Diamond (EIP-2535), and Minimal proxy patterns. Critical for the 54.2% of Ethereum contracts that use proxy architecture.

    Claude Code1 skill
  5. Detects price oracle manipulation and flash loan attack vectors in DeFi smart contracts. Classifies oracle trust models (Chainlink, TWAP, spot price), identifies stale price risks, circular dependencies, and flash loan atomicity exploitation patterns. Covers the #2 OWASP Smart Contract vulnerability category.

    Claude Code1 skill
  6. Detects input validation failures and arithmetic vulnerabilities in smart contracts — the #1 direct exploitation cause at 34.6% of cases. Covers missing zero-checks, precision loss from division-before-multiplication, rounding direction exploitation, ERC4626 inflation attacks, unsafe casting, dust amount exploitation, and Solidity 0.8+ edge cases in unchecked blocks.

    Claude Code1 skill
  7. Detects unsafe external call patterns and token integration vulnerabilities in smart contracts. Covers unchecked call return values, fee-on-transfer tokens, rebasing tokens, missing ERC20 return values (USDT), ERC-777 callback risks, unsafe approve patterns, return data bombs, and pull vs push payment analysis. Addresses OWASP SC06.

    Claude Code1 skill
  8. Detects Denial of Service and griefing vulnerabilities in smart contracts — OWASP SC10. Covers unbounded loops, block gas limit exhaustion, external call failure DoS, insufficient gas griefing (63/64 rule), storage bloat, timestamp griefing, self-destruct force-feeding, and push vs pull payment pattern analysis.

    Claude Code1 skill
  9. Multi-dimensional smart contract security auditing using Behavioral State Analysis (BSA). Combines behavioral intent extraction, parallel threat engines (economic, access control, state integrity), adversarial simulation with PoC generation, and Bayesian confidence scoring.

    Claude Code1 skill
  10. Terraform provider development skills for Claude Code, including resources, data sources, actions, and acceptance testing.

    Claude Code6 skills
  11. Terraform Policy skills for authoring .policy.hcl files, writing .policytest.hcl tests, and converting Sentinel policies to Terraform Policy.

    Claude Code1 skill1 MCP server
  12. Terraform module generation and refactoring skills for Claude Code, including module design and Terraform Stacks.

    Claude Code2 skills1 MCP server
  13. Terraform code generation skills for Claude Code, including HCL generation, style guides, and testing.

    Claude Code4 skills1 MCP server
  14. packer-hcp791stars

    HCP Packer registry integration for tracking and managing image metadata.

    Claude Code1 skill
  15. Packer builder skills for AWS, Azure, and Windows image creation.

    Claude Code3 skills
  16. Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

    Claude Code
  17. ralph-wiggum961stars

    Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.

    Claude Code
  18. Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

    Claude Code
  19. plugin-dev961stars

    Comprehensive toolkit for developing Claude Code plugins. Includes expert skills covering hooks, MCP integration, commands, agents, and best practices.

    Claude Code
  20. Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)

    Claude Code
  21. hookify961stars

    Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns

    Claude Code
  22. Lightweight gstack-inspired engineering workflows for OPC: investigation, review, security, QA reporting, and documentation release checks.

    Claude Code5 skills
  23. Frontend design skill for UI/UX implementation

    Claude Code1 skill
  24. feature-dev961stars

    Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

    Claude Code
  25. Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)

    Claude Code
  26. Streamline your git workflow with simple commands for committing, pushing, and creating pull requests

    Claude Code
  27. code-review961stars

    Automated code review for pull requests using multiple specialized agents with confidence-based scoring

    Claude Code
  28. Migrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.

    Claude Code1 skill
  29. Claude Agent SDK Development Plugin

    Claude Code
  30. Research, search, and analysis specialists - market research, competitive analysis, trend forecasting, and idea validation

    Claude Code
  31. voltagent-meta25.5kstars

    Agent coordination and meta-programming - multi-agent orchestration, workflow automation, and safe refactor governance. Works best with other voltagent plugins installed.

    Claude Code
  32. voltagent-biz25.5kstars

    Product, legal, and business specialists - product strategy, licensing, project management, UX research

    Claude Code
  33. Domain-specific technology experts - blockchain, fintech, gaming, IoT, payments, X/Twitter APIs

    Claude Code
  34. Tooling and developer productivity experts - CLI tools, documentation, README generation, and DX optimization

    Claude Code
  35. Data engineering, ML, and AI specialists - data pipelines, machine learning, LLM architecture

    Claude Code
  36. Testing, security, and code quality experts - code review, penetration testing, QA automation, and UI flow validation

    Claude Code
  37. voltagent-infra25.5kstars

    DevOps, cloud, and deployment specialists - Kubernetes, Terraform, AWS, Azure, GCP, and SRE

    Claude Code
  38. voltagent-lang25.5kstars

    Language-specific expert agents with deep framework knowledge - Python, TypeScript, Go, Rust, Java, and more

    Claude Code
  39. Essential development subagents for everyday coding tasks - backend, frontend, fullstack, mobile, and API design

    Claude Code
  40. sagemaker-ai856stars

    Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.

    CodexClaude Code19 skills1 MCP server
  41. This no-cost tool assesses your current cloud provider's usage, geography, and billing data to estimate and compare AWS services and pricing, and recommends migration or continued use of your current provider. AWS pricing is based on current published pricing and may vary over time. The tool may generate a .migration folder containing comparison and migration execution data, which you may delete upon completion or use to migrate to AWS.

    Codex
  42. Deploy applications to AWS with architecture recommendations, cost estimates, and IaC deployment. Generate validated AWS architecture diagrams as draw.io XML.

    CodexClaude Code3 skills3 MCP servers
  43. Expert database guidance for the AWS database portfolio. Design schemas, execute queries, handle migrations, and choose the right database for your workload.

    CodexClaude Code1 skill3 MCP servers
  44. Analyze codebases to generate structured technical documentation with source-of-truth citations. Optimized for AWS workloads using CDK, CloudFormation, and Terraform.

    CodexClaude Code1 skill2 MCP servers
  45. Migrate, modernize, and upgrade codebases to AWS. Transforms .NET Framework to .NET 8/10, mainframe COBOL to Java, VMware VMs to EC2, SQL Server to Aurora, and upgrades Java/Python/Node.js versions and AWS SDKs. AWS Transform - continuous modernization analyzes codebases for tech debt, security issues, and upgrade opportunities, then remediates them.

    CodexClaude Code1 skill1 MCP server
  46. Design, build, deploy, test, and debug serverless applications with AWS Serverless services.

    CodexClaude Code7 skills1 MCP server
  47. aws-amplify856stars

    Build full-stack apps with AWS Amplify Gen 2 using guided workflows for authentication, data models, storage, GraphQL APIs, and Lambda functions.

    CodexClaude Code1 skill1 MCP server
  48. Guide developers through adding maps, places search, geocoding, routing, and other geospatial features with Amazon Location Service, including authentication setup, SDK integration, and best practices.

    CodexClaude Code1 skill1 MCP server
  49. Long-term semantic memory for Codex, powered by OpenViking. Recall on UserPromptSubmit, incremental add_message on Stop (per turn), commit on SessionEnd (Codex >= 0.145) and on PreCompact, with an idle/ended sweep on SessionStart as the fallback for signals, crashes and older Codex builds. Includes a local stdio MCP proxy that reads OpenViking credentials from env/ovcli.conf.

    Codex4 skills1 MCP server
  50. Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.

    Claude Code4 skills1 MCP server