aped-context

Generate a structured project-context report from an existing codebase.

2|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/yabafre/aped-claude --skill aped-context
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aped-context
Source: https://github.com/yabafre/aped-claude/tree/main/src/templates/skills/aped-context
Command: npx skills add https://github.com/yabafre/aped-claude --skill aped-context

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bash, git, yq, jq, and includes references (resource) components.

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audit: Classifies discovered docs as fresh, stale, or unknown (with explicit warnings for stale docs) to prevent outdated guidance from driving decisions.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.

Frequently Asked Questions about aped-context

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a project context file from an existing codebase for brownfield migration?

Context mapping classifies an existing repository as brownfield, greenfield, or hybrid by walking the codebase to determine its actual state. This classification ensures later planning phases adapt their behavior to the correct project type, preventing inaccurate assumptions.

How do I audit documentation freshness for a legacy codebase before planning new features?

Auditing documentation freshness involves scanning the repository to classify discovered docs as fresh, stale, or unknown, and explicitly warning about stale docs. This prevents outdated guidance from driving decisions during brownfield onboarding and hybrid feature planning.

What is the best way to extract architecture and conventions from a legacy repository?

The best way to extract architecture and conventions is to scan the existing codebase for entry points, data flow, dependencies, error handling, logging, and config management. This maps the structural patterns into a deterministic report for reliable downstream pipeline consumption.

Do I need bash and jq installed to run a codebase analysis scan?

Yes, you need bash, git, yq, and jq installed to perform a codebase analysis scan. The scan requires resolving APED config.yaml variables, running enabled-gate checks, and safely scanning code and docs to write the final context outputs.

Can I use architecture mapping on a hybrid project with new features in a legacy system?

Yes, architecture mapping applies to hybrid projects with new features in a legacy system. It scans the existing structure, classifies the project state, and updates state.yaml so downstream skills adapt their planning behavior to the hybrid context.