ai-engineering-loop 1.0.14 → 1.0.15

package/examples/backend-api/payment-idempotency/README.md

@@ -22,12 +22,12 @@ Task: Implement atomic idempotency key validation and SELECT FOR UPDATE row lock
 
 ## 3. Walkthrough Artifacts
 
-1. **[Goal Contract (`goal-contract.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/backend-api/payment-idempotency/goal-contract.md)**:
+1. **[Goal Contract (`goal-contract.md`)](./goal-contract.md)**:
    - AC-1: Idempotency-Key header mandatory on POST `/api/v1/payments/charge`.
    - AC-2: Atomic reservation using PostgreSQL `INSERT ... ON CONFLICT DO NOTHING`.
    - AC-3: Concurrent requests for same user wallet serialized with `SELECT ... FOR UPDATE`.
-2. **[Adversarial Review Findings (`review-findings.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/backend-api/payment-idempotency/review-findings.md)**:
+2. **[Adversarial Review Findings (`review-findings.md`)](./review-findings.md)**:
    - Devil's Advocate activates `backend-api` rules (concurrency, database atomicity).
    - Flags missing rollback on external gateway timeout (`ERR-001`).
-3. **[Judge Verdict (`judge-verdict.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/backend-api/payment-idempotency/judge-verdict.md)**:
+3. **[Judge Verdict (`judge-verdict.md`)](./judge-verdict.md)**:
    - Evaluates parallel test execution (`go test -race ./...`), verifies concurrency safety, and issues `PASS` verdict.

package/examples/dot/status-display/README.md

@@ -0,0 +1,23 @@
+# Reference Example: Request Display Status Fix
+
+## 1. Context & Scenario
+
+This walkthrough shows how a status-display bug moves through the **AI Engineering Loop** and the **DOT Delivery Adapter**. Names, URLs, and schema below are **fictional**. Do not copy real client tickets, GitLab links, or field names into this package.
+
+### The Problem
+
+On an employee portal, request cards on the list and pagination endpoints showed `"PENDING"` after every line item was already approved or rejected. Non-standard-window records were also scored with the standard-day rule.
+
+---
+
+## 2. Walkthrough Stages & Artifacts
+
+1. **[Stage 1: Goal Contract (`goal-contract.md`)](./goal-contract.md)**:
+   - Objective, acceptance criteria (standard window, holiday, non-standard window, null values), and verification plan.
+2. **[Stage 2: Adversarial Review & Triage (`review-findings.md`)](./review-findings.md)**:
+   - Devil's Advocate flags a null-safety bug (`COR-001`) and an invalid nitpick (`MAINT-001`).
+   - Maker triage and surgical fix.
+3. **[Stage 3: Judge Evaluation & Verdict (`judge-verdict.md`)](./judge-verdict.md)**:
+   - Audit of tests, typecheck, finding resolutions, and `PASS`.
+4. **[Stage 4: DOT Delivery Pipeline (`delivery-report.md`)](./delivery-report.md)**:
+   - Fictional issue, base MR, cherry-picks to `staging` and `develop`, Coreview triage, Mattermost notice.

package/examples/dot/status-display/delivery-report.md

@@ -0,0 +1,41 @@
+# DOT Delivery Report: Request Display Status Fix
+
+Fictional sample. Replace host, group, repo, issue, and MR ids from `glab` output. Never paste real client URLs into this package.
+
+## 1. Summary of Delivery Actions
+
+1. **GitLab Issue Created**: [Issue #42 - [BE] [Requests] Fix display status](https://gitlab.example.com/example-org/work-portal/-/issues/42).
+2. **Primary MR Created**: [MR !10 targeting `main`](https://gitlab.example.com/example-org/work-portal/-/merge_requests/10).
+3. **Multi-Branch Cherry-Pick**:
+   - [MR !11 targeting `staging`](https://gitlab.example.com/example-org/work-portal/-/merge_requests/11).
+   - [MR !12 targeting `develop`](https://gitlab.example.com/example-org/work-portal/-/merge_requests/12).
+4. **Coreview Bot Triage**:
+   - Comments fetched on MR !12. Zero blocking comments.
+5. **Mattermost Notification**:
+   - Resolved repository `example-org/work-portal` to channel `"team-work-portal"`.
+   - Dispatched via MCP `mattermost_send_message` with `from: "AI Agent"`.
+
+---
+
+## 2. GitLab Links
+
+| Artifact | Branch | Link |
+|---|---|---|
+| **GitLab Issue** | — | [Issue #42](https://gitlab.example.com/example-org/work-portal/-/issues/42) |
+| **Merge Request DEV** | `develop` | [MR !12](https://gitlab.example.com/example-org/work-portal/-/merge_requests/12) |
+| **Merge Request STAGING** | `staging` | [MR !11](https://gitlab.example.com/example-org/work-portal/-/merge_requests/11) |
+| **Merge Request MAIN** | `main` | [MR !10](https://gitlab.example.com/example-org/work-portal/-/merge_requests/10) |
+
+---
+
+## 3. Dispatched Mattermost Notification
+
+```text
+[MR DEV] https://gitlab.example.com/example-org/work-portal/-/merge_requests/12
+Changes log
+- Include standard-window and rush-note fields when loading request list pages.
+- Resolve display status from all line items, including holiday and null collections.
+- Add unit tests for standard, holiday, non-standard-window, and null line-item cases.
+
+cc: @owner
+```

