Glossary Alignment Check

Workflow

Per claim:
- [ ] Step 1: Tokenize claim for candidate terms (named concepts, TLAs, math)
- [ ] Step 2: Grep shared-context/glossary.md for each term
- [ ] Step 3: If found, pull writer's definition
- [ ] Step 4: Compare to field-standard (prior knowledge + optional WebSearch)
- [ ] Step 5: Emit: aligned | diverged-safe | diverged-risky

Three outcomes

• aligned: writer's definition matches field-standard. No note.
• diverged-safe: definitions differ but the post's argument doesn't depend on the difference. Note but don't block.
• diverged-risky: definitions differ AND the post's argument hinges on which definition is in force. Tier-2 note for the writer.