context-engineeringlisted

# Context Engineering Feed the agent the right information at the right time. Context is the single biggest lever for agent output quality — too little and the agent hallucinates, too much and it loses focus. Deliberately curate what the agent sees, when it sees it, and how it's structured. ## When to use - Starting a new coding session or switching between major features. - Agent output quality is declining (wrong patterns, hallucinated APIs, ignoring conventions). - Setting up a new project for AI-assisted development. - The agent is not following project conventions. - Explaining existing code to a user, or giving a codebase tour (see `references/code-explanation.md`). **Not for:** Session-start routing when the task is clear (use `using-skills`); implementing from a spec (use `implement`). ## Steps 1. **Structure context from most persistent to most transient:** - **Rules files** (CLAUDE.md, .cursorrules, AGENTS.md) — always loaded, project-wide. The highest-leverage context you can provide. Cover tech stack, commands, conventions, and boundaries. - **Spec / architecture docs** — loaded per feature. Load only the relevant section, not the entire 5000-word spec. - **Relevant source files** — loaded per task. Read the file before editing; find an existing example of a similar pattern before implementing. - **Error output / test results** — loaded per iteration. Feed the specific error, not the entire 500-line log. - **Conversa