querylisted

# engram query Query engram's knowledge graph instead of reading files directly. Saves tokens when a structural answer suffices. The argument is a natural-language question. Run: ``` engram query "$ARGUMENTS" -p $CLAUDE_PROJECT_DIR ``` The graph returns a token-budgeted answer with: - Relevant nodes (functions, files, concepts) - Edges (calls, imports, decided-for relationships) - Mistake hits if any (these surface with ⚠️ at the top — read carefully, they represent past failure modes) If the answer doesn't fully address the question, fall back to reading specific files mentioned in the result. For a connection between two specific concepts use `engram path <source> <target>`. For most-connected entities use `engram gods`. ## Example invocations **User:** "How does authentication work in this project?" **You:** Run `engram query "how does authentication work" -p $CLAUDE_PROJECT_DIR`. Read the structured response. Cite the relevant nodes (function names, file paths). If the answer mentions specific files, those are good candidates for a follow-up Read — but only if the structural view leaves a question. **User:** "What calls `validateToken`?" **You:** Run `engram query "what calls validateToken" -p $CLAUDE_PROJECT_DIR`. The graph returns the inbound call sites without you ever Reading those files. **User:** "Where is the rate limiter implemented?" **You:** Run `engram query "rate limiter implementation" -p $CLAUDE_PROJECT_DIR`. If the answer points at one file, yo