package/examples/dot/status-display/goal-contract.md

@@ -0,0 +1,46 @@
+# Goal Contract: Request Display Status Fix
+
+## 1. Objective
+
+Fix incorrect display status on list and pagination endpoints when a request has mixed line items, holiday logs, non-standard windows, or null collections.
+
+## 2. Business Outcome & User Lifecycle Impact
+
+- **Employees**: See APPROVED, REJECTED, or NEED_APPROVAL matching the real record.
+- **Reviewers**: Stop getting false pending notices for already-settled holiday logs.
+- **Finance**: Totals used by the downstream aggregate job stay consistent.
+
+## 3. Acceptance Criteria (AC)
+
+- [ ] **AC-1**: If `hasStandardWindow = true` and `duration` is within the standard day limit on a weekday without a rush note, display status is `APPROVED` or `NEED_APPROVAL` from clock-in/out presence only.
+- [ ] **AC-2**: If a rush note exists, or duration exceeds the standard limit, or `isHoliday = true`, evaluate pending status across all associated `lineItems`.
+- [ ] **AC-3**: Non-standard-window records (`user.type.hasStandardWindow = false`) must not use the weekday duration threshold.
+- [ ] **AC-4**: Null or missing `lineItems` default to `APPROVED` without throwing `TypeError`.
+- [ ] **AC-5**: The existing API response contract is unchanged.
+
+## 4. Technical Constraints
+
+- Keep the existing list/pagination query shape.
+- Centralize logic in a pure function: `resolveRequestDisplayStatus`.
+- No new runtime dependencies.
+- `tsc --noEmit` exits 0.
+
+## 5. Out of Scope
+
+- Frontend layout changes.
+- Database migrations.
+- Changing the downstream aggregate/export job.
+
+## 6. Verification Requirements
+
+- **Unit Tests**: Jest suite at `src/server/requests/utils/resolve-display-status.test.ts`.
+- **Typecheck**: `npx tsc --noEmit` exits 0.
+- **Linter**: `npx eslint --fix` on modified files, 0 errors.
+- **Regression**: commands in `.ai-engineering-loop/verification.md` (example: `npx jest && npx tsc --noEmit`).
+
+## 7. Definition of Done (DoD)
+
+- [ ] AC-1 through AC-5 proven by unit tests.
+- [ ] Deterministic verification passes.
+- [ ] Devil's Advocate review with 0 unresolved blocking findings.
+- [ ] Judge issues PASS.

package/examples/dot/status-display/judge-verdict.md

@@ -0,0 +1,44 @@
+# Judge Evaluation Report: Request Display Status Fix
+
+## 1. Executive Verdict
+
+- **Verdict**: `PASS`
+- **Iteration**: `Iteration 2 of 3`
+- **Confidence**: `HIGH`
+
+---
+
+## 2. Deterministic Verification Audit
+
+| Check | Command Executed | Raw Result | Status |
+|---|---|---|:---:|
+| **Unit Tests** | `npx jest src/server/requests/utils/resolve-display-status.test.ts` | `Tests: 12 passed, 12 total.` | PASS |
+| **Full Suite** | `npx jest && npx tsc --noEmit` | `Test Suites: 12 passed. tsc exit 0.` | PASS |
+| **TypeScript** | `npx tsc --noEmit` | `Exit code 0.` | PASS |
+| **Linter** | `npx eslint --fix src/server/requests/**` | `0 errors.` | PASS |
+
+---
+
+## 3. Goal Contract Compliance Audit
+
+| Criterion | Verified By Test / Artifact | Result |
+|---|---|:---:|
+| **AC-1**: Standard-window weekday | `resolve-display-status.test.ts > standard window` | PASS |
+| **AC-2**: Holiday and over-limit handling | `resolve-display-status.test.ts > holiday rush` | PASS |
+| **AC-3**: Non-standard-window records | `resolve-display-status.test.ts > non-standard window` | PASS |
+| **AC-4**: Null `lineItems` | `resolve-display-status.test.ts > null safety` | PASS |
+| **AC-5**: API contract | router typecheck | PASS |
+
+---
+
+## 4. Finding Triage Audit
+
+- **COR-001 (High - Null Safety)**: Maker applied null coalescing in Iteration 2. **Status: RESOLVED & VERIFIED**.
+- **MAINT-001 (Low - Factory Suggestion)**: Invalid speculative nitpick. **Status: DISMISSED / INVALID**.
+
+---
+
+## 5. Formal Conclusion & Hand-off
+
+Definition of Done is met with reproducible evidence.
+**Authorized next action**: DOT Delivery Adapter (`adapters/dot/README.md`) for GitLab MR, multi-branch cherry-pick, Coreview triage, and Mattermost.

