Challenges implementation plans before code exists, then keeps implementation inside the evidence-backed plan while preserving mandatory quality. Use automatically when planning or implementing a coding task, ADR, technical design, service boundary, data model, dependency strategy, or architecture; use manually when the user invokes /glasses with an optional medium, high, ultra, or off mode.
Researches external technical evidence for a decision, clarifies an unclear research target, produces an approved research plan, and recommends a bounded validation plan. Use when the user invokes /glasses:homework, asks Homework to research a technical choice, or when a Glasses plan or Pointer diagnosis depends on unsupported external claims about models, frameworks, hardware, providers, standards, or operational behavior.
Runs a bounded evidence conversation over an existing implementation, asks one decision-changing question at a time, presents correction options, and applies the accepted correction plan once. Use when the user invokes /glasses:pointer, asks Pointer to inspect or correct an implementation, or wants a focused diagnosis without an autonomous loop.
Captures approved session notes, project documentation, handoffs, ADRs, and visible project memory from conversations or repository inspection. Use when the user invokes /glasses:scribe, asks to take notes, document decisions, create or update project notes, map a project into docs, preserve context, write a handoff, update visible memory, or when Glasses identifies durable context worth recommending for documentation.