@smartsoft001-mobilems/claude-plugins 2.82.0 → 2.84.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@smartsoft001-mobilems/claude-plugins",
-  "version": "2.82.0",
+  "version": "2.84.0",
   "publishConfig": {
     "access": "public"
   },

package/plugins/flow/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "flow",
   "description": "Development flow skills for Linear-driven development workflow",
-  "version": "2.82.0"
+  "version": "2.84.0"
 }

package/plugins/flow/skills/impl/SKILL.md

@@ -59,7 +59,7 @@ Execute each step in order. Do not skip any step marked as MANDATORY.
 - [ ] **5. MANDATORY: Agent orchestration plan** — delegate to `shared-impl-orchestrator`, save result as `orchestration.md` attachment via `mcp__linear__create_attachment` (replace any existing one). **Calling `mcp__linear__save_comment` with the orchestration body is FORBIDDEN.**
 - [ ] **6. Check external library blockers** — if blockers found, set status to Blocked and skip
 - [ ] **7. Capture "before" screenshots** — if `UI_CHANGE_REQUIRED: YES`, launch `screenshot-reporter` in background
-- [ ] **8. MANDATORY: Implement with 3x3 rule** — pause every 3 changes, use `shared-tdd-developer` for ALL code (RED → GREEN → REFACTOR)
+- [ ] **8. MANDATORY: Implement with 3x3 rule** — pause every 3 changes (skip pause in `--auto`, log checkpoint as Linear comment instead), use `shared-tdd-developer` for ALL code (RED → GREEN → REFACTOR)
 - [ ] **9. Verify implementation** — run tests, lint, build check
 - [ ] **9.5. E2E tests (conditional)** — if `E2E_TESTS_RECOMMENDED: YES`, delegate to `test-e2e` skill
 - [ ] **10. Capture "after" screenshots** — if `UI_CHANGE_REQUIRED: YES`, capture + post comparison to Linear + cleanup
@@ -68,13 +68,13 @@ Execute each step in order. Do not skip any step marked as MANDATORY.
 - [ ] **13. MANDATORY: Write reports in Polish** — all Linear comments must be in Polish language
 - [ ] **14. Update status** — delegate to `shared-linear-subtask-iterator` for status determination
 - [ ] **15. Agent evolution** — if user confirmed feedback, delegate to `shared-agent-evolver`
-- [ ] **16. Pause for user confirmation** — ALWAYS wait before proceeding to next subtask
+- [ ] **16. Pause for user confirmation** — wait before proceeding to next subtask (skipped in `--auto`; post completion comment and continue)
 
 ### Finalization
 
 - [ ] **17. Final summary** — present summary of all subtasks with statuses
 - [ ] **18. Session-wide evolution** — analyze all feedback across session
-- [ ] **19. ALWAYS pause** — wait for user confirmation at end
+- [ ] **19. ALWAYS pause** — wait for user confirmation at end (skipped in `--auto`; post final summary comment and exit)
 
 ### Task Progress Tracking
 
@@ -151,12 +151,31 @@ You implement code that is:
 ```
 /impl [linearTaskId]
 /impl [linearTaskId] --team    # Agent Team mode (experimental)
+/impl [linearTaskId] --auto    # Non-interactive mode for CI / GitHub Actions
 ```
 
 ## Parameters
 
 - `linearTaskId` - Linear task ID (e.g., ENG-123)
 - `--team` - Enable parallel Implementation Squad mode (experimental, requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`)
+- `--auto` - Non-interactive mode: skip ALL `AskUserQuestion` prompts, 3x3 checkpoint pauses, per-subtask pauses, and the final end pause. If `plan.md` attachment is missing, auto-invoke `/plan` flow to generate it instead of posting a "run /plan first" comment and skipping. Designed for CI / GitHub Actions runs where no human is at the keyboard.
+
+## Auto Mode (`--auto`)
+
+**When `--auto` is set, the skill MUST run end-to-end without any human-in-the-loop prompts.** Apply these overrides:
+
+| Default behavior                                         | `--auto` override                                                                                         |
+| -------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
+| Post comment "no plan.md found, run /plan first" + skip  | Inline-invoke `/plan` flow for the task to generate `plan.md` attachment + `AI Plan` label, then continue |
+| 3x3 rule pauses every 3 changes asking "Continue?"       | Log the checkpoint summary as a status comment, then continue automatically                               |
+| Pause after each subtask waiting for user confirmation   | Post subtask completion comment, then proceed to next subtask                                             |
+| Final end pause "wait for user confirmation"             | Post final summary comment and exit cleanly                                                               |
+| `AskUserQuestion` for any decision                       | Use the option marked **(Recommended)**; if none, fail fast with a Linear comment explaining why          |
+| Confirmation before destructive ops (delete attachments) | Proceed without confirmation — replace old `orchestration.md` automatically                               |
+
+**Hard requirement in `--auto`**: every checkpoint, decision, or skip MUST be logged as a Linear comment in Polish so the run remains auditable after the fact. Comments replace the interactive prompts — they are the audit trail.
+
+**Detection**: The flag `--auto` is provided as a positional/named arg. Treat any of `--auto`, `--ci`, `--non-interactive` as equivalent. Combinable with `--team` (parallel squad mode runs without per-subtask approval).
 