package/examples/dot/status-display/review-findings.md

@@ -0,0 +1,63 @@
+# Adversarial Review Findings & Triage: Request Display Status Fix
+
+## 1. Review Summary
+
+- **Reviewer**: Devil's Advocate Agent
+- **Target Branch**: `main...fix/request-display-status`
+- **Total Findings**: 2
+- **Blocking (SEV-1/2)**: 1
+- **Non-Blocking / Invalid**: 1
+
+---
+
+## 2. Findings Ledger
+
+### Finding COR-001: Missing null safety when iterating `lineItems`
+
+- **Severity**: `HIGH` (SEV-2)
+- **Category**: `Correctness`
+- **Location**: `src/server/requests/utils/resolve-display-status.ts:34-41`
+- **Evidence**:
+
+```typescript
+const hasPending = confirmation.lineItems.some(
+  (item) => item.status === "NEED_APPROVAL"
+);
+```
+
+- **Problem**:
+  If `confirmation.lineItems` is `null` or `undefined` (legacy rows), `.some()` throws `TypeError`.
+- **Impact**:
+  Pagination API crashes for historical records.
+- **Recommendation**:
+
+```diff
+- const hasPending = confirmation.lineItems.some(
++ const hasPending = (confirmation.lineItems ?? []).some(
+    (item) => item.status === "NEED_APPROVAL"
+  );
+```
+
+- **Confidence**: `HIGH`
+- **Status**: `TRIAGED_VALID`
+- **Resolution**:
+  Maker applied `(confirmation.lineItems ?? [])` and added `should return APPROVED when lineItems is null or undefined`.
+
+---
+
+### Finding MAINT-001: Suggestion to convert helper into an abstract factory class
+
+- **Severity**: `LOW` (SEV-4)
+- **Category**: `Maintainability`
+- **Location**: `src/server/requests/utils/resolve-display-status.ts:1-50`
+- **Evidence**:
+  Utility is `export function resolveRequestDisplayStatus(...)`.
+- **Problem**:
+  Reviewer wanted a Strategy/Factory for future calculator swaps.
+- **Impact**:
+  None. Pure functions match this repo.
+- **Recommendation**: Refactor to `class StatusCalculatorFactory`.
+- **Confidence**: `LOW`
+- **Status**: `TRIAGED_INVALID`
+- **Triage Reason**:
+  Speculative overengineering. Constraint: surgical change, no extra abstractions.

package/examples/initialization/README.md

@@ -13,7 +13,7 @@ This walkthrough demonstrates how the **AI Engineering Loop** automatically init
 
 ## 2. Walkthrough Artifacts
 
-1. **[Discovery Execution Trace (`discovery-trace.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/initialization/discovery-trace.md)**:
+1. **[Discovery Execution Trace (`discovery-trace.md`)](./discovery-trace.md)**:
    - Full 5-pass log of directory inspection, manifest parsing, script discovery, architecture tracing, and second-pass quality check.
-2. **[Generated Context Artifacts (`generated-context.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/initialization/generated-context.md)**:
+2. **[Generated Context Artifacts (`generated-context.md`)](./generated-context.md)**:
    - The exact evidence-based `.ai-engineering-loop/` files generated automatically by the agent without user intervention.

package/examples/initialization/discovery-trace.md

@@ -18,7 +18,7 @@
   - `packages/` (contains `ui/`, `database/`, `shared/`)
   - `pnpm-workspace.yaml` (detected `pnpm` monorepo)
   - `turbo.json` (detected Turborepo pipeline)
-- **Profile Binding**: Bound [`profiles/monorepo.md`](file:///Users/egagofur/Development/work/ai-engineering-loop/profiles/monorepo.md).
+- **Profile Binding**: Bound [`profiles/monorepo.md`](../../profiles/monorepo.md).
 
