startuplisted

Session startup. Follow these steps: ## 0. Orientation Prelude Do both of these before any `scope=project` memory calls or substantive work. **0a. Refresh global directives.** Read `~/.claude/CLAUDE.md` — your global operating rules (communication style, memory scope resolution, git safety, Python convention). It's loaded at session start but fades when buried in a long system prompt; re-reading pulls it into active attention. **0b. Confirm project identity.** Check `.engram.cfg` at the repo root. - If present: parse `project = <name>`. This is the canonical user_id for all `scope=project` memory and inbox addressing. Proceed. - If absent: 1. **Only** auto-suggest a name when CWD matches `~/projects/<name>/` (one level directly under `projects/`, at the repo root) AND `<name>` is NOT a generic deploy label (`prod`, `dev`, `staging`, `main`, `trunk`, `current`, `release`, `live`). In that case, suggest `<name>` and ask the user to confirm. 2. Otherwise (nested layouts like `~/projects/site/sub/`, domain-style `~/projects/site.com/dev/`, server paths like `/var/www/site/prod`, or anything that doesn't match the clean `~/projects/<name>/` shape), do NOT guess — ask the user directly for the canonical project name. Do not infer from git remotes or path segments in ambiguous cases; the user decides. 3. Once the user confirms the name: write `.engram.cfg` at the repo root containing `project = <name>`. Stage it. Commit (`Add .engram.cfg — canonical project identifier`).