 ## Instructions
 
@@ -304,7 +323,12 @@ Parse the markdown for:
 - Testing Strategy
 - External Library Changes (if any — these are blockers, not to be implemented)
 
-**If no `plan.md` attachment found**: Create a comment noting that no plan was found, suggest running `/plan <taskId>` first, and skip this task. Set status back to "To Do". Do NOT fall back to reading plan content from comments — the attachment is the source of truth.
+**If no `plan.md` attachment found**:
+
+- **Default mode**: Create a comment noting that no plan was found, suggest running `/plan <taskId>` first, and skip this task. Set status back to "To Do".
+- **`--auto` mode**: Inline-invoke the `/plan` skill flow for this task to generate `plan.md` attachment + `AI Plan` label, then proceed with implementation. Post a comment in Polish noting the plan was auto-generated. Do NOT skip the task.
+
+Do NOT fall back to reading plan content from comments — the attachment is the source of truth.
 
 #### Step 3b-classify: MANDATORY UI Change Classification
 
@@ -717,7 +741,10 @@ The agent will provide:
 - Next subtask details (if any)
 - Pause point for user confirmation
 
-**IMPORTANT**: ALWAYS wait for user confirmation before proceeding to next subtask.
+**IMPORTANT**:
+
+- **Default mode**: ALWAYS wait for user confirmation before proceeding to next subtask.
+- **`--auto` mode**: Skip the wait. The completion comment from Step 3f is the audit trail; proceed directly to Step 3i.
 
 #### Step 3i: Move to Next Subtask
 
@@ -739,7 +766,10 @@ When all subtasks are processed, the agent will return `🏁 Iteration Complete`
 - Statistics (completed, partial, blocked)
 - Recommendations for follow-up
 
-**IMPORTANT**: ALWAYS pause and present the final summary to the user.
+**IMPORTANT**:
+
+- **Default mode**: ALWAYS pause and present the final summary to the user.
+- **`--auto` mode**: Post the final summary as a Linear comment in Polish on the parent task (or invoked task) and exit cleanly without pausing.
 
 ### Step 4a: Session-Wide Agent Evolution
 
@@ -788,18 +818,18 @@ To Do → In Progress → In Review (if completed)
 
 ## Pause Points (3x3 Rule)
 
-**ALWAYS stop and wait for user confirmation at these points:**
+**ALWAYS stop and wait for user confirmation at these points** (skipped in `--auto` — see overrides):
 
-| Pause Point          | When                                | What to Show                              |
-| -------------------- | ----------------------------------- | ----------------------------------------- |
-| **3x3 Checkpoint**   | After every 3 changes               | Summary of 3 changes + next 3 steps       |
-| **Subtask Complete** | After finishing each subtask        | Subtask summary + next subtask info       |
-| **Task Complete**    | After finishing all subtasks        | Final summary with all results            |
-| **Blocker Found**    | When external dependency found      | Blocker details + options                 |
-| **Error/Issue**      | When unexpected problem occurs      | Error details + proposed solution         |
-| **Agent Evolution**  | After subtask / after final summary | Evolution report with filed Linear issues |
+| Pause Point          | When                                | What to Show                              | `--auto` behavior                                             |
+| -------------------- | ----------------------------------- | ----------------------------------------- | ------------------------------------------------------------- |
+| **3x3 Checkpoint**   | After every 3 changes               | Summary of 3 changes + next 3 steps       | Post checkpoint as Linear comment, continue                   |
+| **Subtask Complete** | After finishing each subtask        | Subtask summary + next subtask info       | Post completion comment, continue to next subtask             |
+| **Task Complete**    | After finishing all subtasks        | Final summary with all results            | Post final summary comment, exit                              |
+| **Blocker Found**    | When external dependency found      | Blocker details + options                 | Set status to Blocked, post blocker comment, skip subtask     |
+| **Error/Issue**      | When unexpected problem occurs      | Error details + proposed solution         | Post error comment to Linear, fail the run with non-zero exit |
+| **Agent Evolution**  | After subtask / after final summary | Evolution report with filed Linear issues | Skip evolution prompt, file issues silently if any            |
 
-**Never proceed automatically** - always wait for explicit user confirmation before:
+**In default mode, never proceed automatically** - always wait for explicit user confirmation before:
 
