ai-engineering-loop 1.0.14 → 1.0.15

package/.agents/workflows/ai-engineering-loop.md

@@ -5,7 +5,7 @@ description: Run the AI Engineering Loop on Antigravity (init, status, refresh,
 
 Follow `policies/review-budget.md`. Parent is Maker plus orchestrator. Do not use `browser_subagent`.
 
-Stage 1: if the user asks for ideas, list a short menu and wait; do not implement. Grill if the task is ambiguous (`core/grill-policy.md`), then freeze the Goal Contract file. Chat agreement is not freeze. On `adapter_type: dot`, that grill includes `task-impact-inquiry` (Antigravity skill under `~/.gemini/config/skills/`); do not run a second interview. Use `.ai-engineering-loop/glossary.md`. Name test seams. AC is a failure table (happy, empty/omit, boundary, sibling, error). One red test per AC row. Do not freeze sunny-path-only. Maker: TDD at those seams (`policies/tdd-policy.md`): one red test per AC row. Bugs: red repro first (`core/root-cause-analysis.md`). Mid-loop stop: `core/handoff-policy.md`.
+Stage 1: if the user asks for ideas, list a short menu and wait; do not implement. Grill if the task is ambiguous (`core/grill-policy.md`), then freeze the Goal Contract file. Chat agreement is not freeze. On business-logic change, and always on `adapter_type: dot`, grill includes blast radius: lifecycle sketch, four pillars (state, sibling, approval, queues), ASCII picture. Load `task-impact-inquiry` if present. Do not run a second interview. Passing unit tests are not isolation proof. Use `.ai-engineering-loop/glossary.md`. Name test seams. AC is a failure table (happy, empty/omit, boundary, sibling, error). One red test per AC row. Do not freeze sunny-path-only. Maker: TDD at those seams (`policies/tdd-policy.md`): one red test per AC row. Bugs: red repro first (`core/root-cause-analysis.md`). Mid-loop stop: `core/handoff-policy.md`.
 
 If `invoke_subagent` (or Task) exists, spawn `devil-advocate` then `judge` as siblings. Wait for each child. Do not run them in the background. Use `general-purpose` only if the named type is rejected.
 

package/.claude/skills/ai-engineering-loop/SKILL.md

@@ -32,7 +32,7 @@ Claude Code talks to strict proxies (including Kiro). Follow this exactly:
 Parent session is Maker plus orchestrator. Spawn Devil's Advocate and Judge as **siblings**, not nested.
 
 1. Stage 0: `npx ai-engineering-loop sync-hosts` then `npx ai-engineering-loop status` (init or refresh if missing or stale). Read `.ai-engineering-loop/glossary.md`. If sync-hosts copied files, tell the user a new session is needed for updated skill text; keep going with this session.
-2. Stage 1: Goal Contract (`core/goal-contract.md`). If the user asks for ideas, list a short menu and wait; do not implement. If the task is ambiguous and the user can answer, grill first (`core/grill-policy.md`): design tree, recommended answers, do not ask look-up facts. Skip grill if the contract is already frozen or the user waived it. On `adapter_type: dot`, that grill includes the four-pillar blast radius (state, sibling, approval, queues). Do not run a second interview. Chat agreement is not freeze: every user-visible decision must be a numbered AC in the Goal Contract file. Freeze before any production edit. Name test seams. Use glossary terms. AC is a failure table (happy, empty/omit, boundary, sibling, error). One red test per AC row. Do not freeze sunny-path-only.
+2. Stage 1: Goal Contract (`core/goal-contract.md`). If the user asks for ideas, list a short menu and wait; do not implement. If the task is ambiguous and the user can answer, grill first (`core/grill-policy.md`): design tree, recommended answers, do not ask look-up facts. Skip grill if the contract is already frozen or the user waived it. On business-logic change, and always on `adapter_type: dot`, grill includes blast radius: lifecycle sketch, four pillars (state, sibling, approval, queues), ASCII picture. Load `task-impact-inquiry` if present. Do not run a second interview. Passing unit tests are not isolation proof. Chat agreement is not freeze: every user-visible decision must be a numbered AC in the Goal Contract file. Freeze before any production edit. Name test seams. Use glossary terms. AC is a failure table (happy, empty/omit, boundary, sibling, error). One red test per AC row. Do not freeze sunny-path-only.
 3. Stages 2-4: Maker in the parent. Bugs: red repro first (`core/root-cause-analysis.md`). Features: TDD at named seams (`policies/tdd-policy.md`): one red test per AC row. Surgical diff.
 4. Stage 5: run commands from `.ai-engineering-loop/verification.md`. Keep command, exit code, stdout, test counts. Vague "seems green" is invalid.
 5. Write artifacts, then spawn. Before Devil's Advocate:

package/.gemini/skills/ai-engineering-loop/SKILL.md

@@ -25,7 +25,7 @@ Canonical mode ids: `TRUE_INDEPENDENT_AGENT`, `ISOLATED_AGENT_INSTANCE`, `FRESH_
 ## Loop
 
