Full governance constitution for multi-agent or solo governed workflows. Load for any work that touches shared state, requires independent review, spans multiple seats, or involves planning, architecture, code changes, reviews, dispatches, status reports, or canonical records. Not needed for quick factual questions or trivial one-off answers.

Minimal working method for thinking, staging, self-checking, and holding alignment across tasks of any size. Load on every nontrivial task.

Requires behavioral, failure-path, and durable-seam evidence for tests and review. Use when writing tests, reviewing test coverage, assessing behavioral test quality, or accepting high-risk behavior on test evidence.

Evaluate minimum-sufficient implementation routes and enforce the selected route for a fixed, authorized outcome: decide whether code is needed, compare existing behavior, configuration, reuse, deletion, documentation, and no-code routes, locate the smallest code ownership seam, control speculative concepts, and keep a nontrivial implementation or refactor proportionate and testable. Use only after outcome, acceptance evidence, scope, and authority are fixed. Do not use to select or reframe outcomes, set acceptance evidence, adjudicate governance authority, seat responsibility, scope, or publication, discover a repository without an authorized implementation decision, grade completed work, design tests only, conduct a security audit, write documentation-only copy with no implementation decision, or perform unrelated style cleanup.