 ### Pass 2: Manifests & Verification Commands Discovery
 - Parsed `package.json` (root):

package/examples/mobile-app/offline-sync-queue/README.md

@@ -22,12 +22,12 @@ Task: Implement persistent offline SQLite mutation queue with exponential backof
 
 ## 3. Walkthrough Artifacts
 
-1. **[Goal Contract (`goal-contract.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/mobile-app/offline-sync-queue/goal-contract.md)**:
+1. **[Goal Contract (`goal-contract.md`)](./goal-contract.md)**:
    - AC-1: All form submissions persist immediately to local SQLite `mutation_queue` table before network dispatch.
    - AC-2: Background sync engine triggers on network restoration with exponential backoff.
    - AC-3: OS suspension / app kill must not drop un-synced items.
-2. **[Adversarial Review Findings (`review-findings.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/mobile-app/offline-sync-queue/review-findings.md)**:
+2. **[Adversarial Review Findings (`review-findings.md`)](./review-findings.md)**:
    - Devil's Advocate activates `mobile-app` rules (offline persistence, lifecycle, battery).
    - Flags missing disk write error handling when device storage is full (`PERF-001`).
-3. **[Judge Verdict (`judge-verdict.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/mobile-app/offline-sync-queue/judge-verdict.md)**:
+3. **[Judge Verdict (`judge-verdict.md`)](./judge-verdict.md)**:
    - Audits Flutter unit & mock network tests, verifies 100% pass, and issues `PASS` verdict.

package/lib/sync-hosts.js

@@ -33,6 +33,7 @@ function hostFileMap(home) {
       root: claude,
       files: [
         { src: '.claude/skills/ai-engineering-loop/SKILL.md', dest: path.join(claude, 'skills/ai-engineering-loop/SKILL.md'), mode: 'upsert' },
+        { src: 'adapters/dot/skills/task-impact-inquiry/SKILL.md', dest: path.join(claude, 'skills/task-impact-inquiry/SKILL.md'), mode: 'upsert' },
         { src: '.claude/agents/devil-advocate.md', dest: path.join(claude, 'agents/devil-advocate.md'), mode: 'upsert' },
         { src: '.claude/agents/judge.md', dest: path.join(claude, 'agents/judge.md'), mode: 'upsert' },
         { src: '.claude/commands/ai-engineering-loop.md', dest: path.join(claude, 'commands/ai-engineering-loop.md'), mode: 'upsert' }
@@ -43,6 +44,7 @@ function hostFileMap(home) {
       root: grok,
       files: [
         { src: '.grok/skills/ai-engineering-loop/SKILL.md', dest: path.join(grok, 'skills/ai-engineering-loop/SKILL.md'), mode: 'upsert', grokSkillOverlay: true },
+        { src: 'adapters/dot/skills/task-impact-inquiry/SKILL.md', dest: path.join(grok, 'skills/task-impact-inquiry/SKILL.md'), mode: 'upsert', grokSkillOverlay: true },
         { src: '.grok/agents/devil-advocate.md', dest: path.join(grok, 'agents/devil-advocate.md'), mode: 'upsert' },
         { src: '.grok/agents/judge.md', dest: path.join(grok, 'agents/judge.md'), mode: 'upsert' },
         { src: '.grok/commands/ai-engineering-loop.md', dest: path.join(grok, 'commands/ai-engineering-loop.md'), mode: 'upsert' }
@@ -52,7 +54,8 @@ function hostFileMap(home) {
       id: 'gemini',
       root: gemini,
       files: [
-        { src: '.gemini/skills/ai-engineering-loop/SKILL.md', dest: path.join(gemini, 'config/skills/ai-engineering-loop/SKILL.md'), mode: 'upsert' }
+        { src: '.gemini/skills/ai-engineering-loop/SKILL.md', dest: path.join(gemini, 'config/skills/ai-engineering-loop/SKILL.md'), mode: 'upsert' },
+        { src: 'adapters/dot/skills/task-impact-inquiry/SKILL.md', dest: path.join(gemini, 'config/skills/task-impact-inquiry/SKILL.md'), mode: 'upsert' }
       ]
     },
     {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-engineering-loop",
-  "version": "1.0.14",
+  "version": "1.0.15",
   "description": "A reusable, framework-agnostic AI Engineering Operating System for autonomous coding agents.",
   "main": "bin/ai-engineering-loop.js",
   "bin": {

