harness-engineeringlisted

# Harness Engineering A harness is the combined set of deterministic tooling and LLM-based agents that keeps AI code generation trustworthy and maintainable at scale. The concept originates from Birgitta Boeckeler's article "Harness Engineering" (2026), which identifies three components that together form a complete harness. For the full article summary and four hypotheses, consult `references/boeckeler-summary.md`. ## The Three Components ### Context Engineering The knowledge an LLM needs to work effectively in a codebase. This includes explicit documentation (conventions, constraints, stack declarations) and implicit context (the code design itself). A well-structured codebase is easier to harness than a sprawling one because the structure communicates intent. In this plugin, context engineering lives in HARNESS.md's **Context** section — stack declaration, convention documentation, and any project-specific knowledge that shapes how code should be written. ### Architectural Constraints Rules that must be enforced — not suggestions, but hard boundaries. Each constraint is backed by a **verification slot** that can be filled by either a deterministic tool (linter, formatter, structural test) or an agent-based review. The rest of the system does not care which backs the slot — only whether the constraint passed. In this plugin, constraints live in HARNESS.md's **Constraints** section and are enforced at three timescales: advisory at edit time (hooks), strict at merge