@hegemonart/get-design-done 1.18.0 → 1.19.5

package/agents/design-pattern-mapper.md

@@ -38,6 +38,7 @@ The orchestrating stage supplies a `<required_reading>` block in the prompt pass
 - `.design/DESIGN-CONTEXT.md` — goals, decisions, must-haves, baseline audit, domain, scopes
 - `reference/audit-scoring.md` — maps task types to scoring categories
 - `reference/brand-voice.md` — voice axis defaults and industry context (use when classifying copy-system patterns and inferring brand register from existing UI text)
+- `reference/information-architecture.md` — nav pattern catalog (use to classify existing navigation implementation: hub-and-spoke, nested, faceted, flat, mega-menu)
 
 **Invariant:** Read every file in the `<required_reading>` block before taking any other action.
 
@@ -266,4 +267,14 @@ You MUST NOT:
 
 ---
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## MAPPING COMPLETE

package/agents/design-pencil-writer.md

@@ -97,3 +97,13 @@ Mode: <mode>
 Applied: N/M operations (N committed, M failed)
 Failed: <list or "none">
 ```
+
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.

package/agents/design-phase-researcher.md

@@ -87,7 +87,7 @@ Research loading and rendering performance norms for the project type:
 Target ~2 minutes of research time:
 
 - Use `WebSearch` for: industry design conventions, published pattern libraries, WCAG guidance, framework-specific design docs
-- Use `Read` for: in-repo reference files (`reference/heuristics.md`, `reference/accessibility.md`, `reference/anti-patterns.md`) when they exist
+- Use `Read` for: in-repo reference files (`reference/heuristics.md`, `reference/accessibility.md`, `reference/anti-patterns.md`, `reference/user-research.md`, `reference/platforms.md`) when they exist — `user-research.md` informs which evaluation methods fit the project type; `platforms.md` informs platform-appropriate patterns when the project targets mobile, native, or cross-platform
 - Use `Glob`/`Grep` for: identifying the actual tech stack from project files when DESIGN-CONTEXT.md is ambiguous
 
 Prioritize in-repo reference files over web search — they are already project-calibrated.
@@ -226,4 +226,14 @@ flowchart TD
 @.design/intel/dependencies.json (if present)
 @.design/intel/graph.json (if present)
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## RESEARCH COMPLETE

package/agents/design-plan-checker.md

@@ -161,4 +161,14 @@ You MUST NOT:
 
 ---
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## PLAN CHECK COMPLETE

package/agents/design-planner.md

@@ -349,4 +349,14 @@ You MUST NOT:
 @.design/intel/dependencies.json (if present)
 @.design/intel/graph.json (if present)
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## PLANNING COMPLETE

package/agents/design-reflector.md

@@ -172,4 +172,14 @@ Aggregate per agent across cycles:
 - Proposals are additive — propose additions, not deletions of existing content, unless the evidence is clear (e.g., wrong frontmatter value).
 - Maximum 20 proposals per reflection file. If more are warranted, batch the lowest-priority ones into a single summary note at the end.
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## REFLECTION COMPLETE

package/agents/design-research-synthesizer.md

@@ -163,4 +163,14 @@ Read .design/STATE.md
 
 Single file: `.design/DESIGN-CONTEXT.md`.
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## SYNTHESIZE COMPLETE

package/agents/design-start-writer.md

@@ -219,3 +219,13 @@ The JSON block at the bottom is the contract future `/gdd:fast` / `/gdd:do` invo
 - Do not omit any of the seven H2 sections — even empty, they must exist for downstream regression fixtures.
 
 ## START-WRITER COMPLETE
+
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.

package/agents/design-update-checker.md

@@ -115,3 +115,13 @@ Last line of your response MUST be:
 ```
 
 The spawning skill greps for this marker to confirm you finished successfully. Emit it even on the "no cache" fallback path.
+
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.

package/agents/design-verifier-gate.md

@@ -94,4 +94,14 @@ You MAY:
 
 Per 10.1-CONTEXT decision **D-21** (Lazy Checker Spawning): "Cheap Haiku gate agents at `agents/*-gate.md` decide whether to spawn full checker. Gate agent: reads DIFF of changed files, applies heuristic (design-system paths touched? copy strings touched? token files touched?), returns `{spawn: true|false, rationale: '...'}`. If false, skip full checker, log as `lazy_skipped: true` in telemetry." This gate is the verifier-specific instance of that pattern — full `design-verifier` is an XL-size spawn and the most expensive single agent in the pipeline, so gating it behind a cheap Haiku diff-scan yields the largest single cost win in Phase 10.1.
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## GATE COMPLETE

package/agents/design-verifier.md

@@ -553,6 +553,17 @@ Emit a 2–4 sentence summary paragraph describing results, then:
 Emit `## GAPS FOUND` heading, then the full structured gap list (BLOCKER first, MAJOR, MINOR, COSMETIC), then on a new line:
 
 ```
+
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## VERIFICATION COMPLETE
 ```
 

package/agents/gdd-graphify-sync.md

@@ -98,3 +98,13 @@ Graphify status: <status line>
 @.design/intel/files.json (if present)
 
 ## GRAPHIFY-SYNC COMPLETE
+
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.

package/agents/gdd-intel-updater.md

@@ -85,4 +85,14 @@ Generated:      <timestamp>
 A slice is stale if its `generated` timestamp is older than the newest `mtime` in `files.json`.
 The updater does not need to check this manually — `build-intel.cjs` handles mtime comparison.
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## INTEL UPDATE COMPLETE

package/agents/gdd-learnings-extractor.md

@@ -82,4 +82,14 @@ For each learning with `Proposed reference update: yes`:
 @.design/intel/patterns.json (if present)
 @.design/learnings/LEARNINGS.md (if present)
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## LEARNINGS EXTRACTION COMPLETE

package/agents/motion-mapper.md

@@ -210,4 +210,14 @@ If no violations found, emit: `## Micro-motion findings — CLEAN (0 violations)
 
 No modifications outside `.design/map/`. No git. No agent spawning.
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## MOTION MAP COMPLETE

package/agents/token-mapper.md

@@ -144,4 +144,14 @@ Total: N findings. (0 = clean)
 
 You MUST NOT modify anything outside `.design/map/`. Do not run git commands or spawn agents.
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## TOKEN MAP COMPLETE

package/agents/visual-hierarchy-mapper.md

@@ -121,4 +121,14 @@ Total: N findings.
 