package/tests/no-company-leak.test.js

@@ -0,0 +1,82 @@
+'use strict';
+
+const test = require('node:test');
+const assert = require('node:assert');
+const fs = require('fs');
+const path = require('path');
+
+const ROOT = path.join(__dirname, '..');
+
+const SKIP_DIR = new Set([
+  '.git',
+  'node_modules',
+  '.serena',
+  '.DS_Store'
+]);
+
+function walk(dir, out = []) {
+  for (const name of fs.readdirSync(dir)) {
+    if (SKIP_DIR.has(name)) continue;
+    const abs = path.join(dir, name);
+    const st = fs.lstatSync(abs);
+    if (st.isSymbolicLink()) continue;
+    if (st.isDirectory()) walk(abs, out);
+    else if (st.isFile()) out.push(abs);
+  }
+  return out;
+}
+
+function rel(abs) {
+  return path.relative(ROOT, abs).split(path.sep).join('/');
+}
+
+const FINGERPRINTS = [
+  { re: /dotify/i, label: 'dotify' },
+  { re: /bikin-rindu/i, label: 'bikin-rindu' },
+  { re: /hasNormalHours/, label: 'hasNormalHours' },
+  { re: /overtimeNote/, label: 'overtimeNote' },
+  { re: /attendanceConfirmation/i, label: 'attendanceConfirmation' },
+  { re: /internal-dotify/, label: 'internal-dotify' },
+  { re: /hanaaaca/, label: 'coworker handle' },
+  { re: /ulfa\.mufida/, label: 'coworker handle' },
+  { re: /kontribusi\/mattermost-agent/, label: 'local mattermost-agent checkout' },
+  { re: /dot-system\//, label: 'dot-system/' },
+  { re: /timeEntities/, label: 'timeEntities' },
+  { re: /resolveAttendanceConfirmation/, label: 'resolveAttendanceConfirmation' },
+  { re: /attendance-confirmations/, label: 'attendance-confirmations' }
+];
+
+test('packaged files do not embed real client tickets, schema, or machine paths', () => {
+  const files = walk(ROOT).filter((abs) => {
+    const r = rel(abs);
+    return !r.startsWith('tests/no-company-leak.test.js');
+  });
+  const hits = [];
+  for (const abs of files) {
+    const r = rel(abs);
+    let text;
+    try {
+      text = fs.readFileSync(abs, 'utf8');
+    } catch {
+      continue;
+    }
+    if (text.includes('\u0000')) continue;
+
+    if (r !== 'bin/ai-engineering-loop.js' && /gitlab\.dot\.co\.id/.test(text)) {
+      hits.push(`${r}: gitlab.dot.co.id (allowed only as adapter auto-detect in bin/)`);
+    }
+    if (r === 'bin/ai-engineering-loop.js' && /gitlab\.dot\.co\.id\/.+/.test(text)) {
+      hits.push(`${r}: gitlab.dot.co.id with a path (ticket URL)`);
+    }
+
+    const inSensitiveTree = r.startsWith('adapters/') || r.startsWith('examples/');
+    if (inSensitiveTree && /\/Users\/egagofur/.test(text)) {
+      hits.push(`${r}: /Users/egagofur`);
+    }
+
+    for (const { re, label } of FINGERPRINTS) {
+      if (re.test(text)) hits.push(`${r}: ${label}`);
+    }
+  }
+  assert.deepStrictEqual(hits, []);
+});

package/tests/skill-host-compat.test.js

@@ -166,17 +166,33 @@ test('Gemini Antigravity skill matches the loop and never uses Grok spawn keys o
   assert.match(gemini, /TRUE_INDEPENDENT_AGENT/);
 });
 
-test('DOT adapter locates task-impact-inquiry on Antigravity Gemini skills, not Claude', () => {
+test('task-impact-inquiry is Claude-safe and ships to Claude, Grok, and Gemini', () => {
+  const skill = readRepo('adapters/dot/skills/task-impact-inquiry/SKILL.md');
+  const { fm } = parseFrontmatter(skill, 'task-impact-inquiry');
+  assert.doesNotMatch(fm, /^description:\s*>-?/m);
+  assert.doesNotMatch(skill, /```mermaid/);
+  assert.doesNotMatch(skill, /\$\\/);
+  assert.doesNotMatch(skill, /spawn_subagent/);
+  assert.match(skill, /lifecycle/);
+  assert.match(skill, /ASCII/);
+  assert.match(skill, /failure table/);
+  assert.match(skill, /Do not interview again/);
+  assert.match(skill, /Passing unit tests are not isolation proof|Green unit tests/);
+  assert.match(skill, /New-dev briefing/);
+  assert.match(skill, /Hit map|Where it hits/);
+  assert.match(skill, /Do not generate an FSD/);
+  const grill = readRepo('core/grill-policy.md');
+  assert.match(grill, /Business blast radius/);
+  assert.match(grill, /~\/\.claude\/skills\/task-impact-inquiry/);
+  assert.match(grill, /~\/\.grok\/skills\/task-impact-inquiry/);
+  assert.match(grill, /~\/\.gemini\/config\/skills\/task-impact-inquiry/);
   const readme = readRepo('adapters/dot/README.md');
-  assert.match(readme, /~\/\.gemini\/config\/skills/);
   assert.match(readme, /task-impact-inquiry/);
-  assert.match(readme, /not from `~\/\.claude\/skills\/`/);
-  assert.doesNotMatch(readme, /and `~\/\.claude\/skills\/`/);
-  const grill = readRepo('core/grill-policy.md');
-  assert.match(grill, /task-impact-inquiry/);
-  assert.match(grill, /Do not skip grill/);
+  assert.match(readme, /~\/\.claude\/skills\//);
+  assert.doesNotMatch(readme, /not from `~\/\.claude\/skills\/`/);
   const wf = readRepo('.agents/workflows/ai-engineering-loop.md');
   assert.match(wf, /task-impact-inquiry/);
+  assert.match(wf, /blast radius: lifecycle sketch/);
 });
 
