core-agents Bundle
The core-agents bundle scaffolds a complete AI agent team into your repository,
ready for spec-to-ship workflows.
What gets installed
| Agent | Role |
|---|---|
ag-architect | Turns feature requests into structured specs, context maps, and ADRs |
ag-coder | Implements backend code from an approved spec |
ag-ui-developer | Implements UI code from an approved spec |
ag-tester | Writes and runs tests, enforces TDD |
A workflow.md file is also installed (e.g. .github/agents/workflow.md) with
the full spec-to-ship sequence.
Install
# Default stacks: dotnet backend, react frontend
ag-skill add core-agents
# Choose a different backend
ag-skill add core-agents --backend python --frontend react
ag-skill add core-agents --backend java --frontend react
ag-skill add core-agents --backend go --frontend react
Stack options
| Flag | Values |
|---|---|
--backend | dotnet (default), python, java, go |
--frontend | react (default) |
See Stack Variants for full details.
How to use the agent team
- Open your AI agent (e.g. GitHub Copilot Chat)
- Select
ag-architectand describe your feature - Architect produces a spec, context map, ADRs, and a summary of artifact file paths
- Approve explicitly when prompted (for example, reply
approved) to allow handoff - Hand the approved spec to
ag-coderandag-ui-developer ag-testerwrites and runs tests against the implementation
See the Workflow Usage Guide for step-by-step instructions.