Context Engineering Fundamentals

Context is the complete state available to a language model at inference time: system instructions, tool definitions, retrieved documents, message history, and tool outputs. Context engineering is the discipline of curating the smallest high-signal token set that maximizes the likelihood of desired outcomes.

This skill does not own operational work: debugging attention failures belongs to context-degradation, and token-efficiency tactics belong to context-optimization.

When to Activate

When the work is conceptual:

• Explaining what context is and how attention mechanics constrain agent behavior.
• Onboarding new contributors who need the mental models before diving into operational skills.
• Reasoning about a context-related design decision from first principles (what does this constraint mean, why does this trade-off exist) before picking a specific tactic.
• Writing or reviewing documentation that needs to ground operational guidance in the underlying mechanics.

Do not activate this skill for operational work. The specialized skills handle the doing:

• Diagnosing lost-in-middle, context poisoning, or attention failures: context-degradation.
• Reducing token cost via masking, partitioning, prefix caching, budgets: context-optimization.