Comprehensive PR reviews with feedback on code quality, security, and best practices.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and simplification.
Generate and publish a living project status page as a shareable claude.ai artifact.
Prompt-engineering toolkit adding commands and agents to craft, refine, and evaluate prompts in Claude Code.
Cedar policy enforcement plus Ed25519 signed receipts for every Claude Code tool call.
Community Cursor plugin (by Lauren Tan) with rigorous, parallelizable agent workflows for higher-quality code.
Python language server (Pyright) integration for type checking and code intelligence in Claude Code.
Multi-agent QA toolkit with 10 specialized agents spanning the full QA lifecycle.
Reusable agent skills for code quality checks, automated testing, and security scanning workflows.
Quantitative trading stack for Claude Code with risk management, circuit breakers, and execution hooks.
Claude Code plugin providing an autonomous AI copywriter with a skill, a command, and a hook.
Interactive self-referential AI loops (the Ralph Wiggum technique) for iterative development until completion.
Interactive self-referential AI loops that rerun the same task until completion.
Continuous memory for Claude Code — extracts and compresses conversations into tiered daily logs.
Deploy, debug, and monitor apps on Render with skills, an agent, commands, and a render.yaml validation hook.
Binary reverse engineering, malware analysis, and firmware security for authorized security research.
Requires human approval before an AI agent can post PR reviews, merge, or write to CI configuration.
Full-lifecycle incident management — deploy safety, incident response, on-call, and retrospectives.
RunAPI MCP server for browsing models and creating image, video, music, audio, and LLM tasks.
Rust language server (rust-analyzer) integration for code intelligence and analysis.
Circuit breakers, kill switches, approval guards, and safety mechanisms for production agent systems.
Circuit breakers, kill switches, approval guards, and safety mechanisms for production agent systems.
Anthropic plugin that reviews each code change for vulnerabilities across three checkpoints and instructs Claude to fix them.
SOC2, HIPAA, and GDPR compliance validation with secrets scanning and regulatory documentation.