 test('DOT router sends commit-bound work to ai-engineering-loop; workflow is Stage 8 only', () => {
@@ -260,6 +276,7 @@ test('Failure table is required to freeze, TDD, verify, and Judge', () => {
     assert.match(text, /failure table/, rel);
     assert.match(text, /One red test per AC row/, rel);
     assert.match(text, /Do not freeze sunny-path-only/, rel);
+    assert.match(text, /blast radius: lifecycle sketch/, rel);
   }
 });
 

package/tests/sync-hosts.test.js

@@ -47,9 +47,27 @@ test('sync upserts Claude AEL files but does not invent DOT skills', () => {
   assert.ok(fs.existsSync(path.join(home, '.claude/agents/judge.md')));
   assert.ok(fs.existsSync(path.join(home, '.claude/commands/ai-engineering-loop.md')));
   assert.ok(!fs.existsSync(path.join(home, '.claude/skills/dot-dev-workflow/SKILL.md')));
+  assert.ok(fs.existsSync(path.join(home, '.claude/skills/task-impact-inquiry/SKILL.md')));
   assert.ok(!fs.existsSync(path.join(home, '.claude/settings.local.json')));
 });
 
+test('sync upserts task-impact-inquiry onto Claude, Grok, and Gemini', () => {
+  const home = tmpHome();
+  fs.mkdirSync(path.join(home, '.claude'));
+  fs.mkdirSync(path.join(home, '.grok'));
+  fs.mkdirSync(path.join(home, '.gemini'));
+  applyHostSync({ packageRoot: ROOT, home });
+  const claude = fs.readFileSync(path.join(home, '.claude/skills/task-impact-inquiry/SKILL.md'), 'utf8');
+  const grok = fs.readFileSync(path.join(home, '.grok/skills/task-impact-inquiry/SKILL.md'), 'utf8');
+  const gemini = fs.readFileSync(path.join(home, '.gemini/config/skills/task-impact-inquiry/SKILL.md'), 'utf8');
+  assert.match(claude, /name: task-impact-inquiry/);
+  assert.doesNotMatch(claude, /```mermaid/);
+  assert.match(claude, /New-dev briefing/);
+  assert.match(grok, /^user-invocable: true$/m);
+  assert.match(grok, /Where it hits/);
+  assert.match(gemini, /Business blast radius|blast radius/);
+});
+
 test('DOT skills update only when already installed', () => {
   const home = tmpHome();
   const dest = path.join(home, '.claude/skills/dot-dev-workflow/SKILL.md');
@@ -84,7 +102,7 @@ test('dry-run does not write; second apply is current', () => {
   assert.ok(!fs.existsSync(path.join(home, '.gemini/config/skills/ai-engineering-loop/SKILL.md')));
   applyHostSync({ packageRoot: ROOT, home });
   const again = applyHostSync({ packageRoot: ROOT, home });
-  assert.strictEqual(summarizeHostSync(again.filter((item) => item.id === 'gemini')).current, 1);
+  assert.strictEqual(summarizeHostSync(again.filter((item) => item.id === 'gemini')).current, 2);
   assert.strictEqual(summarizeHostSync(again.filter((item) => item.id === 'gemini')).copy, 0);
 });
 

package/examples/dot/attendance-confirmation/README.md

@@ -1,22 +0,0 @@
-# Reference Example: Attendance Confirmation Status Fix
-
-## 1. Context & Scenario
-
-This reference walkthrough demonstrates how a complex real-world bug in the DOT ecosystem moves through the complete **AI Engineering Loop** and is subsequently delivered via the **DOT Delivery Adapter**.
-
-### The Problem
-In the Dotify employee portal, attendance confirmation cards displayed an incorrect status (`"PENDING"`) for employees working overtime or on weekends, even when all underlying time logs had already been approved or rejected. Furthermore, non-normal hours employees (shift workers) had their records mistakenly treated under standard 9-to-5 rules.
-
----
-
-## 2. Walkthrough Stages & Artifacts
-
-1. **[Stage 1: Goal Contract (`goal-contract.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/dot/attendance-confirmation/goal-contract.md)**:
-   - Formalized objective, acceptance criteria (normal hours, weekends, non-normal hours, null values), and verification plan.
-2. **[Stage 2: Adversarial Review & Triage (`review-findings.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/dot/attendance-confirmation/review-findings.md)**:
-   - Independent Devil's Advocate review flagging a timezone offset bug (`COR-001`) and an invalid nitpick (`MAINT-001`).
-   - Maker Agent triage and surgical resolution.
-3. **[Stage 3: Judge Evaluation & Verdict (`judge-verdict.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/dot/attendance-confirmation/judge-verdict.md)**:
-   - Audit of unit test results, typecheck logs, finding resolutions, and issuance of `PASS` verdict.
-4. **[Stage 4: DOT Delivery Pipeline (`delivery-report.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/dot/attendance-confirmation/delivery-report.md)**:
-   - Creation of GitLab Issue #307, base MR !946, multi-branch propagation to `staging` (!947) and `develop` (!948), Coreview bot triage, and automated Mattermost channel notification.

