Metho Agentic — AI skill for Claude Code
Scaffold AI-powered projects with built-in methodology.
How to install Metho Agentic
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open iLomer/Metho_agentic and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Metho Agentic does
Scaffold AI-powered projects with built-in methodology. Agents, memory, kanban and governance out of the box. Works with Claude Code.
Alternatives in AI
- Cindy — Consider it done 2.3k ★
- Mex — Persistent project memory for AI coding agents 672 ★
- Cwc Long Running Agents — Claude Code's built-in /goal command gives you a generator/evaluator loop out of the box: set a completion con 668 ★
README
Meto
Lovable gives you an app. Meto gives you a project -- built the right way, your way.
Meto scaffolds structured software projects with built-in methodology. You describe what you want to build, and Meto bootstraps a project with AI-generated epics, a sliced backlog, agent definitions, product context, and coding conventions -- ready for your first Claude Code session.

Quick Start
npx meto-cli init
Answer a few questions, and Meto generates a fully structured repository in seconds -- with AI-powered content if Claude Code is installed.
**Already have a project?** Run the audit to bring it up to standard:
cd your-existing-project
npx meto-cli audit
How It Works
Meto detects whether Claude Code is installed on your machine and offers two paths:
**With Claude Code (AI-powered):**
- You answer 5 questions -- project name, description, target users, tech stack, output directory
- Choose your workflow mode -- Sprint (sequential) or Swarm (parallel epic agents)
- Select any MCP integrations to pre-configure for your project (GitHub, Sentry, PostgreSQL)
- Claude Code generates your product vision, problem statement, epics, and a sliced backlog with acceptance criteria
- Meto renders everything --
.claude/settings.jsonpre-configured with your stack's permission allowlist,.mcp.jsongenerated if you selected integrations - Context7, Sequential Thinking MCP, and ccstatusline are installed into your Claude Code environment automatically
**Without Claude Code (static):**
- You answer 10 questions -- the 5 above plus problem statement, success criteria, value proposition, out of scope, and code conventions
- Choose your workflow mode -- Sprint or Swarm
- Select any MCP integrations to pre-configure for your project (GitHub, Sentry, PostgreSQL)
- Meto renders your answers into the same structured project -- `.claude/
Related Skills
CoworkOS
A minimal, installable template for running an AI agent as a persistent, structured assistant: a routing proto
Vellum
Vellum: an auditable agentic ICD-10-CM/PCS autocoder that proves every code and catches the model fabricating
Claude Agent Lab
RAG-powered CLI code assistant with agentic task planning, MCP tool integration, semantic caching, and session
Metaharness
🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MC
Agent Handoff Kit
為 Agentic AI 新手友好的輕量項目記憶與治理套件:把狀態、決策、下一步、文件地圖、新手引導與工具邊界寫成標準檔案,讓不同 AI 工具可在同一項目資料夾內跨 Session 對話延續工作。 A beginner-
AI Visibility Dashboard Kit
Look at the questions you track in AI assistants, find out which numbers are worth a dashboard, then have a co
Related Agents
Reconcile Agent
Reads the findings from finished steps and works out what they change for the steps not yet built — stale path
Domain Extractor
Layer-0 subagent for the rev-3 agentic-ontology methodology. Reads the target project's live documentation (We
Acx Handoff
AgentCortex /handoff phase executor. Use when delegating handoff work that must produce a resumable state summ