What problem does it solve?
Brownfield projects often lack a clear, up-to-date overview of what the codebase already does, so downstream work starts with wrong assumptions and produces inconsistent PRDs, UX, architecture, and implementation plans.
Core Features & Use Cases
- Brownfield/Greenfield/Hybrid discovery: Walks the existing repository to determine whether the project is brownfield, greenfield, or hybrid so later skills adapt their behavior.
- Architecture + conventions mapping: Extracts structure, entry points, architectural patterns, data flow, dependencies, conventions, error handling, logging, and config management.
- Documentation freshness audit: Classifies discovered docs as fresh, stale, or unknown (with explicit warnings for stale docs) to prevent outdated guidance from driving decisions.
- Deterministic outputs for the pipeline: Produces project-context.md and updates state.yaml under pipeline.phases.context so later skills can reliably consume the results.
Quick Start
Run aped-context first to generate project-context.md from your existing codebase before aped-analyze on that same project.