apt-mcp-agent-setup 3.2.5 → 3.2.6

package/src/templates/AGENTS.md

@@ -1,13 +1,13 @@
-# APT workspace contract
-
-At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
-
-For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
-
-Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
-
-Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
-
-Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
-
-Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.
+# APT workspace contract
+
+At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
+
+For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
+
+Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
+
+Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
+
+Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
+
+Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.

package/src/templates/CLAUDE.md

@@ -1,13 +1,13 @@
-# APT workspace contract
-
-At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
-
-For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
-
-Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
-
-Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
-
-Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
-
-Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.
+# APT workspace contract
+
+At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
+
+For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
+
+Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
+
+Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
+
+Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
+
+Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.

package/src/templates/GEMINI.md

@@ -1,13 +1,13 @@
-# APT workspace contract
-
-At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
-
-For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
-
-Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
-
-Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
-
-Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
-
-Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.
+# APT workspace contract
+
+At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
+
+For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
+
+Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
+
+Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
+
+Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
+
+Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.

package/src/templates/apt-runtime.md

@@ -1,16 +1,16 @@
-# APT session and execution contract
-
-1. Call `session_bootstrap` at session start and after context recovery. Read project conventions from `.agents/memory/MEMORY.md`; retrieve only relevant dynamic knowledge. Report unavailable backends once and use available fallbacks.
-2. Call `route_request` for a new request or changed intent, including target package/stack and explicit skills. Load the selected specialist and companion skills with `skill_load`. Do not read the complete trigger catalog into the model context.
-3. Read-only questions, reviews and running existing tests do not require a code-change pipeline. Before executable changes, inspect `pipeline_status` and bind `pipeline_start` or `pipeline_use` with canonical task/run identity and an explicit workspace.
-4. Small changes use scope, fix/check and review. Features use clarification only where needed, a plan with acceptance criteria, implementation, verification, review and acceptance. Bug fixes start with diagnosis and regression coverage. Do not require three questions, a PRD or external issues when the task is already clear.
-5. Use `pipeline_next` to reserve work before dispatch. Delegate useful independent research and reviews to native host subagents, with at most four active actors including the coordinator. Only one writer per workspace. Workers must not start/reset/rebind the parent pipeline.
-6. Pin a quality plan for new executable runs: stable criteria, expected outcomes, concrete check IDs, target platforms and required review roles. Use `pipeline_verify` with a supported test report and named assertions, then `pipeline_checkpoint` with the current evidence IDs. Exit code, build, screenshot or a free-form summary cannot prove functional acceptance. Missing required checks keep the run unaccepted.
-7. Record separate technical and Product/UX review verdicts when the work affects a user flow. Review staged, unstaged and relevant untracked changes. Keep finding IDs open across reviews until a current fix or reasoned dismissal is confirmed by a reviewer. High-risk work needs a host-observed independent technical reviewer; actor names and self-reported models do not prove independence. Rerun checks after affected changes. Review-only requests produce findings, not unsolicited edits or MR comments.
-8. Stop after ten repair/check attempts per work item or three repeated outcomes without progress. Preserve budgets and blocked/paused states across resume. User interruption always wins over continuation hooks.
-9. Native tool enforcement and automatic continuation depend on observed host capability. If unavailable, use sequential execution and state that limitation. Never claim independent review without an independent reviewer.
-10. Keep prose short and clear, reuse existing code, and load only current-step references. Strong caveman style is opt-in. Publishing, merging and external communication require authorization for those actions.
-
-`pipeline_reset(task, runId, confirm=true)` cancels a run while preserving history. Legacy runs retain their legacy definitions. Content-only documentation does not require PRD, issue or TDD steps; AGENTS.md, SKILL.md, trigger maps and runtime configuration are operational contracts.
-
-Read `docs/agents/mcp-tools.md` for interfaces. Run `npx apt-mcp-agent-setup doctor` to inspect configuration. A registered MCP server or installed hook is not proof of successful activation. Health must show successful initialization and functional probes, not only a running process.
+# APT session and execution contract
+
+1. Call `session_bootstrap` at session start and after context recovery. Read project conventions from `.agents/memory/MEMORY.md`; retrieve only relevant dynamic knowledge. Report unavailable backends once and use available fallbacks.
+2. Call `route_request` for a new request or changed intent, including target package/stack and explicit skills. Load the selected specialist and companion skills with `skill_load`. Do not read the complete trigger catalog into the model context.
+3. Read-only questions, reviews and running existing tests do not require a code-change pipeline. Before executable changes, inspect `pipeline_status` and bind `pipeline_start` or `pipeline_use` with canonical task/run identity and an explicit workspace.
+4. Small changes use scope, fix/check and review. Features use clarification only where needed, a plan with acceptance criteria, implementation, verification, review and acceptance. Bug fixes start with diagnosis and regression coverage. Do not require three questions, a PRD or external issues when the task is already clear.
+5. Use `pipeline_next` to reserve work before dispatch. Delegate useful independent research and reviews to native host subagents, with at most four active actors including the coordinator. Only one writer per workspace. Workers must not start/reset/rebind the parent pipeline.
+6. Pin a quality plan for new executable runs: stable criteria, expected outcomes, concrete check IDs, target platforms and required review roles. Use `pipeline_verify` with a supported test report and named assertions, then `pipeline_checkpoint` with the current evidence IDs. Exit code, build, screenshot or a free-form summary cannot prove functional acceptance. Missing required checks keep the run unaccepted.
+7. Record separate technical and Product/UX review verdicts when the work affects a user flow. Review staged, unstaged and relevant untracked changes. Keep finding IDs open across reviews until a current fix or reasoned dismissal is confirmed by a reviewer. High-risk work needs a host-observed independent technical reviewer; actor names and self-reported models do not prove independence. Rerun checks after affected changes. Review-only requests produce findings, not unsolicited edits or MR comments.
+8. Stop after ten repair/check attempts per work item or three repeated outcomes without progress. Preserve budgets and blocked/paused states across resume. User interruption always wins over continuation hooks.
+9. Native tool enforcement and automatic continuation depend on observed host capability. If unavailable, use sequential execution and state that limitation. Never claim independent review without an independent reviewer.
+10. Keep prose short and clear, reuse existing code, and load only current-step references. Strong caveman style is opt-in. Publishing, merging and external communication require authorization for those actions.
+
+`pipeline_reset(task, runId, confirm=true)` cancels a run while preserving history. Legacy runs retain their legacy definitions. Content-only documentation does not require PRD, issue or TDD steps; AGENTS.md, SKILL.md, trigger maps and runtime configuration are operational contracts.
+
+Read `docs/agents/mcp-tools.md` for interfaces. Run `npx apt-mcp-agent-setup doctor` to inspect configuration. A registered MCP server or installed hook is not proof of successful activation. Health must show successful initialization and functional probes, not only a running process.

