Pythoughts-labs/claude-architect
18 stars · Last commit 2026-07-31
Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.
README preview
<p align="center"> <img src="assets/banner.svg?v=6" alt="Claude Architect: CLI coding-agent orchestration for Claude" width="880"> </p> <p align="center"> <a href="#quick-start"><img alt="delegate skill" src="https://img.shields.io/badge/skill-delegate-e6edf3?style=flat-square&labelColor=0b0e14"></a> <a href="#direct-codex-cli"><img alt="codex skill" src="https://img.shields.io/badge/skill-codex-e6edf3?style=flat-square&labelColor=0b0e14"></a> </p> <p align="center"> <img alt="Claude Code" src="https://img.shields.io/badge/Claude_Code-plugin-d97757?style=flat-square&labelColor=0b0e14"> <img alt="OpenCode" src="https://img.shields.io/badge/OpenCode-native-58a6ff?style=flat-square&labelColor=0b0e14"> <img alt="version" src="https://img.shields.io/badge/version-0.43.0-9aa4b2?style=flat-square&labelColor=0b0e14"> <img alt="license" src="https://img.shields.io/badge/license-MIT-3fb950?style=flat-square&labelColor=0b0e14"> </p> **Verified coding-agent delegation for Claude Code.** Claude stays the architect and reviewer — it writes the spec, judges the evidence, and reports what landed. Implementation is delegated to fresh-context subagent implementers running on the coding CLI you choose — **Codex, OpenCode, Pi, or Pythinker** — each invocation starting clean with no inherited conversation state, inside an isolated Git worktree. The work comes back as a frozen, hash-anchored candidate that Claude reviews against independent verification evidence before a single byte can reach your checkout. In practice that means three guarantees the plugin enforces in host code, not in prompts: