Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By ed3dai
Orchestrates parallel AI subagents (Haiku, Sonnet, Opus) to analyze large code/text corpora that exceed single-agent context, with automatic model selection based on task complexity
npx claudepluginhub ed3dai/ed3d-plugins --plugin ed3d-basic-agentsAn unprompted generic subagent. Uses Haiku. Intended for tasks that require less thinking and analysis. Good for summarization, research, and tool calls.
An unprompted generic subagent. Uses Opus. Intended for tasks that require deep reasoning, complex analysis, or nuanced judgment.
An unprompted generic subagent. Uses Sonnet. Intended for tasks that require attention to detail, thinking, and analysis.
Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic review subagents, and a final Summarizer subagent with task tracking and failure recovery
Use to decide what kind of generic agent you should use
Uses power tools
Uses Bash, Write, or Edit tools
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.
Agents used for research across multiple data sources. Other plugins expect this one to be enabled.
Multi-agent collaboration plugin for Claude Code. Spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any problem that benefits from diverse solutions. Evaluate by metric or LLM judge, merge the winner. 7 slash commands, agent templates, git DAG orchestration, message board coordination.
Dynamic orchestrator plugin — 200+ agents, 200+ skills, hooks, and MCP servers. Upstream sources linked via git submodules (agency-agents, everything-claude-code, oh-my-claudecode, gstack, superpowers)
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Agents used for research across multiple data sources. Other plugins expect this one to be enabled.
EXPERIMENTAL. Session awareness and conversation review tooling. Captures session metadata via SessionStart hook and provides conversation review agents and skills for analyzing prompting effectiveness, agent performance, and environment gaps.
Playwright automation toolkit with MCP integration, specialized agent for browser control, and best practice skills
Getting started guide and onboarding for ed3d-plugins
Ed's stylistic particulars for writing code and English.
This is my collection of plugins that I use on a day-to-day basis for getting stuff done with Claude Code. Most of these are development-oriented in some way or another, but also often end up being useful for other things. Product design, general research, accidentally becoming my homelab sysadmin—these are a lot of what I've learned so far and what I've found helpful.
The big stick in this repository is ed3d-plan-and-execute, which implements an "RPI" (research-plan-implement) loop that I think does a really good job of avoiding hallucination in the planning stages, adhering to high-level product requirements, avoiding drift between design planning and implementation planning, and reviewing the results such that you get out the other end not just what you asked for, but what you actually wanted.
NOTE: ed3d-plugins is generally a more stable marketplace. If you'd like to track changes as they happen a bit more aggressively, take a look at ed3d-plugins-testing.
ed3d-plan-and-executeMore in the README for the plugin, and it's worth skimming, but here's a quickstart:
Rough Idea
│
▼
/start-design-plan ──────► Design Document (committed to git)
│
▼
/start-implementation-plan ──► Implementation Plan (phase files)
│
▼
/execute-implementation-plan ──► Working Code (reviewed & committed)
Customization: Create .ed3d/design-plan-guidance.md and .ed3d/implementation-plan-guidance.md in your project to provide project-specific constraints, terminology, and standards. Run /how-to-customize for details.
| Plugin | Description |
|---|---|
ed3d-00-getting-started | Getting started guide and onboarding for ed3d-plugins. Run /getting-started to see this README. |
ed3d-plan-and-execute | Planning and execution workflows for Claude Code. Feed it a decent-sized task and it'll help you get it done in a sustainable and thought-through way |
ed3d-house-style | House style for software development; Very Opinionated |
ed3d-basic-agents | Core agents for general-purpose tasks (haiku, sonnet, opus). Other plugins expect this to exist |
ed3d-research-agents | Agents for research across multiple data sources (codebase, internet, combined); other plugins expect this to exist |
ed3d-extending-claude | Knowledge skills for extending Claude Code: plugins, commands, agents, skills, hooks, MCP servers. Other plugins expect this to exist |
ed3d-playwright | Playwright automation with subagents |
ed3d-hook-skill-reinforcement | UserPromptSubmit hook that reinforces the need to activate skills—helps make sure skills actually get used. Requires ed3d-extending-claude to work |
ed3d-hook-claudemd-reminder | PostToolUse hook that reminds to update CLAUDE.md before committing |
ed3d-hook-security-hardening | PreToolUse and PostToolUse hooks that catch secrets leakage patterns |
ed3d-session-reflection | EXPERIMENTAL. Session awareness and conversation review tooling. Requires ed3d-extending-claude |
/plugin marketplace add https://github.com/ed3dai/ed3d-plugins.git
All plugins are available from the ed3d-plugins marketplace:
/plugin install ed3d-plan-and-execute@ed3d-plugins
/plugin install ed3d-house-style@ed3d-plugins
# ... etc
ed3d-plugins/
├── .claude-plugin/
│ └── marketplace.json
├── plugins/
│ ├── ed3d-00-getting-started/
│ ├── ed3d-plan-and-execute/
│ ├── ed3d-house-style/
│ ├── ed3d-basic-agents/
│ ├── ed3d-research-agents/
│ ├── ed3d-extending-claude/
│ ├── ed3d-playwright/
│ ├── ed3d-hook-skill-reinforcement/
│ ├── ed3d-hook-claudemd-reminder/
│ ├── ed3d-hook-security-hardening/
│ └── ed3d-session-reflection/
└── README.md
Issues and pull requests gratefully solicited, except ed3d-house-style is my house style, and provided for reference, so I might not take contributions there. (You can make your own house-style plugin though and use that instead!)
ed3d-plan-and-execute and parts of ed3d-extending-claude are derived from obra/superpowers by Jesse Vincent. The original plugin has been folded, spindled, and mutilated extensively.
Some skills in ed3d-house-style are derived from obra/superpowers and others (property-based-testing is a big one) are derived from the Trail of Bits Skills repository.
The original obra/superpowers code in this repository is licensed under the MIT License, copyright Jesse Vincent. See plugins/ed3d-plan-and-execute/LICENSE.superpowers.