⚗️ Experimental — A markdown brain that gives your AI coding tools judgment and rigor: sharp defaults, real decisions, and the discipline to verify before saying done. For Claude Code, Cursor and Codex. It improves itself over time.
Agent
Designs the solution BEFORE code is written, module/API boundaries, data model, state, contracts, and tech decisions, for whatever field is active (frontend, backend, mobile…). Use for any non-trivial feature, new module, or architectural choice. Returns a concrete design + one-line rationale per decision, not code.
Agent
Reviews a diff, a file, or a whole area against MasterMind's principles and rigor gate: correctness, security, edge cases, types, architecture, stack defaults, the field's audit rules. Use after a non-trivial change, before committing, or to audit code you didn't just write. Returns ranked findings and proposed fixes…
Agent
Restructures working code toward better design WITHOUT changing behavior: deeper modules, a cleaner data model, illegal states made unrepresentable, tangled dependencies unpicked. Use to pay down design/architectural debt on code that already works. Distinct from code-reviewer (finds problems, doesn't edit) and…
Agent
Makes a technical ADOPTION decision, "should we use library/tool/pattern X (vs Y, vs build it)?": evaluated against MasterMind's reuse-with-judgment rubric and returned as a clear verdict with trade-offs. Use when choosing a dependency, framework, or approach. Distinct from /deep-research (broad reports) and Explore…