By stilero
Spawns 11 parallel agents to audit a codebase for technical debt, groups findings into actionable issues, and offers GitHub issue creation
Audits codebase for API design issues: inconsistent endpoint naming, missing pagination, versioning gaps, inconsistent error responses, and missing validation schemas. Spawned by tech-debt-audit command.
Audits codebase for structural issues: circular dependencies, layer violations, pattern inconsistencies, legacy patterns, tight coupling, and missing abstractions. Spawned by tech-debt-audit command.
Audits codebase for code smells: long functions, high complexity, deep nesting, duplication, dead code, magic values, inconsistent naming, and god files. Spawned by tech-debt-audit command.
Audits codebase for over-engineering: unnecessary abstractions, premature generalization, wrapper classes adding no value, indirection layers with single implementations, and enterprise patterns in simple contexts. Spawned by tech-debt-audit command.
Audits codebase for dependency health issues: outdated packages, known CVEs, unused dependencies, unmaintained packages, duplicate versions, and license risks. Spawned by tech-debt-audit command.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A curated directory of plugins for Claude Code.
⚠️ Important: Make sure you trust a plugin before installing, updating, or using it. This directory does not control what MCP servers, files, or other software are included in plugins and cannot verify that they will work as intended or that they won't change. See each plugin's homepage for more information.
Plugins can be installed directly from this marketplace via Claude Code's plugin system.
To Add marketplace, run this command from claude:
/plugin marketplace add stilero/claude-plugins
To Add a specific plugin:
/plugin install pr-comment-fixer@stilero-tools
Each plugin follows a standard structure:
plugin-name/
├── .claude-plugin/
│ └── plugin.json # Plugin metadata (required)
├── .mcp.json # MCP server configuration (optional)
├── commands/ # Slash commands (optional)
├── agents/ # Agent definitions (optional)
├── skills/ # Skill definitions (optional)
└── README.md # Documentation
For more information on developing Claude Code plugins, see the official documentation.
npx claudepluginhub stilero/claude-plugins --plugin tech-debt-auditA persistent, indexed knowledge bank that stores learnings, ADR decisions, technical context, and session notes as markdown files inside your repo. Scales to thousands of files with fast grep-based index lookups. Integrates with Claude hooks for automatic session capture.
Evaluates findings and ideas from conversations and creates high-value GitHub issues. Checks for duplicates before creating, and updates existing issues with new findings instead of creating redundant ones.
A plugin to automatically fix PR comments
A plugin to help with shopify apps
Strict hardcore code reviewer that spawns 12 parallel subagents to review code from every angle: bugs, security, architecture, tests, error handling, performance, complexity, observability, API contracts, data/migrations, accessibility, and type safety
Codebase exploration, refactoring, and quality analysis
Analyze local repos for code health, complexity, test coverage gaps - multi-dimensional health analysis combining complexity + churn + coverage
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
Technical debt reduction, dependency updates, and code refactoring automation
DevOps patterns: CI debugging, tech debt detection, own all failures
Point it at a codebase and it figures out what's worth doing — bugs, perf, tech debt, what to build next — then writes plans any agent can execute. It can hand the work to a cheaper model and review the result. It never edits your code.