package/examples/dot/attendance-confirmation/delivery-report.md

@@ -1,51 +0,0 @@
-# DOT Delivery Report: Attendance Confirmation Fix
-
-## 1. Summary of Delivery Actions
-
-Upon receiving the `PASS` verdict from the Judge Agent, the DOT Delivery Adapter executed the following release actions:
-
-1. **GitLab Issue Created**: [Issue #307 - [BE] [Attendance] Fix Attendance Confirmation Display Status](https://gitlab.dot.co.id/dot-system/dotify-new/-/issues/307).
-2. **Primary MR Created**: [MR !946 targeting `main`](https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/946).
-3. **Multi-Branch Cherry-Pick**:
-   - [MR !947 targeting `staging`](https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/947).
-   - [MR !948 targeting `develop`](https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/948).
-4. **Coreview Bot Triage**:
-   - Comments fetched on MR !948. Zero blocking comments found.
-5. **Mattermost Notification**:
-   - Resolved repository `dot-system/dotify-new` to channel `"internal-dotify"`.
-   - Dispatched Markdown report via MCP `mattermost_send_message` with `from: "AI Agent"`.
-
----
-
-## 2. GitLab Links
-
-| Artifact | Branch | Link |
-|---|---|---|
-| **GitLab Issue** | — | `[Issue #307](https://gitlab.dot.co.id/dot-system/dotify-new/-/issues/307)` |
-| **Merge Request DEV** | `develop` | `[MR !948](https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/948)` |
-| **Merge Request STAGING** | `staging` | `[MR !947](https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/947)` |
-| **Merge Request MAIN** | `main` | `[MR !946](https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/946)` |
-
----
-
-## 3. Dispatched Mattermost Notification
-
-```text
-[MR DEV] https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/948
-Changes log 
-- Include user.type.hasNormalHours and timeEntities.overtimeNote in attendanceConfirmationPagination Prisma query.
-- Create resolveAttendanceConfirmationDisplayStatus utility to properly evaluate hasPendingTimeEntities by checking overtimeNote, isWeekend, duration > 8, non-normal hours employees, and null statuses.
-- Add comprehensive unit tests in src/server/attendance-confirmations/utils/resolve-display-status.test.ts covering all status permutations.
-
-[MR STAGING] https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/947
-Changes log 
-- Include user.type.hasNormalHours and timeEntities.overtimeNote in attendanceConfirmationPagination Prisma query.
-- Create resolveAttendanceConfirmationDisplayStatus utility to properly evaluate hasPendingTimeEntities by checking overtimeNote, isWeekend, duration > 8, non-normal hours employees, and null statuses.
-- Add comprehensive unit tests in src/server/attendance-confirmations/utils/resolve-display-status.test.ts covering all status permutations.
-
-[MR MAIN] https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/946
-Changes log 
-- Include user.type.hasNormalHours and timeEntities.overtimeNote in attendanceConfirmationPagination Prisma query.
-- Create resolveAttendanceConfirmationDisplayStatus utility to properly evaluate hasPendingTimeEntities by checking overtimeNote, isWeekend, duration > 8, non-normal hours employees, and null statuses.
-- Add comprehensive unit tests in src/server/attendance-confirmations/utils/resolve-display-status.test.ts covering all status permutations.
-```