package/src/templates/copilot-instructions.md

@@ -1,13 +1,13 @@
-# APT workspace contract
-
-At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
-
-For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
-
-Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
-
-Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
-
-Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
-
-Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.
+# APT workspace contract
+
+At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
+
+For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
+
+Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
+
+Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
+
+Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
+
+Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.

package/src/templates/cursorrules.mdc

@@ -1,18 +1,18 @@
----
-description: APT session bootstrap and workspace contract
-alwaysApply: true
----
-
-# APT workspace contract
-
-At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
-
-For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
-
-Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
-
-Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
-
-Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
-
-Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.
+---
+description: APT session bootstrap and workspace contract
+alwaysApply: true
+---
+
+# APT workspace contract
+
+At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
+
+For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
+
+Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
+
+Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
+
+Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
+
+Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.

package/src/templates/design-config.md

@@ -1,52 +1,52 @@
-# Design Tools Configuration
-
-How the design-to-code skills connect to external design tools.
-
-## Figma
-
-| Setting | Value |
-|---|---|
-| **MCP Server** | `GLips/Figma-Context-MCP` |
-| **Auth** | `FIGMA_ACCESS_TOKEN` environment variable |
-| **Mode** | Read-only layout, style, and asset extraction |
-
-Paste a Figma file or frame URL in chat. The agent reads the design and routes the result to the design-to-code flow.
-
-## Stitch
-
-| Setting | Value |
-|---|---|
-| **MCP Server** | `@_davideast/stitch-mcp@0.9.0` |
-| **Transport** | `proxy` over stdio |
-| **Activation** | Automatic for the `stitch` and `system` presets |
-| **Mode** | Agent creates, user edits in Stitch, agent pulls code |
-
-The package update command verifies Stitch authentication and opens setup when an interactive terminal is available. For a fresh install or recovery, authenticate once, then restart the MCP client:
-
-```bash
-npx --yes @_davideast/stitch-mcp@0.9.0 init
-```
-
-Check authentication and API access with:
-
-```bash
-npx --yes @_davideast/stitch-mcp@0.9.0 doctor --verbose
-```
-
-`STITCH_API_KEY` can replace browser authentication. `STITCH_ENABLED=true` remains an optional compatibility override. Set `STITCH_ENABLED=false` to disable the backend even when the preset includes Stitch.
-
-### Public tools
-
-- `design-stitch-create-project`
-- `design-stitch-list-projects`
-- `design-stitch-get-project`
-- `design-stitch-list`
-- `design-stitch-get-screen`
-- `design-stitch-generate`
-- `design-stitch-edit`
-- `design-stitch-get-code`
-- `design-stitch-get-image`
-
-There is no separate Design DNA tool. The agent derives design tokens from screen metadata and downloaded code.
-
-The Stitch MCP package is an independent experimental project. It is not maintained or endorsed by Google.
+# Design Tools Configuration
+
+How the design-to-code skills connect to external design tools.
+
+## Figma
+
+| Setting | Value |
+|---|---|
+| **MCP Server** | `GLips/Figma-Context-MCP` |
+| **Auth** | `FIGMA_ACCESS_TOKEN` environment variable |
+| **Mode** | Read-only layout, style, and asset extraction |
+
+Paste a Figma file or frame URL in chat. The agent reads the design and routes the result to the design-to-code flow.
+
+## Stitch
+
+| Setting | Value |
+|---|---|
+| **MCP Server** | `@_davideast/stitch-mcp@0.9.0` |
+| **Transport** | `proxy` over stdio |
+| **Activation** | Automatic for the `stitch` and `system` presets |
+| **Mode** | Agent creates, user edits in Stitch, agent pulls code |
+
+The package update command verifies Stitch authentication and opens setup when an interactive terminal is available. For a fresh install or recovery, authenticate once, then restart the MCP client:
+
+```bash
+npx --yes @_davideast/stitch-mcp@0.9.0 init
+```
+
+Check authentication and API access with:
+
+```bash
+npx --yes @_davideast/stitch-mcp@0.9.0 doctor --verbose
+```
+
+`STITCH_API_KEY` can replace browser authentication. `STITCH_ENABLED=true` remains an optional compatibility override. Set `STITCH_ENABLED=false` to disable the backend even when the preset includes Stitch.
+
+### Public tools
+
+- `design-stitch-create-project`
+- `design-stitch-list-projects`
+- `design-stitch-get-project`
+- `design-stitch-list`
+- `design-stitch-get-screen`
+- `design-stitch-generate`
+- `design-stitch-edit`
+- `design-stitch-get-code`
+- `design-stitch-get-image`
+
+There is no separate Design DNA tool. The agent derives design tokens from screen metadata and downloaded code.
+
+The Stitch MCP package is an independent experimental project. It is not maintained or endorsed by Google.