 - Continuing after 3x3 checkpoint
 - Moving to next subtask

package/plugins/flow/skills/plan/SKILL.md

@@ -55,8 +55,8 @@ Execute each step in order. Do not skip any step marked as MANDATORY.
 - [ ] **8. Analyze external library deps** — check if `@smartsoft001` or `@smartsoft001-mobilems` changes are needed (mark as separate process)
 - [ ] **9. Create implementation plans** — generate structured plans per task/subtask with all required sections
 - [ ] **10. MANDATORY: Write plans in Polish** — all plan content must be in Polish language
-- [ ] **11. Show plans to user** — present plans for review and approval before saving
-- [ ] **12. MANDATORY: Confirm old plan deletion** — if replacing existing `plan.md`, ask user to confirm deletion of old attachment before proceeding
+- [ ] **11. MANDATORY: Get user approval of generated plan** — present the full plan content in the chat, then call `AskUserQuestion` with three options: save / regenerate / cancel. Save and label steps below MUST NOT run without approval. Skipped only in `--auto` (auto-approved; logged in audit comment).
+- [ ] **12. MANDATORY: Confirm old plan deletion** — if replacing existing `plan.md`, ask user to confirm deletion of old attachment before proceeding (skipped in `--auto`; delete old attachment automatically)
 - [ ] **13. MANDATORY: Save plan as native Linear attachment** — base64-encode `plan.md` content and upload via `mcp__linear__create_attachment`. **Calling `mcp__linear__save_comment` for the plan body is FORBIDDEN.** Linear hosts the file natively; no external storage.
 - [ ] **14. MANDATORY: Add "AI Plan" label** — ensure `AI Plan` label exists on the team and apply it to the invoked issue (the `linearTaskId` passed to `/plan` — parent task or subtask, whichever was called)
 - [ ] **15. Confirm to user** — list saved plans with summaries and Linear links
@@ -117,12 +117,30 @@ You create plans that are:
 ```
 /plan [linearTaskId]
 /plan [linearTaskId] --deep    # Deep planning with Agent Team (experimental)
+/plan [linearTaskId] --auto    # Non-interactive mode for CI / GitHub Actions
 ```
 
 ## Parameters
 
 - `linearTaskId` - Linear task ID (e.g., ENG-123)
 - `--deep` - Enable deep planning with Agent Team (experimental, requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`)
+- `--auto` - Non-interactive mode: skip ALL `AskUserQuestion` prompts. Auto-approve plans before saving (no review step), auto-delete stale `plan.md` attachments without confirmation, and silently skip when all plans are up to date (no "regenerate anyway?" prompt). Designed for CI / GitHub Actions runs where no human is at the keyboard.
+
+## Auto Mode (`--auto`)
+
+**When `--auto` is set, the skill MUST run end-to-end without any human-in-the-loop prompts.** Apply these overrides:
+
+| Default behavior                                                  | `--auto` override                                                                                |
+| ----------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ |
+| Final approval of generated plan content before saving            | Skip the approval gate; proceed directly to attachment save (auto-approve)                       |
+| Ask user to confirm deletion of old `plan.md` attachments         | Delete old attachments automatically before saving new ones                                      |
+| Ask "regenerate anyway?" when all plans are up-to-date            | Exit cleanly with a Linear comment noting all plans are current; no regeneration                 |
+| Secondary signal prompt (keyword-triggered confirmation to regen) | Ignore the secondary signal; only the mtime rule decides regeneration                            |
+| `AskUserQuestion` for any decision                                | Use the option marked **(Recommended)**; if none, fail fast with a Linear comment explaining why |
+
+**Hard requirement in `--auto`**: every decision (save, replace, skip) MUST be logged as a Linear comment in Polish so the run remains auditable after the fact. The mtime rule remains authoritative — `--auto` does not change _what_ gets regenerated, only that no human is asked.
+
+**Detection**: The flag `--auto` is provided as a positional/named arg. Treat any of `--auto`, `--ci`, `--non-interactive` as equivalent. Combinable with `--deep` (deep team mode runs without the final approval prompt).
 
 ## Instructions
 
@@ -195,7 +213,10 @@ Create a list of tasks/subtasks that need planning:
 - `tasksWithExistingPlan`: Array of task IDs with valid, up-to-date plans (skip these)
 - `oldPlanAttachments`: Map of task ID → `attachmentId` for plans that will be replaced (needed for deletion in Step 9)
 
-**Important**: If ALL tasks already have up-to-date plans, inform the user and ask if they want to regenerate anyway.
+**Important**: If ALL tasks already have up-to-date plans:
+
+- **Default mode**: Inform the user and ask if they want to regenerate anyway.
+- **`--auto` mode**: Exit cleanly with a Linear comment in Polish noting all plans are current; do NOT regenerate.
 
