What problem does it solve? AI coding agents produce poor output when they receive too little context (hallucinated APIs, ignored conventions) or too much context (lost focus, degraded quality). This Skill provides a systematic method for deciding what information an agent sees, when it sees it, and how it is structured across a session. ## Core Features & Use Cases - Five-Level Context Hierarchy: Organizes context from persistent rules files (AGENTS.md, CLAUDE.md, .cursorrules) down through specs, source files, error output, and conversation history. - Context Packing Strategies: Provides templates like the Brain Dump, Selective Include, and Hierarchical Summary for loading focused context per task. - Confusion Management: Defines explicit patterns for surfacing conflicting specs, missing requirements, and ambiguity instead of silently guessing. - Use Case: When starting a new feature, you load only the relevant spec section, the files to modify, one existing pattern example, and the project rules file — keeping context under roughly 2,000 focused lines so the agent follows conventions instead of inventing them. ## Quick Start Ask the agent to set up a context plan for your project by creating an AGENTS.md rules file and selecting only the files relevant to your current task.