package/src/templates/gdrive-config.md

@@ -1,57 +1,57 @@
-# Google Drive Configuration
-
-QC, BA, and PM presets can connect to Google Drive to enable online document generation and live collaboration.
-
-## Setup Steps
-
-### 1. Create a Google Cloud Project
-- Go to the [Google Cloud Console](https://console.cloud.google.com).
-- Create a new project (e.g. "Bank Project MCP Client").
-- Under "APIs & Services" > "Library", search for and enable:
-  - **Google Drive API**
-  - **Google Sheets API**
-  - **Google Docs API**
-
-### 2. Configure OAuth Consent Screen
-- Go to "OAuth consent screen".
-- Choose "External" (or "Internal" if using Workspace).
-- Add your test user email addresses.
-- Add scopes:
-  - `../auth/drive`
-  - `../auth/spreadsheets`
-  - `../auth/documents`
-
-### 3. Create Desktop Credentials
-- Go to "Credentials" > "+ Create Credentials" > "OAuth client ID".
-- Select **Desktop app** as the application type.
-- Click "Create" and download the JSON credentials file.
-- Save the file to your machine (e.g. `C:\Users\admin\google-oauth.json`).
-
-### 4. Authenticate Locally
-Run the authorization CLI to link your account:
-```bash
-npx @piotr-agier/google-drive-mcp auth
-```
-This will open your browser and prompt you to log in to your Google Account. Once authenticated, a token file `tokens.json` will be saved to your local config directory (e.g. `~/.config/google-drive-mcp/tokens.json`).
-
-### 5. Add Environment Variables
-Add the following to your active `.env` file in the project workspace:
-```bash
-GOOGLE_DRIVE_OAUTH_PATH="C:/Users/admin/google-oauth.json"
-GOOGLE_DRIVE_TOKEN_PATH="C:/Users/admin/.config/google-drive-mcp/tokens.json"
-GOOGLE_DRIVE_FOLDER_ID="1A2B3C4D5E6F7G8H9I0J" # Optional default folder ID
-```
-
----
-
-## Tool Reference
-
-The following tools will be made available when the `google-drive` preset addon is enabled:
-
-| Tool | Action | Description |
-|---|---|---|
-| `gdrive-search` | Search files | Search files across your Google Drive |
-| `gdrive-list-folder` | List contents | List files and subfolders in a folder |
-| `gdrive-upload-file` | Upload file | Upload local `.xlsx` or `.docx` and auto-convert to Sheets/Docs |
-| `gdrive-update-sheet-cell` | Update cell | Modify a specific cell in a Google Sheet |
-| `gdrive-share-file` | Share file | Share a document with a user email address |
+# Google Drive Configuration
+
+QC, BA, and PM presets can connect to Google Drive to enable online document generation and live collaboration.
+
+## Setup Steps
+
+### 1. Create a Google Cloud Project
+- Go to the [Google Cloud Console](https://console.cloud.google.com).
+- Create a new project (e.g. "Bank Project MCP Client").
+- Under "APIs & Services" > "Library", search for and enable:
+  - **Google Drive API**
+  - **Google Sheets API**
+  - **Google Docs API**
+
+### 2. Configure OAuth Consent Screen
+- Go to "OAuth consent screen".
+- Choose "External" (or "Internal" if using Workspace).
+- Add your test user email addresses.
+- Add scopes:
+  - `../auth/drive`
+  - `../auth/spreadsheets`
+  - `../auth/documents`
+
+### 3. Create Desktop Credentials
+- Go to "Credentials" > "+ Create Credentials" > "OAuth client ID".
+- Select **Desktop app** as the application type.
+- Click "Create" and download the JSON credentials file.
+- Save the file to your machine (e.g. `C:\Users\admin\google-oauth.json`).
+
+### 4. Authenticate Locally
+Run the authorization CLI to link your account:
+```bash
+npx @piotr-agier/google-drive-mcp auth
+```
+This will open your browser and prompt you to log in to your Google Account. Once authenticated, a token file `tokens.json` will be saved to your local config directory (e.g. `~/.config/google-drive-mcp/tokens.json`).
+
+### 5. Add Environment Variables
+Add the following to your active `.env` file in the project workspace:
+```bash
+GOOGLE_DRIVE_OAUTH_PATH="C:/Users/admin/google-oauth.json"
+GOOGLE_DRIVE_TOKEN_PATH="C:/Users/admin/.config/google-drive-mcp/tokens.json"
+GOOGLE_DRIVE_FOLDER_ID="1A2B3C4D5E6F7G8H9I0J" # Optional default folder ID
+```
+
+---
+
+## Tool Reference
+
+The following tools will be made available when the `google-drive` preset addon is enabled:
+
+| Tool | Action | Description |
+|---|---|---|
+| `gdrive-search` | Search files | Search files across your Google Drive |
+| `gdrive-list-folder` | List contents | List files and subfolders in a folder |
+| `gdrive-upload-file` | Upload file | Upload local `.xlsx` or `.docx` and auto-convert to Sheets/Docs |
+| `gdrive-update-sheet-cell` | Update cell | Modify a specific cell in a Google Sheet |
+| `gdrive-share-file` | Share file | Share a document with a user email address |