 ### Step 4: Analyze Previous Commits
 
@@ -654,11 +675,47 @@ When using `--deep` flag and the Planning Team has completed its analysis, appen
 - 2: Significant disagreements on approach
 - 1: Fundamental disagreements — plan needs revision
 
+### Step 8a: User Approval of Generated Plan
+
+**MANDATORY.** Before any Linear write (deletion of old `plan.md`, creation of new `plan.md`, label apply), the user MUST approve the generated plan content. This is the gate FRA-126 added.
+
+**`--auto` mode**: Skip this entire step. The plan is auto-approved. Record the auto-approval in the final Linear audit comment (e.g. `Plan zaakceptowany automatycznie (--auto)`). Proceed to Step 9.
+
+**Default mode** (interactive):
+
+1. **Render the full plan(s) in chat.** Print the markdown produced in Step 8 for every task/subtask that needs planning. The `AskUserQuestion` option labels alone do not give the user enough context — the full text must be visible above the prompt.
+
+2. **Ask for approval** via `AskUserQuestion`:
+
+   ```markdown
+   ## Akceptacja planu
+
+   Powyżej znajduje się wygenerowany plan dla zadania <linearTaskId> (oraz <N> podzadań, jeśli dotyczy).
+   Czy akceptujesz plan i mogę zapisać go jako załącznik `plan.md` w Linear?
+   ```
+
+   Options (use exactly these labels for consistency with Step 9):
+
+   - **"Tak, zapisz plan do Linear"** _(Recommended)_ — user accepts. Proceed to Step 9 (delete old attachment if replacing, then save). Existing flow continues unchanged from here.
+   - **"Wygeneruj plan ponownie"** — user wants a different plan. Go to step 3 (regeneration loop) below.
+   - **"Anuluj"** — user rejects. Stop the whole skill. Do NOT delete the existing `plan.md` attachment. Do NOT save a new one. Do NOT apply the `AI Plan` label. Print a short status in Polish (`Plan nie został zapisany. Anulowano na żądanie użytkownika.`) and exit.
+
+3. **Regeneration branch**: if the user chose "Wygeneruj plan ponownie":
+
+   - Ask a follow-up `AskUserQuestion` (or accept the free-text the user typed alongside the rejection) to capture what should change: scope, structure, missed files, wrong approach, etc.
+   - Loop back to **Step 7 (Create implementation plans)** with the user's feedback in mind. Do NOT re-run Steps 1–6 — the Linear task, comments, commits, and codebase analysis have not changed.
+   - On the regenerated plan, return to **Step 8a step 1** (render + ask again).
+   - **Cap the loop at 3 regenerations.** On the 3rd rejection, surface the situation to the user (`Plan został odrzucony 3 razy. Przerywam, abyś mógł doprecyzować wymagania.`) and exit without saving.
+
+4. **State invariants on entry to Step 9**: the only path that reaches Step 9 is the explicit "Tak, zapisz plan do Linear" choice (or `--auto`). Treat plan content as final.
+
 ### Step 9: Confirm and Delete Old Plan Attachments
 
 **This step applies only when replacing existing plans** (i.e., `oldPlanAttachments` from Step 3a is not empty).
 
-Before saving new plans, ask the user to confirm deletion of old `plan.md` attachments:
+**`--auto` mode**: Skip the confirmation prompt. For each task in `oldPlanAttachments`, delete the Linear attachment via `mcp__linear__delete_attachment({ id: attachmentId })` and proceed directly to Step 9a. Log the deletions in the final summary comment.
+
+**Default mode** (interactive): The plan content was already approved in Step 8a; this prompt is strictly about confirming deletion of the **existing** Linear attachment that will be overwritten. Ask the user:
 
 ```markdown
 ## Zastąpienie istniejących planów
@@ -938,4 +995,9 @@ _Plan generated by Claude Code_
 
 ---
 
-**Important**: Before saving the plans as attachments, show them to the user for review and approval. The plan content is written to `/tmp/claude-plans/<taskId>-plan.md`, base64-encoded, and uploaded as a native Linear attachment via `mcp__linear__create_attachment`. After that, the `AI Plan` label is applied to the invoked issue.
+**Important**:
+
+- **Default mode**: Before saving the plans as attachments, show them to the user for review and approval.
+- **`--auto` mode**: Skip the review step; proceed directly to saving the attachments.
+
+The plan content is written to `/tmp/claude-plans/<taskId>-plan.md`, base64-encoded, and uploaded as a native Linear attachment via `mcp__linear__create_attachment`. After that, the `AI Plan` label is applied to the invoked issue.

package/plugins/flow-external/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "flow-external",
   "description": "Development flow skills for standalone Angular 6-11 museum projects without framework (Angular CLI, Karma/Jasmine, Bootstrap 4)",
-  "version": "2.82.0"
+  "version": "2.84.0"
 }

package/plugins/flow-external/skills/impl/SKILL.md

@@ -33,11 +33,28 @@ Implement changes based on approved plans from Linear `plan.md` attachments.
 
