sema или copilot-goal-skill

Sema adds a content-addressed vocabulary of 452 cognitive patterns to Claude. Each pattern has a handle like StateLock#5602 — a SHA-256 hash of its definition — so two agents using the same handle are provably talking about the same thing. Any divergence in meaning produces a different hash, making silent misalignment impossible. Key features: - sema_search — semantic + keyword search across the pattern library • sema_resolve — full definition, mechanism, invariants, and dependency graph for any handle • sema_handshake — verify two agents share the exact same definition; halt on mismatch • sema_tree — browse the taxonomy (Physics / Mind / Society / Infrastructure) • sema_root — one-hash fingerprint of the whole vocabulary, for fast drift checks • sema_mint — add project-local patterns (survives pip upgrades) • sema pull — sync a project DB with upstream, auto-redirecting renamed handles

Goal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector subagent (judges the result with fresh context). The Inspector never trusts the Builder. Output is auditable in git commits from each subagent actions. Use when the user says "achieve this goal", "make this work", "implement until done", or wants verified autonomous task completion with independent quality review.