Stack-agnostic monorepo template where agents are the workflow: PM → implementer → fresh-context reviewer loops via Claude Code subagents, skills, and GitHub Actions
This repository also configures its own agents. See what agentic-monorepo-template tells them →
chrille0313/agentic-monorepo-template
Agent Claude Code
Implements exactly one task spec end-to-end and verifies it against the command contract. Use when a spec is ready to build, and when review findings need applying to work already done.
chrille0313/agentic-monorepo-template
Agent Claude Code
Product-manager agent. Reads the backlog, prioritizes, and shapes the next most valuable item into a build-ready task spec. Use when deciding what to work on next, or when a request is too vague to implement and needs acceptance criteria first. Read-only on code; it never implements.
chrille0313/agentic-monorepo-template
Agent Claude Code
Judges a diff strictly against its task spec, grounded in commands it actually ran, and returns a structured APPROVE/REQUESTCHANGES verdict. Read-only on source; never fixes anything itself. Use when finished work needs an independent verdict before it ships.