 ```
 /impl <linearTaskId>
+/impl <linearTaskId> --auto    # Non-interactive mode for CI / GitHub Actions
 ```
 
 ## Parameters
 
 - `linearTaskId` - Linear task ID (e.g., MOB-123)
+- `--auto` - Non-interactive mode: skip ALL `AskUserQuestion` prompts and any per-step pauses. If `plan.md` attachment is missing, auto-invoke `/plan` flow to generate it instead of stopping. Designed for CI / GitHub Actions runs where no human is at the keyboard.
+
+## Auto Mode (`--auto`)
+
+When `--auto` is set, the skill MUST run end-to-end without any human-in-the-loop prompts:
+
+| Default behavior                                                  | `--auto` override                                                                                         |
+| ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
+| Stop with "no plan.md found, run /plan first" suggestion          | Inline-invoke `/plan` flow for the task to generate `plan.md` attachment + `AI Plan` label, then continue |
+| Pause after each step / subtask waiting for user confirmation     | Post completion comment, then proceed automatically                                                       |
+| Confirmation before destructive ops (delete `orchestration.md`)   | Proceed without confirmation — replace old attachment automatically                                       |
+| Any `AskUserQuestion`                                             | Use the **(Recommended)** option; if none, fail fast with a Linear comment                                |
+
+Every checkpoint, decision, or skip MUST be logged as a Linear comment in Polish (audit trail).
+
+**Detection**: The flag `--auto` is provided as a positional/named arg. Treat any of `--auto`, `--ci`, `--non-interactive` as equivalent.
 
 ## 🚨 Hard Rules — read before doing anything
 
@@ -72,7 +89,11 @@ This is for standalone Angular CLI projects. Key rules:
 2. Find the attachment where `title == "plan.md"` (or `filename == "plan.md"`) and capture its `id`. Do NOT use the `url` field for fetching.
 3. `mcp__linear__get_attachment({ id: <attachmentId> })` — returns the markdown content directly (Linear hosts the file natively).
 4. Parse the plan content.
-5. If no `plan.md` attachment exists, inform the user and suggest running `/plan <taskId>` first. Do NOT fall back to parsing plan content from comments, and do NOT attempt `curl`/`WebFetch` on a URL.
+5. If no `plan.md` attachment exists:
+   - **Default mode**: inform the user and suggest running `/plan <taskId>` first. Stop the skill.
+   - **`--auto` mode**: inline-invoke the `/plan` skill flow for this task to generate `plan.md` attachment + `AI Plan` label, then proceed with implementation. Post a Linear comment in Polish noting the plan was auto-generated.
+
+   Do NOT fall back to parsing plan content from comments, and do NOT attempt `curl`/`WebFetch` on a URL.
 
 ### Step 2: Detect Project Structure
 

package/plugins/flow-external/skills/plan/SKILL.md

@@ -27,11 +27,28 @@ Create a structured implementation plan for a Linear task and save it as a `plan
 
 ```
 /plan <linearTaskId>
+/plan <linearTaskId> --auto    # Non-interactive mode for CI / GitHub Actions
 ```
 
 ## Parameters
 
 - `linearTaskId` - Linear task ID (e.g., MOB-123)
+- `--auto` - Non-interactive mode: skip ALL `AskUserQuestion` prompts. Auto-approve plan before saving, auto-delete stale `plan.md` attachment without confirmation, and silently skip when the existing plan is up to date. Designed for CI / GitHub Actions runs where no human is at the keyboard.
+
+## Auto Mode (`--auto`)
+
+When `--auto` is set, the skill MUST run end-to-end without any human-in-the-loop prompts:
+
+| Default behavior                                              | `--auto` override                                                                    |
+| ------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
+| Ask user to confirm deletion of old `plan.md` attachment      | Delete old attachment automatically before saving the new one                        |
+| Ask "regenerate?" when plan is up-to-date but keywords detect | Ignore the secondary signal; only the mtime rule decides regeneration                |
+| Final approval of generated plan content before saving        | Skip the approval gate (Step 4a); proceed directly to attachment save (auto-approve) |
+| Any `AskUserQuestion`                                         | Use the **(Recommended)** option; if none, fail fast with a Linear comment           |
+
+Every decision MUST be logged as a Linear comment in Polish (audit trail). The mtime rule remains authoritative.
+
+**Detection**: The flag `--auto` is provided as a positional/named arg. Treat any of `--auto`, `--ci`, `--non-interactive` as equivalent.
 
 ## 🚨 Hard Rules — read before doing anything
 
@@ -156,6 +173,40 @@ Structure the plan as follows:
 | -   | [Subtask 2] | Medium    | 2    |
 ```
 
