architecture-maplisted

# Architecture Map Produce `<repo>/architecture-out/architecture-map.json` + `.html`. The JSON is the source of truth; the HTML is rendered from it by `scripts/build.sh` — never write HTML by hand. ## 0. Freshness gate (always first) ```bash HEAD=$(git rev-parse HEAD) LAST=$(node -e "try{const v=JSON.parse(require('fs').readFileSync('architecture-out/architecture-map.json')).analyzedAtCommit;console.log(typeof v==='string'&&v.length>=7?v:'')}catch{console.log('')}") ``` - `LAST == HEAD` → report "architecture map is up to date (commit <short>)" and STOP. - `LAST` non-empty → **incremental mode**: `git diff --name-only $LAST..HEAD` → map changed paths onto existing `modules[].path` prefixes; re-describe ONLY touched modules, re-check only flows whose steps reference them; keep the rest. - `LAST` empty → full analysis. ## 1. Inventory (ground truth, no invention) - `.claude/project.json` — name, repos, stack, domainTerms. - Root `CLAUDE.md` — layout section, commands, hard rules → `conventions` + `importantNotes`. - `graphify-out/graph.json` if present (nodes have `community`/`community_name`, top-level `built_at_commit`): communities are *candidate* module groupings, god nodes are *candidate* hubs. Curate — target 15–40 modules, never 1:1 with communities. If graphify's `built_at_commit` trails HEAD, note it in `importantNotes` and lean on direct exploration instead. - Manifests (`package.json`, `go.mod`, `plugin.json`, workflow YAML) → techStack, entryPoin