 1. Stage 0: `npx ai-engineering-loop sync-hosts` then `npx ai-engineering-loop status` (init or refresh if missing or stale). Read `.ai-engineering-loop/glossary.md`. If sync-hosts copied files, tell the user a new session is needed for updated skill text; keep going with this session.
-2. Stage 1: Goal Contract (`core/goal-contract.md`). If the user asks for ideas, list a short menu and wait; do not implement. If the task is ambiguous and the user can answer, grill first (`core/grill-policy.md`): design tree, recommended answers, do not ask look-up facts. Skip grill if the contract is already frozen or the user waived it. On `adapter_type: dot`, that grill includes `task-impact-inquiry` (this host: `~/.gemini/config/skills/task-impact-inquiry`); do not run a second interview. Chat agreement is not freeze: every user-visible decision must be a numbered AC in the Goal Contract file. Freeze before any production edit. Name test seams. Use glossary terms. AC is a failure table (happy, empty/omit, boundary, sibling, error). One red test per AC row. Do not freeze sunny-path-only.
+2. Stage 1: Goal Contract (`core/goal-contract.md`). If the user asks for ideas, list a short menu and wait; do not implement. If the task is ambiguous and the user can answer, grill first (`core/grill-policy.md`): design tree, recommended answers, do not ask look-up facts. Skip grill if the contract is already frozen or the user waived it. On business-logic change, and always on `adapter_type: dot`, grill includes blast radius: lifecycle sketch, four pillars (state, sibling, approval, queues), ASCII picture. Load `task-impact-inquiry` if present. Do not run a second interview. Passing unit tests are not isolation proof. Chat agreement is not freeze: every user-visible decision must be a numbered AC in the Goal Contract file. Freeze before any production edit. Name test seams. Use glossary terms. AC is a failure table (happy, empty/omit, boundary, sibling, error). One red test per AC row. Do not freeze sunny-path-only.
 3. Stages 2-4: Maker in the parent. Bugs: red repro first (`core/root-cause-analysis.md`). Features: TDD at named seams (`policies/tdd-policy.md`): one red test per AC row. Surgical diff.
 4. Stage 5: run commands from `.ai-engineering-loop/verification.md`. Keep command, exit code, stdout, test counts. Vague "seems green" is invalid.
 5. Write artifacts, then spawn. Before Devil's Advocate:

package/.grok/skills/ai-engineering-loop/SKILL.md

@@ -45,7 +45,7 @@ Run `npx ai-engineering-loop <command>` in the target repo. Do not commit unless
 ### `/ai-engineering-loop [task]`
 
 1. Stage 0: `npx ai-engineering-loop sync-hosts` then `npx ai-engineering-loop status` (init/refresh if missing or stale). Read `.ai-engineering-loop/glossary.md`. If sync-hosts copied files, tell the user a new session is needed for updated skill text; keep going with this session.
-2. Stage 1: Goal Contract (`core/goal-contract.md`). If the user asks for ideas, list a short menu and wait; do not implement. If the task is ambiguous and the user can answer, grill first (`core/grill-policy.md`): design tree, recommended answers, do not ask look-up facts. Skip grill if the contract is already frozen or the user waived it. On `adapter_type: dot`, that grill includes the four-pillar blast radius (state, sibling, approval, queues). Do not run a second interview. Chat agreement is not freeze: every user-visible decision must be a numbered AC in the Goal Contract file. Freeze before any production edit. Name test seams. Use glossary terms. AC is a failure table (happy, empty/omit, boundary, sibling, error). One red test per AC row. Do not freeze sunny-path-only.
+2. Stage 1: Goal Contract (`core/goal-contract.md`). If the user asks for ideas, list a short menu and wait; do not implement. If the task is ambiguous and the user can answer, grill first (`core/grill-policy.md`): design tree, recommended answers, do not ask look-up facts. Skip grill if the contract is already frozen or the user waived it. On business-logic change, and always on `adapter_type: dot`, grill includes blast radius: lifecycle sketch, four pillars (state, sibling, approval, queues), ASCII picture. Load `task-impact-inquiry` if present. Do not run a second interview. Passing unit tests are not isolation proof. Chat agreement is not freeze: every user-visible decision must be a numbered AC in the Goal Contract file. Freeze before any production edit. Name test seams. Use glossary terms. AC is a failure table (happy, empty/omit, boundary, sibling, error). One red test per AC row. Do not freeze sunny-path-only.
 3. Stages 2–4: Maker work in the **parent**. Bugs: red repro first (`core/root-cause-analysis.md`). Features: TDD at named seams (`policies/tdd-policy.md`): one red test per AC row. Surgical diff. Parent may be the Maker; do not spawn Maker as a child if you still need to spawn DA/Judge afterward from the same parent.
 4. Stage 5: run verification from `.ai-engineering-loop/verification.md`. Keep command, exit code, stdout, test counts. Vague "seems green" is invalid.
 5. Write artifacts to disk so children do not need parent chat:

package/README.md

@@ -6,7 +6,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](https://github.com/egagofur/ai-engineering-loop/pulls)
 [![AI Engineering](https://img.shields.io/badge/AI-Engineering%20Loop-orange.svg)](https://github.com/egagofur/ai-engineering-loop)
-[![Release](https://img.shields.io/badge/release-v1.0.14-purple.svg)](https://github.com/egagofur/ai-engineering-loop/releases)
+[![Release](https://img.shields.io/badge/release-v1.0.15-purple.svg)](https://github.com/egagofur/ai-engineering-loop/releases)
 