 No modifications outside `.design/map/`. No git. No agent spawning.
 
+## Record
+
+At run-end, append one JSONL line to `.design/intel/insights.jsonl`:
+
+```json
+{"ts":"<ISO-8601>","agent":"<name>","cycle":"<cycle from STATE.md>","stage":"<stage from STATE.md>","one_line_insight":"<what was produced or learned>","artifacts_written":["<files written>"]}
+```
+
+Schema: `reference/schemas/insight-line.schema.json`. Use an empty `artifacts_written` array for read-only agents.
+
 ## VISUAL HIERARCHY MAP COMPLETE

package/hooks/gdd-decision-injector.js

@@ -25,6 +25,14 @@ const MIN_BYTES = 1500;
 const TOP_N = 15;
 const MATCHER_RE = /[\\/](?:\.design|reference|\.planning)[\\/][^\n]*\.md$/;
 
+// Phase 19.5: try FTS5 backend first; fall back to grep silently.
+let _designSearch = null;
+try {
+  _designSearch = require(path.join(__dirname, '..', 'scripts', 'lib', 'design-search.cjs'));
+} catch { /* not available in this install */ }
+
+const BACKEND = _designSearch ? _designSearch.backendName() : null;
+
 function ripgrepAvailable() {
   try {
     const r = spawnSync('rg', ['--version'], { encoding: 'utf8', windowsHide: true });
@@ -103,7 +111,7 @@ function sortKeyFor(tag) {
   return 0;
 }
 
-function buildRecallBlock(matches, basename) {
+function buildRecallBlock(matches, basename, backendLabel) {
   if (!matches.length) return null;
   const uniq = [];
   const seen = new Set();
@@ -125,10 +133,11 @@ function buildRecallBlock(matches, basename) {
     const excerpt = m.text.length > 140 ? m.text.slice(0, 137) + '…' : m.text;
     lines.push(`> - [${tag}] ${excerpt} (${path.relative(process.cwd(), m.file)}:${m.line})`);
   }
+  // backendLabel passed in from main()
   if (uniq.length > TOP_N) {
-    lines.push(`> … (${uniq.length - TOP_N} more matches; use \`/gdd:recall <term>\` to expand. Grep backend; FTS5 upgrade in Phase 19.5.)`);
+    lines.push(`> … (${uniq.length - TOP_N} more matches; use \`/gdd:recall <term>\` to expand. Backend: ${backendLabel}.)`);
   } else {
-    lines.push(`> (${uniq.length} match${uniq.length === 1 ? '' : 'es'} surfaced. Grep backend; FTS5 upgrade in Phase 19.5.)`);
+    lines.push(`> (${uniq.length} match${uniq.length === 1 ? '' : 'es'} surfaced. Backend: ${backendLabel}.)`);
   }
   lines.push('');
   return lines.join('\n');
@@ -173,13 +182,26 @@ async function main() {
     return;
   }
 
-  const useRg = ripgrepAvailable();
-  const hits = [];
-  for (const src of sources) {
-    hits.push(...(useRg ? grepLinesRg(src, terms) : grepLinesNode(src, terms)));
+  const useRgGlobal = ripgrepAvailable();
+  let hits = [];
+  if (BACKEND === 'fts5' && _designSearch) {
+    // FTS5 path: single query across all indexed docs
+    try {
+      const query = terms.join(' OR ');
+      hits = _designSearch.search(query, cwd, { limit: TOP_N * 3 });
+    } catch { hits = []; }
+    if (!hits.length) {
+      // FTS5 db may be stale — rebuild silently then retry
+      try { _designSearch.reindex(cwd); hits = _designSearch.search(terms.join(' OR '), cwd, { limit: TOP_N * 3 }); } catch { hits = []; }
+    }
+  } else {
+    for (const src of sources) {
+      hits.push(...(useRgGlobal ? grepLinesRg(src, terms) : grepLinesNode(src, terms)));
+    }
   }
 
-  const block = buildRecallBlock(hits, basename);
+  const backendLabel = BACKEND || (useRgGlobal ? 'ripgrep' : 'node-grep');
+  const block = buildRecallBlock(hits, basename, backendLabel);
   if (!block) {
     process.stdout.write(JSON.stringify({ continue: true }));
     return;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hegemonart/get-design-done",
-  "version": "1.18.0",
+  "version": "1.19.5",
   "description": "A Claude Code plugin for systematic design improvement",
   "author": "Hegemon",
   "homepage": "https://github.com/hegemonart/get-design-done",
@@ -76,10 +76,23 @@
     "gesture-mechanics",
     "clip-path-animation",
     "component-specs",
-    "design-system-benchmarks"
+    "design-system-benchmarks",
+    "i18n",
+    "user-research",
+    "information-architecture",
+    "form-patterns",
+    "data-viz",
+    "platforms",
+    "cross-cycle-memory",
+    "fts5",
+    "checkpoints",
+    "experience-archive",
+    "recall",
+    "relevance-counter",
+    "record-contract"
   ],
   "skills": [
     "SKILL.md"
   ],
   "hooks": "hooks/hooks.json"
-}
+}