jared
/
cc-os
1
0
Fork 0
Code Issues 18 Pull Requests Packages Projects Releases Wiki Activity
cc-os/openspec/changes/archive/2026-06-08-memory-project-g.../proposal.md

2.7 KiB
Raw Blame History

Why

The current memory-query skill has a god-node dependency — it assumes a hub note is surfaced in the session's additionalContext as an entry point. That injection relies on heavy session context output (vault graph report, convention query, journal pointer) that pays a cost every session regardless of whether vault knowledge is needed. There is also no routing rule: nothing tells Claude when to reach for the vault versus when to reach for a project graph.

On the project side, the memory-project-graph skill was never implemented. Per-project code graphs exist (any repo can be onboarded to Graphify), but Claude has no protocol for creating, updating, or querying them.

What Changes

  1. Rename memory-query → memory-vault with two changes to the SKILL.md: drop the god-node section (graphify's internal traversal handles this; no injected entry point needed), and add an explicit scope statement — this skill is for cross-project evergreen knowledge, not codebase structure.

  2. Create memory-project — a new skill covering the full lifecycle of per-project Graphify graphs: onboard (extract + cluster + gitignore), incremental update, structural update (--force), remove, and project-scoped query routing. Query mechanics delegate to memory-vault rather than being duplicated.

  3. Add a routing rule block to ~/.claude/CLAUDE.md — vault for anything that generalizes beyond one repo; project graph for codebase structure and module relationships. Decision heuristic: "Would this be useful outside this repo, next year?"

  4. Trim session-context.sh to emit only the project graph path pointer when graphify-out/graph.json exists. Drop: vault graph report, live convention query, journal pointer.

  5. Mirror both skill renames and additions to .codex/skills/ and .pi/skills/ — the three AI assistant directories stay identical.

Capabilities

New Capabilities

  • memory-vault: Cross-project vault querying without god-node injection dependency.
  • memory-project: Per-project graph lifecycle (onboard, update, remove) and project-scoped queries.
  • memory-routing: Routing rule in ~/.claude/CLAUDE.md — globally visible, single place to maintain.

Modified Capabilities

  • session-context.sh: Narrowed to project graph pointer only — less injection noise, faster hook execution.

Impact

  • Rename: ~/.claude/plugins/memory/skills/memory-query/ → memory-vault/
  • New file: ~/.claude/plugins/memory/skills/memory-project/SKILL.md
  • Edit: session-context.sh (trim to graph pointer)
  • Edit: ~/.claude/CLAUDE.md (add routing rule block)
  • Mirror all the above to .codex/skills/ and .pi/skills/
  • No new runtime dependencies — same graphify CLI and qwen2.5-coder:7b Ollama model.