 **A Reusable, Framework-Agnostic AI Engineering Operating System for Autonomous Coding Agents**
 
@@ -64,7 +64,7 @@ The 8-stage loop stays one OS. These techniques sit **inside** existing stages (
 
 | Stage | Technique | Spec |
 |---|---|---|
-| 1 | Grill until the design-tree frontier is empty, then freeze the Goal Contract. Idea requests: menu, wait, then grill the pick. Chat `setuju` is not freeze; user-visible decisions must be numbered AC in the contract file. AC is a **failure table** (happy, empty/omit, boundary, sibling, error), not sunny path only. | `core/grill-policy.md` |
+| 1 | Grill until the design-tree frontier is empty, then freeze the Goal Contract. Idea requests: menu, wait, then grill the pick. Chat `setuju` is not freeze; user-visible decisions must be numbered AC in the contract file. AC is a **failure table** (happy, empty/omit, boundary, sibling, error), not sunny path only. Business-logic change: **blast radius** (lifecycle sketch, four pillars, ASCII picture) via `task-impact-inquiry` inside grill — not a second loop. Passing unit tests are not isolation proof. | `core/grill-policy.md` |
 | 1 | Ubiquitous language in `.ai-engineering-loop/glossary.md`; load-bearing choices in `.ai-engineering-loop/adrs/` | `core/repo-config-schema.md` |
 | 2 | Bugs: red repro → minimise → hypothesise → instrument → fix | `core/root-cause-analysis.md` |
 | 4–5 | Red-green at named **seams**; failure table (not happy path only); coverage is a map; no grep/tautology | `policies/tdd-policy.md` |
@@ -182,7 +182,7 @@ npx ai-engineering-loop run
 npx ai-engineering-loop sync-hosts
 ```
 
-`sync-hosts` updates only hosts that already exist on the machine. DOT skills (`dot-dev-skill-router`, `dot-dev-workflow`) are updated only if they are already installed. It does not install `task-impact-inquiry`. After a copy, start a new session so the host reloads skill text. `/ai-engineering-loop` Stage 0 and `run` call `sync-hosts` so a published package bump reaches global host files without a manual copy.
+`sync-hosts` updates only hosts that already exist on the machine. DOT skills (`dot-dev-skill-router`, `dot-dev-workflow`) are updated only if they are already installed. `task-impact-inquiry` is upserted onto Claude, Grok, and Gemini so blast-radius grill is available on those hosts. After a copy, start a new session so the host reloads skill text. `/ai-engineering-loop` Stage 0 and `run` call `sync-hosts` so a published package bump reaches global host files without a manual copy.
 
 ---
 

package/adapters/dot/README.md

@@ -2,7 +2,7 @@
 
 ## 1. Overview & Architecture
 
-The **DOT Delivery Adapter** connects the generic [AI Engineering Loop](file:///Users/egagofur/Development/work/ai-engineering-loop/README.md) to the specific development infrastructure of **DOT Indonesia**.
+The **DOT Delivery Adapter** connects the generic [AI Engineering Loop](../../README.md) to DOT's delivery tools (GitLab, multi-branch, Coreview, Mattermost).
 
 The generic engineering loop guarantees that code is correct, verified, and adversarially tested. The DOT adapter is responsible for downstream release engineering, collaboration tools, issue tracking, and multi-environment synchronization.
 
@@ -27,18 +27,18 @@ flowchart TD
 
 The DOT adapter is organized into four dedicated specification modules:
 
-1. **[GitLab Integration (`gitlab.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/adapters/dot/gitlab.md)**:
+1. **[GitLab Integration (`gitlab.md`)](gitlab.md)**:
    - CLI automation with `glab`.
    - Standardized issue card templates with actual vs expected tables and QA testing steps.
    - Standardized MR descriptions linking issue IDs and change summaries.
-2. **[Multi-Branch Propagation (`multi-branch.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/adapters/dot/multi-branch.md)**:
+2. **[Multi-Branch Propagation (`multi-branch.md`)](multi-branch.md)**:
    - Multi-environment branching model across `main`, `staging`, and `develop`.
    - Clean cherry-picking workflow and target-specific test verification.
-3. **[Coreview External Reviewer Triage (`coreview.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/adapters/dot/coreview.md)**:
+3. **[Coreview External Reviewer Triage (`coreview.md`)](coreview.md)**:
    - Ingestion of `@coreview-bot` automated PR comments.
    - Mandatory Phase 8 Triage reporting gate before Mattermost dispatch.
    - Rigorous evaluation of bot suggestions into `VALID` (fix & propagate) vs `HALU` (false positive pushback) using principles from `gitlab-mr-feedback` and `receiving-code-review`.
-4. **[Mattermost Notifications (`mattermost.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/adapters/dot/mattermost.md)**:
+4. **[Mattermost Notifications (`mattermost.md`)](mattermost.md)**:
    - Repository-to-channel resolution using persistent configuration.
    - MCP `mattermost_send_message` dispatch with mandatory `from: "AI Agent"` attribution.
    - Environment-tagged Markdown blocks (`[MR DEV]`, `[MR STAGING]`, `[MR MAIN]`) formatted with strict **`no-ai-slop`** human-written standards.
@@ -47,7 +47,7 @@ The DOT adapter is organized into four dedicated specification modules:
 
