Ed's repo of Claude Code plugins, centered around a research-plan-implement workflow. Only a tiny bit cursed. If you're lucky.

Claude Code plugin that transforms vague requirements into detailed implementation plans via research, interviews, and multi-LLM review.

AI-powered development tools. 18 agents, 19 commands, 29 skills, 1 hook, 1 MCP server for code review, research, design, and workflow automation.

Claude-Code-style dynamic workflows for Pi — fan a task out across 100s of subagents with real model routing, token/cost accounting, resume, git-worktree isolation, an interactive /workflows TUI, and a real /deep-research.

A Claude Code plugin that gives Claude persistent memory across sessions — stores lessons and decisions as markdown in your Obsidian vault, searches them with SQLite FTS5, and mines past transcripts automatically.

Claude Code plugin that stops Claude writing like an AI. 29 researched patterns, loaded every session and checked on every file write.

Automates mountain route research for North American peaks. Aggregates data from 10+ mountaineering sources to generate detailed route beta reports with weather, avalanche conditions, and trip reports.

Claude Code plugin for building LLM-maintained Obsidian wikis from raw research — compile, query, lint, and evolve your personal knowledge base. Inspired by Karpathy's knowledge base workflow.

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

ERPAVal — autonomous software development. Six-phase Explore/Research/Plan/Act/Validate/Compound workflow with classifier-driven routing and a compounding lessons store.

Autonomous session memory for Claude Code. Never lose context, never repeat yourself. AI-powered summaries, searchable history, and automatic context injection. 📦 npm install -g memctx

Cross-platform toolkit to enhance Claude Code with multi-LLM consensus, 8 specialist agents, semantic knowledge search, and one-command install.