+### Step 4a: User Approval of Generated Plan
+
+**MANDATORY.** Before any Linear write (subtask creation, attachment delete, attachment create, label apply), the user MUST approve the generated plan content. This is the gate FRA-126 added.
+
+**`--auto` mode**: Skip this entire step. The plan is auto-approved. Record the auto-approval in the final Linear audit comment (e.g. `Plan zaakceptowany automatycznie (--auto)`). Proceed to Step 5.
+
+**Default mode** (interactive):
+
+1. **Render the full plan in chat.** Print the markdown produced in Step 4. The `AskUserQuestion` option labels alone do not give the user enough context — the full text must be visible above the prompt.
+
+2. **Ask for approval** via `AskUserQuestion`:
+
+   ```markdown
+   ## Akceptacja planu
+
+   Powyżej znajduje się wygenerowany plan dla zadania <linearTaskId>.
+   Czy akceptujesz plan i mogę zapisać go jako załącznik `plan.md` w Linear?
+   ```
+
+   Options:
+
+   - **"Tak, zapisz plan do Linear"** _(Recommended)_ — user accepts. Proceed to Step 5 (create subtasks if needed) and Step 6 (save attachment).
+   - **"Wygeneruj plan ponownie"** — user wants a different plan. Go to step 3 (regeneration loop) below.
+   - **"Anuluj"** — user rejects. Stop the whole skill. Do NOT create subtasks. Do NOT delete the existing `plan.md` attachment. Do NOT save a new one. Do NOT apply the `AI Plan` label. Print a short status in Polish (`Plan nie został zapisany. Anulowano na żądanie użytkownika.`) and exit.
+
+3. **Regeneration branch**: if the user chose "Wygeneruj plan ponownie":
+
+   - Ask a follow-up `AskUserQuestion` (or accept the free-text the user typed alongside the rejection) to capture what should change: scope, structure, missed files, wrong approach, etc.
+   - Loop back to **Step 4 (Create Implementation Plan)** with the user's feedback in mind. Do NOT re-run Steps 1–3 — the Linear task, comments, and codebase analysis have not changed.
+   - On the regenerated plan, return to **Step 4a step 1** (render + ask again).
+   - **Cap the loop at 3 regenerations.** On the 3rd rejection, surface the situation to the user (`Plan został odrzucony 3 razy. Przerywam, abyś mógł doprecyzować wymagania.`) and exit without saving.
+
+4. **State invariant on entry to Step 5**: the only path that reaches Step 5 is the explicit "Tak, zapisz plan do Linear" choice (or `--auto`). Treat plan content as final.
+
 ### Step 5: Create Subtasks (if needed)
 
 For complex tasks, create subtasks in Linear:
@@ -171,12 +222,16 @@ Upload the plan directly to Linear via `mcp__linear__create_attachment` — Line
 
 #### 6.1 — If replacing an existing plan, confirm with user
 
-If a `plan.md` attachment is being replaced, ask the user via `AskUserQuestion`:
+If a `plan.md` attachment is being replaced:
 
-- "Tak, usuń stary plan i zapisz nowy" (Recommended)
-- "Anuluj"
+- **Default mode**: ask the user via `AskUserQuestion`:
 
-If confirmed, delete the Linear attachment via `mcp__linear__delete_attachment({ id: oldAttachmentId })`.
+  - "Tak, usuń stary plan i zapisz nowy" (Recommended)
+  - "Anuluj"
+
+  If confirmed, delete the Linear attachment via `mcp__linear__delete_attachment({ id: oldAttachmentId })`.
+
+- **`--auto` mode**: skip the prompt; delete the old Linear attachment via `mcp__linear__delete_attachment({ id: oldAttachmentId })` automatically and proceed.
 
 #### 6.2 — Write `plan.md` locally
 
@@ -217,15 +272,21 @@ Delete `/tmp/claude-plans/<taskId>-plan.md` after the attachment is created. `/p
 
 ### Step 8: Confirm to User
 
+The plan has been approved in Step 4a (or auto-approved in `--auto`). Step 8 is purely informational — **do NOT ask another question here**, just print the status.
+
+**Default mode**:
+
 ```markdown
 ## Plan zapisany
 
 Plan implementacji został dodany jako załącznik `plan.md` do zadania [linearTaskId].
 Etykieta `AI Plan` została dodana.
 
-Czy plan jest zaakceptowany? Po akceptacji uruchom `/impl [linearTaskId]` aby rozpocząć implementację.
+Uruchom `/impl [linearTaskId]` aby rozpocząć implementację.
 ```
 
+**`--auto` mode**: post a Linear comment confirming the plan was saved (no question asked) and exit. The comment is the audit trail for the CI run.
+
 ## Guidelines
 
 1. **Always analyze existing code first** before planning

package/plugins/flow-legacy/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "flow-legacy",
   "description": "Development flow skills for legacy Angular 14 projects with Linear-driven workflow",
-  "version": "2.82.0"
+  "version": "2.84.0"
 }