 ## 3. Official DOT Engineering Skills Integration
 
-This adapter composes the DOT skill suite that Antigravity loads from `~/.gemini/config/skills/` (not from `~/.claude/skills/` and not from this npm package). Claude Code and Grok do not get these skills unless the same files are installed on those hosts.
+This adapter composes the DOT skill suite. `task-impact-inquiry` ships in this package (`adapters/dot/skills/task-impact-inquiry/`) and `sync-hosts` upserts it to Claude, Grok, and Gemini. Other DOT skills (router, workflow) still update-if-exists only.
 
 On a DOT repo (`adapter_type: dot`), **run `ai-engineering-loop`**, not the old 9-phase `dot-dev-workflow`, as the engineering OS. Stage 1 grill **includes** `task-impact-inquiry`. Do not run a second interview. After Judge `PASS`, Stage 8 is `dot-dev-workflow` delivery (GitLab, cherry-pick, Coreview, Mattermost). Canonical copies: `adapters/dot/skills/`. See `core/grill-policy.md`.
 
@@ -56,7 +56,7 @@ On a DOT repo (`adapter_type: dot`), **run `ai-engineering-loop`**, not the old
 | **`ai-engineering-loop`** | Engineering OS (Stages 0-7). Use this for DOT bugfix/feature/refactor. |
 | **`dot-dev-workflow`** | Stage 8 delivery only after Judge PASS. Not a parallel engineering loop. |
 | **`dot-dev-skill-router`** | Routes commit-bound DOT work to `ai-engineering-loop`, then Stage 8. |
-| **`task-impact-inquiry`** | Antigravity skill at `~/.gemini/config/skills/task-impact-inquiry/`. Four-pillar blast radius (state, sibling, approval, downstream queues). Fills Stage 1 grill on DOT; then freeze the Goal Contract. |
+| **`task-impact-inquiry`** | Business blast radius (lifecycle sketch, four pillars, ASCII picture). Canonical: `adapters/dot/skills/task-impact-inquiry/`. Host copies: `~/.claude/skills/`, `~/.grok/skills/`, `~/.gemini/config/skills/`. Fills Stage 1 grill; impact-only stops after the matrix. Not a parallel OS. |
 | **`backend-development`** | Framework-agnostic backend guidelines (clean naming, database queries, security, error handling). |
 | **`backend-safety-guardrails`** | 6 architectural backend safety invariants (queue bypass, BigInt, status recalculation loops). |
 | **`devils-advocate`** | Legacy DOT pre-commit skill. On AEL, Stages 6-7 are package Devil's Advocate + Judge. Do not re-run this skill after Judge PASS. |
@@ -73,7 +73,7 @@ On a DOT repo (`adapter_type: dot`), **run `ai-engineering-loop`**, not the old
 | Generic Core Responsibility | DOT Adapter Responsibility |
 |---|---|
 | Goal Contract & Acceptance Criteria | GitLab Issue Card drafting |
-| Unit testing, typecheck, lint, build | Running DOT-specific scripts (`npx jest --testPathIgnorePatterns="dotify-api"`) |
+| Unit testing, typecheck, lint, build | Commands from `.ai-engineering-loop/verification.md` |
 | Internal Devil's Advocate Review | External `@coreview-bot` triage on GitLab MRs |
 | Judge verdict & completion certificate | Multi-environment cherry-picking & branch synchronization |
 | Evidence collection & finding logs | Mattermost channel notifications & MR link delivery |

package/adapters/dot/coreview.md

@@ -67,7 +67,8 @@ Every Coreview comment must be categorized into one of two paths:
   1. Apply the fix surgically to the local working branch.
   2. Re-run all unit tests and static analysis:
      ```bash
-     npx jest --testPathIgnorePatterns="dotify-api"
+     # commands from .ai-engineering-loop/verification.md
+     npx jest
      npx tsc --noEmit
      ```
   3. Commit and push the fix to the branch:
@@ -104,4 +105,4 @@ Every Coreview comment must be categorized into one of two paths:
 
 ## 5. Anti-Pattern: Blind Compliance
 
-Agents must **never** rewrite working, verified code solely because an automated review bot posted a comment. If the bot's suggestion violates the [Goal Contract](file:///Users/egagofur/Development/work/ai-engineering-loop/core/goal-contract.md) or introduces broken dependencies, it MUST be triaged as `HALU` with evidence.
+Agents must **never** rewrite working, verified code solely because an automated review bot posted a comment. If the bot's suggestion violates the [Goal Contract](../../core/goal-contract.md) or introduces broken dependencies, it MUST be triaged as `HALU` with evidence.

package/adapters/dot/gitlab.md

@@ -2,7 +2,7 @@
 
 ## 1. Purpose & Scope
 
-This module encapsulates all GitLab operations within the DOT ecosystem. Once a code change has successfully passed the [Generic AI Engineering Loop](file:///Users/egagofur/Development/work/ai-engineering-loop/README.md), this adapter automates issue tracking and Merge Request (MR) generation via the `glab` CLI.
+This module encapsulates GitLab operations for the DOT adapter. Once a change has passed the [generic AI Engineering Loop](../../README.md), this adapter automates issue tracking and Merge Request (MR) generation via the `glab` CLI.
 
 ---
 
@@ -54,7 +54,7 @@ flowchart TD
     ```
 
 ### B. Create Standardized Issue Card
-If no issue exists, create one in the designated tracker (e.g. `dot-system/dotify-new` for central Dotify tracker, or the target repository):
+If no issue exists, create one in the current repository (or the tracker named in `.ai-engineering-loop/adapter.md`):
 
