Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By jeffrigby
Systematically audit codebases for dead code, security vulnerabilities, technical debt, and performance issues, generating prioritized reports with action plans. Keep project docs (CLAUDE.md, README, CHANGELOG) synced with code by analyzing git history and detecting undocumented changes.
npx claudepluginhub jeffrigby/somepulp-agents --plugin codebase-healthYou are a dead code detection agent that finds unused code and helps users clean it up. You use automated tools (knip for JS/TS, deadcode for Python) combined with manual verification to filter false positives.
**IMPORTANT: This is an ON-DEMAND tool that should ONLY be run when explicitly requested by the user. This is a comprehensive, resource-intensive analysis that should NOT be triggered automatically or proactively. Only run when the user specifically asks for a deep audit.**
You are a documentation maintenance agent that keeps project documentation current, consistent, and optimized for AI coding agents. You analyze git history to find undocumented changes, verify documentation accuracy, and apply updates.
This skill should be used when the user asks to "audit code", "find technical debt", "perform a security review", "identify dead code", "analyze code quality", "check best practices", "run a code audit", or needs a systematic methodology for comprehensive codebase analysis.
This skill should be used when the user asks to "update docs", "sync documentation", "update CLAUDE.md", "update README", "check documentation freshness", "document recent changes", "optimize docs for AI", or needs guidance on keeping project documentation current and optimized for AI agents.
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Audit Claude Code plugins and skills for best practices, deprecations, compatibility, usability, coverage gaps, duplication, and workflow optimization
Audit and optimize Claude Code configurations with dynamic best-practice research
Helps Claude read a planning document and explore related files to get familiar with a topic. Asking Claude to prepare to discuss seems to work better than asking it to prepare to do specific work. This is followed by Plan, then Execute.
Comprehensive Claude Code ecosystem plugin with official documentation management, meta-skills, development guidance, event logging, and observability hooks. Provides keyword-based doc discovery, doc_id resolution, token-optimized subsection extraction, authoritative knowledge hubs for hooks, memory, skills, MCP, configuration, security, subagents, plugins, and more. Includes comprehensive hook event logging, date/time injection, and file validation.
Audit codebase documentation for accuracy, completeness, and freshness against actual code. Auto-fixes small discrepancies, reports structural changes. Companion to agent-ready.
Structured codebase health attributes with severity-based agent routing
Research libraries, frameworks, and APIs using official documentation. Includes /research for comprehensive investigation and /official-docs for pre-task doc lookups. Works best with Context7 and Fetch MCP servers installed (falls back to WebSearch/WebFetch if unavailable).
A plugin marketplace for Claude Code providing specialized agents for code auditing, research, and multi-model consultation.
Claude Code plugins extend functionality through custom slash commands, specialized agents, and skills. Each plugin in this marketplace can be installed independently, letting you pick the tools that fit your workflow.
| Plugin | Description | Contents |
|---|---|---|
| codebase-health | Comprehensive codebase health tools: code audits, dead code detection, and documentation maintenance | Commands: /deep-audit, /dead-code, /update-docsAgents: deep-audit, dead-code-cleanup, update-docsSkills: code-auditing, docs-maintenance |
| second-opinion | Get second opinions from Codex CLI and Gemini CLI | Commands: /codex-opinion, /gemini-opinionAgents: codex-consultant, gemini-consultantSkill: ai-consultation |
| research-assistant | Research libraries and APIs using official documentation | Commands: /research, /official-docsAgents: research-assistant, official-docsMCP: Context7, Fetch |
Add the marketplace to Claude Code:
/plugin marketplace add jeffrigby/somepulp-agents
Install the plugins you want:
/plugin install codebase-health@somepulp-agents
/plugin install second-opinion@somepulp-agents
/plugin install research-assistant@somepulp-agents
Or use the interactive /plugin command to browse and install.
# Clone the repository
git clone https://github.com/jeffrigby/somepulp-agents.git
# In Claude Code, add as local marketplace
/plugin marketplace add /path/to/somepulp-agents
# Then install the plugins you want
/plugin install codebase-health@somepulp-agents
| Plugin | Requirements |
|---|---|
| research-assistant | Recommended: Context7 and Fetch MCP servers (install separately). Falls back to WebSearch/WebFetch if unavailable. |
| second-opinion | OpenAI Codex CLI + OPENAI_API_KEY or CODEX_API_KEY for Codex; Google Gemini CLI + Google OAuth or GEMINI_API_KEY for Gemini |
Each plugin follows the standard Claude Code plugin structure:
plugin-name/
├── .claude-plugin/
│ └── plugin.json # Plugin metadata
├── commands/ # Slash commands (optional)
├── agents/ # Specialized agents (optional)
├── skills/ # Agent skills (optional)
├── scripts/ # Helper scripts (optional)
├── .mcp.json # MCP server configuration (optional)
└── README.md # Plugin documentation
Contributions are welcome! Please:
MIT License - see LICENSE for details.