package/plugins/flow-legacy/skills/impl/SKILL.md

@@ -56,7 +56,7 @@ Execute each step in order. Do not skip any step marked as MANDATORY.
 - [ ] **5. MANDATORY: Agent orchestration plan** — delegate to `shared-impl-orchestrator` with `Angular Version: 14 (LEGACY)`, save result as `orchestration.md` attachment via `mcp__linear__create_attachment` (replace any existing one). **Calling `mcp__linear__save_comment` with the orchestration body is FORBIDDEN.**
 - [ ] **6. Check external library blockers** — if blockers found, set status to Blocked and skip
 - [ ] **7. Capture "before" screenshots** — if `UI_CHANGE_REQUIRED: YES`, launch `screenshot-reporter` in background
-- [ ] **8. MANDATORY: Implement with 3x3 rule** — pause every 3 changes, use `shared-tdd-developer` for ALL code (RED → GREEN → REFACTOR)
+- [ ] **8. MANDATORY: Implement with 3x3 rule** — pause every 3 changes (skip pause in `--auto`, log checkpoint as Linear comment instead), use `shared-tdd-developer` for ALL code (RED → GREEN → REFACTOR)
 - [ ] **9. MANDATORY: Use Angular 14 patterns** — `*ngIf`/`*ngFor`, constructor DI, `@Input()`/`@Output()`, BehaviorSubject — NEVER signals, `@if`/`@for`, `inject()`
 - [ ] **10. Verify implementation** — run tests, lint, build check
 - [ ] **11. Capture "after" screenshots** — if `UI_CHANGE_REQUIRED: YES`, capture + post comparison to Linear + cleanup
@@ -65,12 +65,12 @@ Execute each step in order. Do not skip any step marked as MANDATORY.
 - [ ] **14. MANDATORY: Write reports in Polish** — all Linear comments must be in Polish language
 - [ ] **15. Update status** — delegate to `shared-linear-subtask-iterator` for status determination
 - [ ] **16. Agent evolution** — if user confirmed feedback, delegate to `shared-agent-evolver`
-- [ ] **17. Pause for user confirmation** — ALWAYS wait before proceeding to next subtask
+- [ ] **17. Pause for user confirmation** — wait before proceeding to next subtask (skipped in `--auto`; post completion comment and continue)
 
 ### Finalization
 
 - [ ] **18. Final summary** — present summary of all subtasks with statuses
-- [ ] **19. ALWAYS pause** — wait for user confirmation at end
+- [ ] **19. ALWAYS pause** — wait for user confirmation at end (skipped in `--auto`; post final summary comment and exit)
 
 ### Task Progress Tracking
 
@@ -218,11 +218,30 @@ export class DataService {
 
 ```
 /impl [linearTaskId]
+/impl [linearTaskId] --auto    # Non-interactive mode for CI / GitHub Actions
 ```
 
 ## Parameters
 
 - `linearTaskId` - Linear task ID (e.g., ENG-123)
+- `--auto` - Non-interactive mode: skip ALL `AskUserQuestion` prompts, 3x3 checkpoint pauses, per-subtask pauses, and the final end pause. If `plan.md` attachment is missing, auto-invoke `/plan` flow to generate it instead of posting a "run /plan first" comment and skipping. Designed for CI / GitHub Actions runs where no human is at the keyboard.
+
+## Auto Mode (`--auto`)
+
+**When `--auto` is set, the skill MUST run end-to-end without any human-in-the-loop prompts.** Apply these overrides:
+
+| Default behavior                                         | `--auto` override                                                                                         |
+| -------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
+| Post comment "no plan.md found, run /plan first" + skip  | Inline-invoke `/plan` flow for the task to generate `plan.md` attachment + `AI Plan` label, then continue |
+| 3x3 rule pauses every 3 changes asking "Continue?"       | Log the checkpoint summary as a status comment, then continue automatically                               |
+| Pause after each subtask waiting for user confirmation   | Post subtask completion comment, then proceed to next subtask                                             |
+| Final end pause "wait for user confirmation"             | Post final summary comment and exit cleanly                                                               |
+| `AskUserQuestion` for any decision                       | Use the option marked **(Recommended)**; if none, fail fast with a Linear comment explaining why          |
+| Confirmation before destructive ops (delete attachments) | Proceed without confirmation — replace old `orchestration.md` automatically                               |
+
+**Hard requirement in `--auto`**: every checkpoint, decision, or skip MUST be logged as a Linear comment in Polish so the run remains auditable after the fact. Comments replace the interactive prompts — they are the audit trail.
+
+**Detection**: The flag `--auto` is provided as a positional/named arg. Treat any of `--auto`, `--ci`, `--non-interactive` as equivalent.
 
 ## Instructions
 
@@ -272,7 +291,12 @@ Parse the markdown for:
 - Testing Strategy
 - External Library Changes (blockers — not to be implemented)
 
-**If no `plan.md` attachment found**: Create a comment noting that no plan was found, suggest running `/plan <taskId>` first, and skip this task. Set status back to "To Do". Do NOT fall back to parsing plan content from comments — the attachment is the source of truth.
+**If no `plan.md` attachment found**:
+
+- **Default mode**: Create a comment noting that no plan was found, suggest running `/plan <taskId>` first, and skip this task. Set status back to "To Do".
+- **`--auto` mode**: Inline-invoke the `/plan` skill flow for this task to generate `plan.md` attachment + `AI Plan` label, then proceed with implementation. Post a comment in Polish noting the plan was auto-generated. Do NOT skip the task.
+
+Do NOT fall back to parsing plan content from comments — the attachment is the source of truth.
 