package/examples/dot/attendance-confirmation/goal-contract.md

@@ -1,39 +0,0 @@
-# Goal Contract: Attendance Confirmation Display Status Fix
-
-## 1. Objective
-Fix the incorrect calculation of attendance confirmation display statuses across list and pagination endpoints when time entities contain overtime notes, weekend logs, non-normal hours employees, or null record states.
-
-## 2. Business Outcome & User Lifecycle Impact
-- **Employees**: View accurate confirmation statuses (APPROVED, REJECTED, NEED_APPROVAL) reflecting their true attendance record.
-- **Managers / Reviewers**: Stop receiving false-positive pending approval notifications for already-settled weekend logs.
-- **HR & Payroll**: Accurate cumulative duration calculations for payroll export.
-
-## 3. Acceptance Criteria (AC)
-- [ ] **AC-1**: If an employee has `hasNormalHours = true` and `duration <= 8` on a standard weekday without overtime notes, display status must resolve to `APPROVED` or `NEED_APPROVAL` strictly based on clock-in/out presence.
-- [ ] **AC-2**: If `overtimeNote` exists or `duration > 8` or `isWeekend = true`, evaluate pending status across all associated `timeEntities`.
-- [ ] **AC-3**: Non-normal hours employees (`user.type.hasNormalHours = false`) must not be evaluated under 8-hour weekday thresholds.
-- [ ] **AC-4**: Null or missing time entity collections must default safely to `APPROVED` without throwing runtime `TypeError`.
-- [ ] **AC-5**: Backward compatibility of the tRPC/REST response contract must be strictly preserved.
-
-## 4. Technical Constraints
-- Preserve existing Prisma query schemas in `attendanceConfirmationPagination`.
-- Centralize logic in a pure, testable utility function: `resolveAttendanceConfirmationDisplayStatus`.
-- No new external runtime dependencies (use existing `dayjs` and `lodash` packages).
-- 0 TypeScript compiler errors on `tsc --noEmit`.
-
-## 5. Out of Scope
-- Modifying the UI frontend component layouts in `dotify-new/web`.
-- Database schema migrations or alter table statements.
-- Changing payroll export report generation scripts.
-
-## 6. Verification Requirements
-- **Unit Tests**: Comprehensive Jest test suite in `src/server/attendance-confirmations/utils/resolve-display-status.test.ts` covering 100% of branches.
-- **Typecheck**: `npx tsc --noEmit` exits with 0.
-- **Linter**: `npx eslint --fix` on modified files with 0 errors.
-- **Regression**: Run entire test suite: `npx jest --testPathIgnorePatterns="dotify-api"`.
-
-## 7. Definition of Done (DoD)
-- [ ] All AC-1 through AC-5 proven by unit tests.
-- [ ] Deterministic verification passes 100%.
-- [ ] Devil's Advocate review conducted with 0 unresolved blocking findings.
-- [ ] Judge issues PASS verdict.

package/examples/dot/attendance-confirmation/judge-verdict.md

@@ -1,43 +0,0 @@
-# Judge Evaluation Report: Attendance Confirmation Fix
-
-## 1. Executive Verdict
-- **Verdict**: `PASS`
-- **Iteration**: `Iteration 2 of 3`
-- **Confidence**: `HIGH`
-
----
-
-## 2. Deterministic Verification Audit
-
-| Check | Command Executed | Raw Result | Status |
-|---|---|---|:---:|
-| **Unit Tests** | `npx jest src/server/attendance-confirmations/utils/resolve-display-status.test.ts` | `Tests: 12 passed, 12 total. Snapshots: 0. Time: 1.42s` | ✅ PASS |
-| **Full Suite** | `npx jest --testPathIgnorePatterns="dotify-api"` | `Test Suites: 48 passed, 48 total. Tests: 382 passed.` | ✅ PASS |
-| **TypeScript** | `npx tsc --noEmit` | `Exit code 0. Zero errors.` | ✅ PASS |
-| **Linter** | `npx eslint --fix src/server/attendance-confirmations/**` | `0 errors, 0 warnings found.` | ✅ PASS |
-
----
-
-## 3. Goal Contract Compliance Audit
-
-| Criterion | Verified By Test / Artifact | Result |
-|---|---|:---:|
-| **AC-1**: Normal hours weekday calculation | `resolve-display-status.test.ts > normal hours` | ✅ PASS |
-| **AC-2**: Weekend & duration > 8 handling | `resolve-display-status.test.ts > weekend overtime` | ✅ PASS |
-| **AC-3**: Non-normal hours employee rules | `resolve-display-status.test.ts > shift worker` | ✅ PASS |
-| **AC-4**: Null & undefined timeEntities safety | `resolve-display-status.test.ts > null safety` | ✅ PASS |
-| **AC-5**: API Contract Preservation | `tRPC router typecheck` | ✅ PASS |
-
----
-
-## 4. Finding Triage Audit
-
-- **COR-001 (High - Null Safety)**: Maker applied null coalescing in Iteration 2. Verified via fresh test execution. **Status: RESOLVED & VERIFIED**.
-- **MAINT-001 (Low - Factory Suggestion)**: Overridden by Judge as invalid speculative nitpick. **Status: DISMISSED / INVALID**.
-
----
-
-## 5. Formal Conclusion & Hand-off
-
-The Definition of Done has been 100% satisfied with reproducible evidence.
-**Authorized next action**: Proceed to [DOT Delivery Adapter](file:///Users/egagofur/Development/work/ai-engineering-loop/adapters/dot/README.md) for GitLab MR generation, multi-branch cherry-picking, Coreview triage, and Mattermost notification.