 ```bash
 glab issue create \
@@ -79,7 +79,7 @@ glab issue create \
 ## Testing Steps
 1. Login as [User Role / Email].
 2. Navigate to [Target Menu / URL].
-3. Perform [Action e.g. submit attendance, clock-in, approve overtime].
+3. Perform [Action e.g. submit the form, approve the request].
 4. Verify [Expected Result].
 
 ## Expectation

package/adapters/dot/mattermost.md

@@ -2,74 +2,70 @@
 
 ## 1. Overview & Objectives
 
-The **Mattermost Notification Module** formats final release notes and automatically delivers them to designated team channels via the Mattermost MCP server or CLI.
+The **Mattermost Notification Module** formats final release notes and delivers them to team channels via the Mattermost MCP server or CLI.
 
-This provides seamless visibility to QA engineers, product managers, and reviewers upon successful completion of the delivery pipeline.
+This gives QA, product, and reviewers visibility when the delivery pipeline finishes.
 
 ---
 
 ## 2. Channel Resolution & Dispatch Flow
 
-```mermaid
-flowchart TD
-    Complete[MRs Created Across Environments] --> CheckMap[Check /Users/egagofur/.gemini/config/mattermost-channel-mapping.json]
-    
-    CheckMap --> Found{Channel Found for Repo?}
-    
-    Found -->|Yes| Dispatch[Dispatch via MCP mattermost_send_message]
-    Found -->|No| PromptUser[Ask User for Target Channel]
-    
-    PromptUser --> SaveMap[Save New Channel to mattermost-channel-mapping.json]
-    SaveMap --> Dispatch
-    
-    Dispatch --> CheckMCP{MCP Success?}
-    CheckMCP -->|Yes| Done([Notification Complete])
-    CheckMCP -->|No / Failed| FallbackCLI[Fallback to Mattermost Agent CLI]
-    FallbackCLI --> Done
+```text
+MRs created
+  -> read ~/.gemini/config/mattermost-channel-mapping.json
+     -> channel found  -> MCP mattermost_send_message
+     -> channel missing -> ask user, save mapping, then send
+  -> if MCP fails -> Mattermost agent CLI once
 ```
 
+Do not hard-code a machine path. The mapping file lives under the user's home directory.
+
 ---
 
 ## 3. Mandatory Attribution Rule
 
-> [!IMPORTANT]
-> When sending messages or replying to threads on Mattermost (via MCP tools or CLI):
-> - **Always** include the sender attribution parameter (`from: "AI Agent"`) in MCP calls:
->   ```json
->   {
->     "channel": "internal-dotify",
->     "message": "...",
->     "from": "AI Agent"
->   }
->   ```
-> - **Always** include the CLI flag (`--from "AI Agent"`) in CLI calls:
->   ```bash
->   node /Users/egagofur/Development/work/kontribusi/mattermost-agent/dist/cli/index.js send <channel> "<message>" --from "AI Agent"
->   ```
-> - Do not omit or suppress sender attribution.
+When sending messages or replying to threads (MCP or CLI):
+
+- Always set sender attribution (`from: "AI Agent"`) in MCP calls:
+
+```json
+{
+  "channel": "<team-channel>",
+  "message": "...",
+  "from": "AI Agent"
+}
+```
+
+- Always pass `--from "AI Agent"` on the CLI:
+
+```bash
+<mattermost-cli> send <channel> "<message>" --from "AI Agent"
+```
+
+Resolve the CLI from PATH or the command the user already uses. Do not embed another developer's local checkout.
 
 ---
 
 ## 4. Channel Resolution Logic
 
-1. **Inspect Mapping File**:
-   Read `/Users/egagofur/.gemini/config/mattermost-channel-mapping.json` using the current repository name or project slug (e.g. `dotify-new`, `dotify-api`, `dot-system/dotify-new`).
-2. **Channel Found**:
-   Dispatch message to the mapped channel name (e.g. `"internal-dotify"`).
-3. **Channel Unknown**:
-   - **DO NOT GUESS** or broadcast to arbitrary channels.
-   - Ask the user to specify the target channel for this repository.
-   - Immediately persist the user's answer into `/Users/egagofur/.gemini/config/mattermost-channel-mapping.json` for future automated runs.
+1. **Inspect mapping file**:
+   Read `~/.gemini/config/mattermost-channel-mapping.json` using the current repository name or `git` remote slug (`<group>/<repo>`).
+2. **Channel found**:
+   Dispatch to that channel name.
+3. **Channel unknown**:
+   - Do not guess or broadcast.
+   - Ask the user for the channel for this repository.
+   - Persist the answer in `~/.gemini/config/mattermost-channel-mapping.json`.
 
 ---
 
 ## 5. Standardized Mattermost Markdown Report Format (No AI Slop + Human-Written + PIC at End)
 
-Render separate, ready-to-copy Markdown blocks for every generated Merge Request using a simple, clean, and punchy format:
+Render a ready-to-copy block per Merge Request:
 
