Two bug fixes:
.graphifyignore not respected by collect_files() (#188) — collect_files() in extract.py was ignoring .graphifyignore patterns entirely. On projects with node_modules/ ignored, this caused 40k+ files to be scanned instead of ~200. Fixed by loading and applying ignore patterns the same way detect() does.
Semantic extraction silently dropped with Explore subagent (#195) — if Claude Code dispatched extraction subagents using subagent_type="Explore", chunk files were never written to disk (Explore is read-only), causing up to 2.4x fewer nodes extracted with no warning. skill.md now explicitly requires general-purpose subagent type and Step B3 warns when chunk files are missing instead of silently skipping.
Run pip install --upgrade graphifyy then graphify install to get both fixes.