package/src/templates/mcp-tools.md

@@ -1,23 +1,23 @@
 # MCP Tools — Decision Tree & Conventions
 
-## Runtime and pipelines
-
-For Figma and Stitch tool names and authentication, read `docs/agents/design-config.md` when working on design tasks.
-
-- Bootstrap: `session_bootstrap(sessionId, contextEpoch, host, capabilities)` identifies this context and reports resumable work. Pass native model capability and account scope only when the host supplies them.
-- Route: `route_request(sessionId, requestId, prompt, target, stack, explicitSkills)` returns the workflow, specialist, review roles, platform verification requirements and phase-specific skills. Load current-step skills with `skill_load` and agent/workflow content with `context_load` for each new worker or context epoch.
-- Models: `model_list(sessionId, offset, limit, query)` reports inventory source, account scope, coverage and eligibility. CLI metadata is reference only. Use the model decision from `pipeline_next`; compare requested and host-observed model receipts after dispatch.
-- Start: `pipeline_start(pipeline, task, workspace, acceptanceCriteria, scope, qualityPlan, productImpact, sessionId)` creates a versioned run. New executable runs require at least one acceptance criterion string that exactly matches `qualityPlan.criteria[].expectedOutcome`. The plan uses `criteria: [{id, expectedOutcome, source, checkIds}]`, `checks: [{id, criterionIds, format, testIds, required}]`, and `reviews: [{id, required}]`. A recent user-facing web or mobile route requires its platform check and Product review. Use `pipeline_use(task, runId)` to resume the same run.
-- Execute: `pipeline_next(task, runId, sessionId, role, requestId)` reserves an attempt. Include its APT attempt markers in the native worker brief. Native host agents perform the work; the coordinator controls transitions and continues through ready parts of an approved feature without asking for approval after each internal step. Resource and quota waits remain resumable.
-- Verify: `pipeline_verify` records authorized argv execution under the run workspace. For functional acceptance, pass `checkId`, supported `reportFormat` and named test IDs in the pinned plan. Zero, skipped or unreadable tests and unrelated successful commands remain unverified. `pipeline_checkpoint` records the latest review verdict per stage and persistent finding IDs through `action=review`; resolution needs current evidence and later reviewer confirmation. A direct start without a bound route needs Technical `impactAssessment` before acceptance. User-flow impact requires Product review and platform checks. Missing required platform checks leave the run unaccepted.
-- Inspect: `pipeline_status` reports current criterion/check status, open findings and reviewer provenance without binding sessions. `pipeline_reset` cancels without deleting history. `pipeline_prepare_merge` only prepares a report.
+## Runtime and pipelines
+
+For Figma and Stitch tool names and authentication, read `docs/agents/design-config.md` when working on design tasks.
+
+- Bootstrap: `session_bootstrap(sessionId, contextEpoch, host, capabilities)` identifies this context and reports resumable work. Pass native model capability and account scope only when the host supplies them.
+- Route: `route_request(sessionId, requestId, prompt, target, stack, explicitSkills)` returns the workflow, specialist, review roles, platform verification requirements and phase-specific skills. Load current-step skills with `skill_load` and agent/workflow content with `context_load` for each new worker or context epoch.
+- Models: `model_list(sessionId, offset, limit, query)` reports inventory source, account scope, coverage and eligibility. CLI metadata is reference only. Use the model decision from `pipeline_next`; compare requested and host-observed model receipts after dispatch.
+- Start: `pipeline_start(pipeline, task, workspace, acceptanceCriteria, scope, qualityPlan, productImpact, sessionId)` creates a versioned run. Bootstrap the session in the intended workspace first. `workspace` is a schema-valid object, such as `{mode:"current",confirmed:true}`; a string or an unbound global server cannot create a run. On Antigravity, use the workspace MCP alias. New executable runs require at least one acceptance criterion string that exactly matches `qualityPlan.criteria[].expectedOutcome`. The plan uses `criteria: [{id, expectedOutcome, source, checkIds}]`, `checks: [{id, criterionIds, format, testIds, required}]`, and `reviews: [{id, required}]`. A recent user-facing web or mobile route requires its platform check and Product review. Use `pipeline_use(task, runId)` to resume the same run.