 ```text
 [MR <ENV_TAG>] <MR_URL>
-Changes log 
+Changes log
 - <Poin 1: Apa yang diperbaiki / fitur apa yang aktif>
 - <Poin 2: Perubahan mekanisme/perilaku sistem secara gamblang>
 - <Poin 3: Proteksi regresi atau pengujian yang ditambahkan>
@@ -78,37 +74,29 @@ cc: <PIC>
 ```
 
 ### Formatting & Writing Rules (Prinsip `no-ai-slop`):
-- **DILARANG MENGGUNAKAN HEADING MARKDOWN (`#`, `##`, `###`, `####`)**: Gunakan teks polos agar font di Mattermost tidak membesar secara berlebihan.
-- **Format Sederhana Tanpa Metadata Bertele-tele**: Jangan menyertakan tabel metadata yang panjang (seperti Branch, Repo, Status Verifikasi). Cukup link MR dan list `Changes log`.
-- **Sertakan PIC di Akhir Pesan**: Ambil PIC dari file konfigurasi `mattermost-channel-mapping.json`. Jika belum ada, tanyakan kepada user dan simpan ke file mapping. Tambahkan `cc: <PIC>` di baris paling bawah.
-- **Gunakan Bahasa Manusia yang Lugas & Konkret**:
-  - ✅ **Awali dengan kata kerja aktif**: *"Memperbaiki..."*, *"Memigrasikan..."*, *"Menjaga..."*, *"Menambahkan..."*, *"Mengubah..."*.
-  - ❌ **Dilarang kata-kata AI Slop / Puffery**: `secara komprehensif`, `memastikan keakuratan`, `memfasilitasi`, `menyelaraskan alur`, `mengoptimalkan proses`, `solusi yang kokoh/robust`, `meningkatkan efisiensi`, `telah berhasil diimplementasikan`.
-  - ❌ **Dilarang raw code / AST leakage**: Jangan menyebut nama variabel internal atau query mentah (misal `user.type.hasNormalHours`, `attendanceConfirmationPagination Prisma query`). Jelaskan dampak fungsionalnya.
+
+- **No markdown headings** (`#`, `##`, `###`): plain text so Mattermost does not enlarge fonts.
+- **No long metadata tables** (branch, repo, verification). MR link + Changes log only.
+- **PIC on the last line**: from the mapping file. If missing, ask and save. `cc: <PIC>`.
+- **Concrete human language**:
+  - Start with an active verb: *"Memperbaiki..."*, *"Memigrasikan..."*, *"Menjaga..."*, *"Menambahkan..."*, *"Mengubah..."*.
+  - No puffery: `secara komprehensif`, `memastikan keakuratan`, `memfasilitasi`, `menyelaraskan alur`, `mengoptimalkan proses`, `solusi yang kokoh/robust`, `meningkatkan efisiensi`, `telah berhasil diimplementasikan`.
+  - No raw code / AST: do not name internal fields, queries, or ORM calls. Describe the user-visible change.
 
 ### Environment Tags:
-- `[MR DEV]`: Merge Request targeting `develop`.
-- `[MR STAGING]`: Merge Request targeting `staging`.
-- `[MR MAIN]` (or `[MR PROD]`): Merge Request targeting `main` / `master`.
 
-### Contoh Penerapan Nyata:
+- `[MR DEV]`: `develop`
+- `[MR STAGING]`: `staging`
+- `[MR MAIN]` (or `[MR PROD]`): `main` / `master`
+
+### Fictional sample (do not replace with a real ticket):
 
