By dgca
Let's Fucking Go - Break down large work into manageable pieces and execute efficiently with subagents.
Execute planned tasks through exploration, wave-based execution, QA verification, and learning accumulation.
Show available LFG commands, their purposes, and current project state
Initialize a new LFG project. Detects greenfield vs brownfield, gathers project context, and creates the .lfg/ directory structure.
Map the codebase structure using parallel Explorer agents. Creates STACK.md, ARCHITECTURE.md, PATTERNS.md, and CONCERNS.md in .lfg/codebase/.
Context-aware planning. Creates new epics with milestones, or breaks down existing milestones into executable tasks.
Task execution agent that implements planned tasks with atomic commits. Use for executing individual tasks from a milestone plan.
Fast codebase exploration agent for mapping files, identifying patterns, and surfacing concerns. Use for quick reconnaissance before planning or execution.
Project Manager agent for breaking down epics into milestones and milestones into tasks. Use for planning work with proper dependencies and requirements tracking.
Quality assurance agent that independently verifies completed tasks. Never trusts — always verifies.
Deep research agent for investigating technologies, APIs, and approaches before planning. Use when research_depth is set to "deep" or specific research is needed.
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
Executes directly as bash, bypassing the AI model
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.
Plugins and skills that make Claude Code more effective for real work.
| Component | Type | What It Does |
|---|---|---|
| assume-persona | plugin | Load expert personas for domain-specific assistance |
| lfg | plugin | Break down large work into tasks and execute with subagents |
| create-skill | skill | Guide for building your own Claude Code skills |
Add the marketplace, then install individual plugins:
# Add the marketplace
/plugin marketplace add dgca/mai
# Install plugins you want
/plugin install assume-persona@mai
/plugin install lfg@mai
Requires Node.js 22.6.0+.
Create and load expert personas for domain-specific assistance. Define a React architect, security auditor, or any specialist—Claude adopts their expertise and perspective.
Key features:
See plugins/assume-persona for full documentation.
Let's Fucking Go — structured project management for AI-assisted development. Break large, ambiguous work into right-sized pieces that Claude can execute reliably.
Key features:
See plugins/lfg for full documentation.
A guide for building skills that extend Claude's capabilities. Covers skill structure, YAML frontmatter, bundled resources (scripts, references, assets), and best practices.
npx claudepluginhub p/dgca-lfg-plugins-lfgAssume subject matter expert personas for better domain-specific assistance.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
18 universal AI skills for Claude Code — skill creation, deep research, strategic planning, content processing, solution architecture, and orchestration workflows
AI artifact engineering: prompts, skills, subagents, and output styles
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems