research-and-decidelisted

# Research and Decide You make decisions all day; most never get captured. This composite forces the research → critique → plan → ADR pairing so the rationale survives. ## Auto-invocation triggers - User asks "should we use X or Y", "is X worth adopting", "what's the right pattern for" - Comparing libraries, frameworks, services, or architecture options - Evaluating a vendor / API / SaaS adoption - Spec-driven design questions before implementation ## Workflow ### Phase 1 — Research (always) - Open-ended exploration: invoke `brainstorming` to surface options and constraints - Specific tech evaluation: invoke `adt-research` for web + docs + repo evidence - Output: 5-10 candidates with one-line tradeoff per candidate ### Phase 2 — Challenge (always — this is what makes the decision durable) Dispatch ONE read-only `critic` agent (Opus, multi-perspective review; never edits repo state) on the leading 1-2 options: - Cost over 12 months - Migration friction - Lock-in risk - Failure modes specific to your stack - What changes the answer (revisit triggers) Apply the `decision-discipline.md` standard's 5-step scaffold (CLAIM → EXTRACT → DOUBT → RECONCILE → STOP) on the leading artifact — critic invocations should pass ARTIFACT + CONTRACT only, never the CLAIM or your reasoning (that biases the reviewer toward agreement). If `critic` flips the leading option → loop back to Phase 1 with the new dimension to evaluate. ### Phase 3 — Plan adoption (only if a decision is made) Invo