 ```text
-[MR DEV] https://gitlab.dot.co.id/playground/bikin-rindu-tools-v2/-/merge_requests/108
-Changes log 
-- Memperbaiki crash halaman dashboard di Safari setelah login akibat QuotaExceededError pada localStorage.
-- Memigrasikan penyimpanan cache browser ke IndexedDB (idb-keyval) sehingga kapasitas penyimpanan leluasa dan tidak memblokir main thread.
-- Menjaga synchronous script di head untuk preferensi tema agar tidak terjadi kedipan tampilan (FOUC).
-- Menambahkan auto-migration otomatis untuk memindahkan data lama dari localStorage ke IndexedDB sekaligus membebaskan kuota browser.
-
-cc: @hanaaaca
-
-[MR DEV] https://gitlab.dot.co.id/dot-system/dotify-new/-/merge_requests/963
-Changes log 
-- Mengubah status entitas yang tadinya APPROVED menjadi NEED APPROVAL otomatis saat project atau jam kerjanya diedit.
-- Memperbaiki sinkronisasi worker agar periode absensi berjalan (UNCONFIRMED) tetap diproses saat admin mengedit data.
-- Menjaga entitas lain yang sudah disetujui PM di periode yang sama agar status approval-nya tidak ter-reset.
-- Menambahkan unit test untuk skenario lembur multi-entry harian.
-
-cc: @ulfa.mufida
+[MR DEV] https://gitlab.example.com/example-org/work-portal/-/merge_requests/12
+Changes log
+- Memperbaiki status kartu di daftar request yang masih PENDING padahal semua baris sudah disetujui.
+- Menjaga request lain di periode yang sama agar approval-nya tidak ter-reset.
+- Menambahkan unit test untuk hari libur, jendela non-standar, dan koleksi baris yang kosong.
+
+cc: @owner
 ```

package/adapters/dot/multi-branch.md

@@ -53,7 +53,8 @@ git checkout -b <branch-name>-<target-env> origin/<target-env>
 git cherry-pick <commit-hash>
 
 # 4. Resolve any target-specific differences and verify tests pass
-npx jest --testPathIgnorePatterns="dotify-api"
+# commands from .ai-engineering-loop/verification.md
+npx jest
 npx tsc --noEmit
 
 # 5. Push the branch to remote
@@ -75,7 +76,7 @@ glab mr create \
 ## 3. Conflict & Environment Discrepancy Handling
 
 1. **Clean Cherry-Picks**:
-   Because the [Generic AI Engineering Loop](file:///Users/egagofur/Development/work/ai-engineering-loop/README.md) enforces surgical, minimal diffs, cherry-picking should be clean in >95% of cases.
+   Because the [generic AI Engineering Loop](../../README.md) enforces surgical, minimal diffs, cherry-picking should be clean in >95% of cases.
 2. **Merge Conflicts**:
    If a merge conflict occurs due to divergent code between `main` and `develop`:
    - Resolve the conflict surgically preserving the fix semantics.

package/adapters/dot/skills/dot-dev-workflow/SKILL.md

@@ -32,7 +32,7 @@ While AEL Maker runs, still enforce:
 
 - `backend-development` for naming, queries, layering.
 - `backend-safety-guardrails` on mutations, jobs, recalculation: never bypass BullMQ; scope by entity id not coarse date strings; never overwrite `APPROVED`/`REJECTED` without explicit force; BigInt as string across boundaries; container moves sync old and new parents.
-- Tests: `npx jest --testPathIgnorePatterns="dotify-api"` unless `.ai-engineering-loop/verification.md` says otherwise.
+- Tests: commands in `.ai-engineering-loop/verification.md` (fallback `npx jest && npx tsc --noEmit`).
 - Branch from a clean target (`main`, `staging`, or `develop`), then `git checkout -b <type>/<descriptive-name>`.
 
 Print these six invariants before commit (N/A allowed only with one sentence citing the diff):
@@ -97,7 +97,7 @@ glab api "projects/:fullpath/merge_requests/<mr-id>/discussions/<discussion_id>/
 
 Follow `adapters/dot/mattermost.md` when present.
 
-1. Resolve channel and PIC from `/Users/egagofur/.gemini/config/mattermost-channel-mapping.json`. If PIC is missing, ask the user and save it.
+1. Resolve channel and PIC from `~/.gemini/config/mattermost-channel-mapping.json`. If PIC is missing, ask the user and save it.
 2. Send via MCP `mattermost_send_message` with `from: "AI Agent"`. Use the Mattermost CLI only if MCP fails. Do not send twice.
 3. Put `cc: <PIC>` on the last line.
 

package/adapters/dot/skills/task-impact-inquiry/SKILL.md

@@ -0,0 +1,155 @@
+---
+name: task-impact-inquiry
+description: Map business blast radius before code. Use for impact, side effects, sibling data, approval, queues, or when a new developer must learn the current flow. Triggers: cek impactnya, blast radius, analisa pengaruh, brainstorming impact. Not a substitute for ai-engineering-loop.
+---
+
+# Task Impact Inquiry
+
+Map the **current business flow** and the **blast radius** of a change before any production edit.
+
+This skill fills AI Engineering Loop Stage 1 grill. It is not a parallel engineering OS.
+
+If Stage 1 grill already produced this matrix and the user confirmed it, stop. Do not interview again. On commit-bound work, continue in `ai-engineering-loop` (freeze the Goal Contract, then Maker). Do not start `dot-dev-workflow` Phases 1-6.
+
+## Hard gate
+
+Do not create a branch or edit production code until:
+
+1. The current lifecycle is drawn from evidence (not guessed).
+2. The impact matrix is on screen.
+3. The user has answered the probing questions (or waived them).
+
+Green unit tests later are not proof that siblings, approvals, or downstream jobs survived. A 100% passing suite can still reset approved history or fire the wrong downstream job.
+
+## When to use
+
+- "cek impactnya", "blast radius", "analisa pengaruh", "brainstorming impact"
+- Bug, edge case, or business-logic change
+- Shared service, status transition, calculation, validation, authorization, schema
+- The user is new to the domain and does not know the flow
+
+Impact-only (no implementation): run this skill and stop after the report.
+
+Commit-bound work: run this inside AEL Stage 1, then freeze. Do not run it a second time after grill.
+
+## Host notes
+
+Claude Code / Kiro: no mermaid, no LaTeX, no extra tool keys. ASCII diagrams only.
+
+Grok: do not spawn children for this skill. Stay in the parent.
+
+Look up facts (files, enums, jobs). Grill only **decisions**.
+
+## Steps
+
+### 1. Look up (do not ask)
+
+Read in this order. Skip a source if it is missing. Do not invent statuses.
+
+1. `.ai-engineering-loop/glossary.md`
+2. Existing FSD if present (`docs/fsd/`, `specs-book/fsd/`, especially `impact-matrix.md`). Read only. Do not generate an FSD.
+3. Status enums, services, validators, listeners, BullMQ / cron / queue processors
+4. Matching FE pages, routes, and permission guards when both FE and BE are in the workspace
+
+Cite the path for each claim. If FE or BE is missing, say so.
+
+### 2. New-dev briefing + lifecycle picture
+
+Explain the current flow in plain language for someone new to the app: who acts, what status changes, when a period locks.
+
+Then draw the lifecycle in ASCII. Do not ask the user what the code already shows.
+
+```text
