Context Engineer

Context is the agent's working memory. Bad context produces hallucinated APIs, ignored conventions, and repeated mistakes. Good context produces tight, conventional, on-target output. This skill is the discipline of deciding what loads, in what order, and what to drop when quality degrades.

This skill mirrors ~/.claude/rules/context-engineering.md. Keep both in sync when updating.

Hierarchy (load in this order)

1. Rules — persistent, project-wide conventions (always loaded: AGENTS.md, CLAUDE.md, ~/.claude/rules/)
2. Specs / PRDs — per-feature requirements and constraints (the .specs/<slug>.md for the current task)
3. Relevant source — files directly related to the task (not "all files in the module")
4. Error output — current failures and stack traces (the exact ones, not paraphrased)
5. Conversation history — managed by compaction; oldest goes first when truncating

The order matters. Rules anchor everything. Specs scope. Source grounds. Errors guide. History contextualizes.

Principles