verify

Protocol Verification

Verify epistemic protocol consistency before commit through static checks and expert review.

Purpose

Surface potential issues in protocol definitions without blocking commits. Follow Anthropic philosophy: transparency over enforcement, user agency over automation.

Core Principles

Principle	Implementation
Surface, don't enforce	Present findings; user decides action
Zero-context scripts	Static checks run without consuming context
Explicit control	User invokes /verify intentionally
Graduated severity	Critical / Concern / Note categorization

Workflow

Phase 1: Static Checks

Run scripts/static-checks.js against project root. This script executes without loading into context.

node ${SKILL_DIR}/scripts/static-checks.js ${PROJECT_ROOT}

Output format:

{
  "pass": [{ "check": "...", "file": "...", "message": "..." }],
  "fail": [{ "check": "...", "file": "...", "message": "..." }],
  "warn": [{ "check": "...", "file": "...", "message": "..." }]
}

Checks performed: Structural conformance (JSON schema, Unicode notation, directive verbs, required sections, morphism anatomy, gate-type soundness), cross-reference and routing integrity (cross-reference integrity and scan, routing-index contract, onboard/catalog sync, partition invariant), drift prevention (version staleness, codex-manifest sync, spec-vs-impl drift, single-axis soundness, emit-load discipline, framing-readout enforcement, language purity), and packaging/contract sync (artifact self-containment, packaged-agent contract sync). The check inventory is the script itself (scripts/static-checks.js); references/verification.md carries why the non-obvious checks exist and what to do when one fires.

Phase 2: Expert Review

Spawn parallel Task subagents for LLM-based review — one per perspective (Type Theory / Category Theory, Instruction Design, Claude Code Ecosystem). Load each subagent's prompt template from references/review-checklists.md (single source of truth; do not duplicate the templates here — see Review Checklists below). Each template samples the protocols changed in the current diff, falling back to a representative sample when the diff is not protocol-scoped.