Claude-Code-Workflow vs pilot-shell
Claude-Code-Workflow: Claude Code Workflow is a JSON-driven multi-agent AI development framework that offers a flexible 4-level workflow system. It enables semantic CLI orchestration across various AI models, dependency-aware parallel execution, and advanced code search capabilities.; pilot-shell: Pilot Shell enhances Claude Code with structured workflows for spec-driven development, efficient bug fixes, and product requirement generation. It integrates quality gates, preserves context, and optimizes token usage, enabling engineers to produce consistent, production-grade code.
Pilot Shell is a maintained spec-driven flow for Claude Code. CCW's repository is archived.
TL;DR
- You are already on CCW and want four workflow levels, from quick fixes to multi-role brainstorming.
- You want to orchestrate Gemini, Qwen, Codex and Claude CLIs from one set of commands.
- You want task state kept as `.task/IMPL-*.json` files with a dashboard.
- You need a maintained tool: our data shows the repository is archived (read-only), with the last push on 2026-06-18.
- You do not want several accounts, keys and bills for several CLIs.
- You need stable local search: CodexLens is marked as in development.
- You use Claude Code and want `/spec` to replace plan mode with discuss, plan, approve, TDD, verify.
- You want separate flows for bugs (`/fix`) and requirements (`/prd`).
- You want teammates to review a spec through a shared link.
- You use an agent other than Claude Code: it only works on top of Claude Code.
- You need clear licence terms: GitHub does not detect a licence, so confirm before using it at work.
- Most of your tasks are small: a full spec flow is heavier than plain Claude Code.
Side-by-Side Comparison
Features
Use Cases
Best For
FAQ
Deploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.