+Author submit    -> DRAFT
+Author send      -> NEED_APPROVAL
+Reviewer approve -> APPROVED
+period lock      -> CONFIRMED --> billing / aggregate job
+```
+
+If the flow cannot be determined from the repo, say what is missing.
+
+### 3. Four-pillar scan
+
+**State and conditions.** Does the rule apply the same in normal vs special cases (rush vs standard, holiday, locked vs open period)? What happens in DRAFT, SUBMITTED, NEED_APPROVAL, APPROVED, REJECTED, CONFIRMED, UNCONFIRMED?
+
+**Sibling / historical isolation.** If entity A in parent P changes, do B and C in the same parent, period, or cart change? Can already-approved history reset?
+
+**Actor and approval.** Who creates, who may edit, who must re-approve? When is an existing approval void, and when must it be kept?
+
+**Downstream.** BullMQ, cron, listeners, billing, dashboard totals.
+
+### 4. Where it hits (hit map + blast picture)
+
+List the surfaces a naive edit would touch. Empty rows mean you have not finished looking.
+
+```text
+Surface          Path / job                         Naive risk
+FE page          <route or page>                    <what the user would see>
+BE service       <service / status write>           <what the row would become>
+Sibling rows     <same parent / period / cart>      isolate | also-update
+Approval         <who, void vs keep>                <approval lost or kept>
+Queue / billing  <job name>                         rerun | skip
+```
+
+Then the blast-radius picture (ASCII only):
+
+```text
+edit(A in period P)
+  |- sibling B in P     : isolate | also-update
+  |- approval on A      : void | keep
+  |- billing / queue    : rerun | skip
+```
+
+### 5. Impact matrix (failure table)
+
+| Scenario | Current logic (cite path) | Side effect if we ship naive | Proposed treatment |
+|---|---|---|---|
+| Happy path | | | |
+| Empty / omitted field | | | |
+| Boundary (min/max, locked vs open) | | | |
+| Sibling in the same parent | | | |
+| Error / denied / unauthorized | | | |
+
+A matrix with only the sunny path is not done.
+
+### 6. Probing questions
+
+Ask 2-3 decisions. Number them. Give a recommended answer. Wait.
+
+```text
+Q1 - <title>: <choices>
+Recommended: <your answer>
+```
+
+Typical decisions: void vs keep approval; isolate vs also-update siblings; rerun vs skip the downstream job.
+
+### 7. Contract rows
+
+Each accepted matrix row becomes a numbered AC in the Goal Contract **file** (failure table). Name the seam or artifact.
+
+If this session is AEL: freeze after those ACs are in the file. Chat `setuju` is not freeze.
+
+If this session is impact-only: print the report and stop. Do not implement.
+
+## Output
+
+```text
+Task impact inquiry
+Briefing: <plain-language current flow>
+Lifecycle: <ASCII>
+Hit map: <surfaces + paths>
+Blast radius: <ASCII>
+Matrix: <table>
+Questions: Q1..Qn with Recommended
+Proposed AC: AC-1..N (happy, empty/omit, boundary, sibling, error)
+Next: freeze Goal Contract | stop (impact-only)
+```
+
+## Forbidden
+
+- Implementing, branching, or "small fix while we discuss"
+- Second interview after AEL grill already captured the matrix
+- Mermaid or LaTeX
+- Claiming isolation because unit tests passed
+- Inventing business rules the repo and the user did not supply
+- Generating an FSD or starting `dot-dev-workflow` as a second loop

package/bin/ai-engineering-loop.js

@@ -21,7 +21,7 @@ const {
   formatHostSyncReport
 } = require('../lib/sync-hosts.js');
 
-const VERSION = '1.0.14';
+const VERSION = '1.0.15';
 const CWD = process.cwd();
 const CONTEXT_DIR = path.join(CWD, '.ai-engineering-loop');
 
@@ -275,7 +275,7 @@ function generateContextFiles(rootDir, discovery, trigger = 'init', impact = 'IN
 
   // 0. metadata.json (Baseline)
   const metadataJson = {
-    contextVersion: '1.0.14',
+    contextVersion: '1.0.15',
     generatedAt: new Date().toISOString(),
     repositoryRevision: currentRevision,
     projectProfile: discovery.profile,

package/core/grill-policy.md

@@ -45,22 +45,26 @@ Before Maker starts:
 
 If a decision was agreed in chat and is missing from the file, the contract is not frozen. Do not start Maker.
 
-## DOT adapter (`adapter_type: dot`)
+## Business blast radius
 
-On DOT repositories, grill is **one** session that includes the four-pillar blast radius from Antigravity skill `task-impact-inquiry` (`~/.gemini/config/skills/task-impact-inquiry/SKILL.md`). Do not run that skill as a second interview after grill.
+Green unit tests are not proof that sibling rows, approvals, or downstream jobs survived.
 
-The four pillars must appear in the grill (and then in the Goal Contract) whenever the change can touch:
+When the change can touch state, siblings, actors/approvals, or downstream work, grill **must** include blast radius — even if AC look obvious or the user said "just do it". Typo, lint, and version-bump skips still apply.
 
-1. State and condition permutations (status, overtime vs normal hours, locked vs open periods)
-2. Sibling / historical isolation (other entities in the same parent, period, or cart)
-3. Actor and approval authority (who edits, when an existing approval is void vs kept)
-4. Downstream jobs and queues (BullMQ, cron, payroll/aggregates)
+On `adapter_type: dot`, this is mandatory. On other adapters, skip only when the change cannot touch those four (copy, CSS, comment).
 
-**Do not skip grill** for those four cases, even if AC look obvious or the user said "just do it". Typo, lint, and version-bump skips still apply.
+Canonical skill: `adapters/dot/skills/task-impact-inquiry/SKILL.md`. Host copies via `sync-hosts`: `~/.claude/skills/task-impact-inquiry/`, `~/.grok/skills/task-impact-inquiry/`, `~/.gemini/config/skills/task-impact-inquiry/`. Load that skill if present. If it is missing, still run this section. Do not claim the skill ran.
 
-If the skill file is missing on this host, still ask the four pillars from this section. Do not claim the Gemini skill ran.
+If Stage 1 grill already produced the matrix and the user confirmed it, do not run a second interview.
 
-Present the impact matrix and 2–3 probing questions in the same grill round as other Stage 1 decisions. Recommended answers required. After the frontier is empty, freeze the Goal Contract once.
+In the same grill round:
+
+1. Look up the current flow. Draw an ASCII lifecycle (actor → status → lock). Do not ask look-up facts.
+2. Scan four pillars: state/conditions; sibling/historical isolation; actor and approval (void vs keep); downstream jobs and queues.
+3. ASCII blast-radius picture. No mermaid.
+4. Impact matrix (happy, empty/omit, boundary, sibling, error). Sunny-path-only is not done.
+5. 2–3 probing questions with recommended answers. Wait.
+6. Each accepted row becomes a numbered AC in the Goal Contract **file** (failure table).
 
 ## Design tree