I built a CLI that scaffolds agentic workflows for Claude Code

Developer Patrick Sardinha built AgentKit, a CLI tool that automatically generates orchestration files for Claude Code to manage multi-agent workflows. The tool creates markdown-based agent definitions, success criteria, and handoff procedures from a plain-language blueprint, enabling Claude Code to decompose tasks into specialized agents that run sequentially with automatic retry and escalation. AgentKit was used to build DevLog Desktop, a Tauri v2 app with local RAG via Ollama, in a single Claude Code session.

Most developers using Claude Code work the same way: one long conversation, manual prompting between tasks, context that grows until the model loses track of what it was doing. It works — but it doesn't scale. I built AgentKit to fix this. It's a CLI that generates the orchestration layer for any project: the files that tell Claude Code who to be, what to build, and how to hand off work between specialized agents — automatically. You write a plain-language blueprint describing what you want to build: Todo App — Blueprint Goal A simple web todo app with task creation, completion, and filtering. Tech constraints - Next.js 14 + TypeScript + Tailwind - localStorage for persistence, no backend You run one command: npx @patricksardinha/agentkit-cli init --blueprint PROJECT BLUEPRINT.md AgentKit generates four files: Then you open Claude Code and type one instruction: Read PLAYBOOK.md and execute the procedure. Claude Code runs in three phases automatically. Phase 0 — Decomposition : it reads your blueprint and proposes a list of specialized agents. You validate before anything gets built. Skills enrichment pause : Claude Code creates the agent folders and waits. You can drop API docs, schemas, or any context files into the relevant agent folder before execution starts. Phase 1 — Execution : each agent runs in sequence, validates its success criterion, retries on failure, and escalates to you only when genuinely blocked. I used AgentKit to build DevLog Desktop — a Tauri v2 app with local RAG via Ollama. Result after one Claude Code session: No AI inside the tool. AgentKit is purely structural — it generates markdown files. The intelligence lives in Claude Code, not in AgentKit. This means no API key, no costs, no vendor lock-in. Phase 0 always runs. Most developers don't know how to optimally split work into agents. AgentKit delegates that decision to Claude Code every time, whether or not you provide a blueprint. You describe intent, Claude Code designs the structure. Stack detection first, interactive fallback. AgentKit reads your project directory to detect the stack. If nothing is found new empty project , it asks you interactively from a list of supported stacks: React, Next.js, Tauri, FastAPI, Express, Node.js. On any project empty or existing npx @patricksardinha/agentkit-cli init With a blueprint npx @patricksardinha/agentkit-cli init --blueprint PROJECT BLUEPRINT.md Add a feature to an existing project npx @patricksardinha/agentkit-cli add --feature "add dark mode" GitHub: https://github.com/patricksardinha/agentkit-cli https://github.com/patricksardinha/agentkit-cli npm: https://www.npmjs.com/package/@patricksardinha/agentkit-cli https://www.npmjs.com/package/@patricksardinha/agentkit-cli Feedback welcome.