+- Execute: `pipeline_next(task, runId, sessionId, role, requestId)` reserves an attempt. Include its APT attempt markers in the native worker brief. Native host agents perform the work; the coordinator controls transitions and continues through ready parts of an approved feature without asking for approval after each internal step. Resource and quota waits remain resumable.
+- Verify: `pipeline_verify` records authorized argv execution under the run workspace. For functional acceptance, pass `checkId`, supported `reportFormat` and named test IDs in the pinned plan. Zero, skipped or unreadable tests and unrelated successful commands remain unverified. `pipeline_checkpoint` records the latest review verdict per stage and persistent finding IDs through `action=review`; resolution needs current evidence and later reviewer confirmation. A direct start without a bound route needs Technical `impactAssessment` before acceptance. User-flow impact requires Product review and platform checks. Missing required platform checks leave the run unaccepted.
+- Inspect: `pipeline_status` reports current criterion/check status, open findings, reviewer provenance and pending creation intents without binding sessions. `pipeline_reset(task, runId, sessionId, confirm:true, target:"creation")` abandons a matching unfinished intent while preserving its file. The default `target:"run"` cancels a run without deleting history. `pipeline_prepare_merge` only prepares a report.
 - Read-only questions, review and existing test execution do not require a mutation pipeline. Scope-limited changes use the short pipeline; increased risk adds required checks.
 - MCP gates cover proxied calls. Native tool gates and continuation require observed host hooks. Plan Mode and user interruption take precedence.
 - Codegraph failures permit file-search fallback. The proxy refreshes the review graph before impact analysis; it must report failure rather than use stale results.
-- `mcp_agent_health` reports process, initialization and functional readiness separately. `npx apt-mcp-agent-setup doctor` performs read-only configuration inspection.
-- Browser work uses the lazy `browser-local` backend when the preset has it. Pass `aptTask` and `aptWorker` on browser calls. Use snapshot and console evidence. A page load or screenshot alone is not a feature check. After an uncertain browser action, inspect state before retrying and never replay a side-effecting call automatically.
-- `presentation_prepare` returns pinned PPT Master commands for the document-artifact pipeline. It does not execute commands or overwrite a source deck. Preserve unselected slides and report `visual-unverified` when no renderer and visual review are available.
-- `aso_import` reads workspace-relative CSV/XLSX exports. Preserve nulls and source metadata. It is export intake, not a live Sensor Tower connection; do not call unregistered market-data tool names.
+- `mcp_agent_health` reports process, initialization and functional readiness separately. `npx apt-mcp-agent-setup doctor` performs read-only configuration inspection.
+- Browser work uses the lazy `browser-local` backend when the preset has it. Pass `aptTask` and `aptWorker` on browser calls. Use snapshot and console evidence. A page load or screenshot alone is not a feature check. After an uncertain browser action, inspect state before retrying and never replay a side-effecting call automatically.
+- `presentation_prepare` returns pinned PPT Master commands for the document-artifact pipeline. It does not execute commands or overwrite a source deck. Preserve unselected slides and report `visual-unverified` when no renderer and visual review are available.
+- `aso_import` reads workspace-relative CSV/XLSX exports. Preserve nulls and source metadata. It is export intake, not a live Sensor Tower connection; do not call unregistered market-data tool names.
 
