cc-os/docs/memory-system
jared 72397a00b8 Add assessment-first onboarding to memory-project skill (ADR-017)
Onboarding ran a bare `graphify extract`, but graphify does not honor
.gitignore — it needs its own .graphifyignore. Without one, onboarding
viking-warrior-training-log walked node_modules/ (5,858 files) and
routed its non-code files through the Ollama doc pass; the run was
killed after ~1 hour with no graph.json.

Onboarding is now assessment-first: survey the repo, generate a
per-project .graphifyignore (the ignore set varies by stack), confirm
with the user, then extract. Records the gotcha and decision in ADR-017.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-17 09:17:33 -04:00
..
benchmark Complete graphify-ollama-setup OpenSpec change 2026-06-05 11:44:40 -04:00
00-README.md Remove handoff doc and pivot to Graphify knowledge layer 2026-06-04 07:57:39 -04:00
01-video-synthesis.md Remove handoff doc and pivot to Graphify knowledge layer 2026-06-04 07:57:39 -04:00
02-system-design.md Update design docs and add implementation runbook per ADR-011/012 2026-06-04 09:35:43 -04:00
03-architecture-decisions.md Add assessment-first onboarding to memory-project skill (ADR-017) 2026-06-17 09:17:33 -04:00
04-build-plan.md Add assessment-first onboarding to memory-project skill (ADR-017) 2026-06-17 09:17:33 -04:00
05-implementation-process.md Document memory-project skill completion and vault/project query refactor 2026-06-08 13:24:53 -04:00
06-graphify-evaluation.md Remove handoff doc and pivot to Graphify knowledge layer 2026-06-04 07:57:39 -04:00
07-graph-connectivity-findings.md Complete memory plugin implementation — hooks, skills, and graph-connectivity findings 2026-06-05 16:39:49 -04:00