 
 ## 🔍 Tool Selection — When to Use What
@@ -59,9 +59,9 @@ For Figma and Stitch tool names and authentication, read `docs/agents/design-con
 
 ---
 
-## Memory
-
-Save durable decisions and reusable bug fixes when they will help future sessions. Do not write a memory record after every internal pipeline step or load the whole graph by default. A memory backend outage does not block unrelated core tools.
+## Memory
+
+Save durable decisions and reusable bug fixes when they will help future sessions. Do not write a memory record after every internal pipeline step or load the whole graph by default. A memory backend outage does not block unrelated core tools.
 
 ### Google Drive & Online Documents
 

package/src/templates/windsurfrules.md

@@ -1,13 +1,13 @@
-# APT workspace contract
-
-At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
-
-For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
-
-Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
-
-Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
-
-Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
-
-Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.
+# APT workspace contract
+
+At session start and after context recovery, call `session_bootstrap` for this workspace and read `docs/agents/apt-runtime.md` once per context. Read project conventions in `.agents/memory/MEMORY.md`; retrieve only relevant dynamic memory. Report unavailable backends once and use available fallbacks.
+
+For new or changed intent, call `route_request` with the target, stack and explicit skills. Use `skill_load` for selected skills and current-step references. Do not load the full trigger catalog or repeat rules on every tool call.
+
+Before code changes, bind `pipeline_status` and `pipeline_start` or `pipeline_use` to an explicit task, runId and workspace. Reserve with `pipeline_next`; verify and checkpoint current code before completion. Read-only questions, review and existing tests need no code-change pipeline. Clarify only unresolved decisions.
+
+Use at most four actors including the coordinator and one writer per workspace. Respect host permissions, Plan Mode and user stops. Never claim independent review or native enforcement without observed capability. Keep attempts and evidence across resume; do not reset exhausted budgets.
+
+Preserve custom files. Write concise code and prose, run suitable checks, and review staged, unstaged and relevant new files. Publishing, merging and external messages require authorization. Strong caveman style is opt-in.
+
+Tool interfaces: `docs/agents/mcp-tools.md`. Project/domain and issue conventions: `docs/agents/domain.md` and `docs/agents/issue-tracker.md`. Support: info.alphatechs.ai@gmail.com.