 #### Step 3b-classify: MANDATORY UI Change Classification
 
@@ -607,7 +631,10 @@ The agent will provide:
 - Next subtask details (if any)
 - Pause point for user confirmation
 
-**IMPORTANT**: ALWAYS wait for user confirmation before proceeding to next subtask.
+**IMPORTANT**:
+
+- **Default mode**: ALWAYS wait for user confirmation before proceeding to next subtask.
+- **`--auto` mode**: Skip the wait. The completion comment from Step 3f is the audit trail; proceed directly to Step 3i.
 
 #### Step 3i: Move to Next Subtask
 
@@ -629,7 +656,10 @@ When all subtasks are processed, the agent will return `🏁 Iteration Complete`
 - Statistics (completed, partial, blocked)
 - Recommendations for follow-up
 
-**IMPORTANT**: ALWAYS pause and present the final summary to the user.
+**IMPORTANT**:
+
+- **Default mode**: ALWAYS pause and present the final summary to the user.
+- **`--auto` mode**: Post the final summary as a Linear comment in Polish on the parent task (or invoked task) and exit cleanly without pausing.
 
 ## Status Flow
 
@@ -641,18 +671,18 @@ To Do → In Progress → In Review (if completed)
 
 ## Pause Points (3x3 Rule)
 
-**ALWAYS stop and wait for user confirmation at these points:**
+**ALWAYS stop and wait for user confirmation at these points** (skipped in `--auto` — see overrides):
 
-| Pause Point          | When                                | What to Show                              |
-| -------------------- | ----------------------------------- | ----------------------------------------- |
-| **3x3 Checkpoint**   | After every 3 changes               | Summary of 3 changes + next 3 steps       |
-| **Subtask Complete** | After finishing each subtask        | Subtask summary + next subtask info       |
-| **Task Complete**    | After finishing all subtasks        | Final summary with all results            |
-| **Blocker Found**    | When external dependency found      | Blocker details + options                 |
-| **Error/Issue**      | When unexpected problem occurs      | Error details + proposed solution         |
-| **Agent Evolution**  | After subtask / after final summary | Evolution report with filed Linear issues |
+| Pause Point          | When                                | What to Show                              | `--auto` behavior                                             |
+| -------------------- | ----------------------------------- | ----------------------------------------- | ------------------------------------------------------------- |
+| **3x3 Checkpoint**   | After every 3 changes               | Summary of 3 changes + next 3 steps       | Post checkpoint as Linear comment, continue                   |
+| **Subtask Complete** | After finishing each subtask        | Subtask summary + next subtask info       | Post completion comment, continue to next subtask             |
+| **Task Complete**    | After finishing all subtasks        | Final summary with all results            | Post final summary comment, exit                              |
+| **Blocker Found**    | When external dependency found      | Blocker details + options                 | Set status to Blocked, post blocker comment, skip subtask     |
+| **Error/Issue**      | When unexpected problem occurs      | Error details + proposed solution         | Post error comment to Linear, fail the run with non-zero exit |
+| **Agent Evolution**  | After subtask / after final summary | Evolution report with filed Linear issues | Skip evolution prompt, file issues silently if any            |
 
-**Never proceed automatically** - always wait for explicit user confirmation before:
+**In default mode, never proceed automatically** - always wait for explicit user confirmation before:
 
 - Continuing after 3x3 checkpoint
 - Moving to next subtask

package/plugins/flow-legacy/skills/plan/SKILL.md

@@ -52,8 +52,8 @@ Execute each step in order. Do not skip any step marked as MANDATORY.
 - [ ] **9. Analyze external library deps** — check if `@smartsoft001` or `@smartsoft001-mobilems` changes are needed (mark as separate process)
 - [ ] **10. Create implementation plans** — generate structured plans per task/subtask with all required sections, using Angular 14 patterns
 - [ ] **11. MANDATORY: Write plans in Polish** — all plan content must be in Polish language
-- [ ] **12. Show plans to user** — present plans for review and approval before saving
-- [ ] **13. MANDATORY: Confirm old plan deletion** — if replacing existing `plan.md`, ask user to confirm deletion of old attachment before proceeding
+- [ ] **12. MANDATORY: Get user approval of generated plan** — present the full plan content in the chat, then call `AskUserQuestion` with three options: save / regenerate / cancel. Save and label steps below MUST NOT run without approval. Skipped only in `--auto` (auto-approved; logged in audit comment).
+- [ ] **13. MANDATORY: Confirm old plan deletion** — if replacing existing `plan.md`, ask user to confirm deletion of old attachment before proceeding (skipped in `--auto`; delete old attachment automatically)
 - [ ] **14. MANDATORY: Save plan as native Linear attachment** — base64-encode `plan.md` content and upload via `mcp__linear__create_attachment`. **Calling `mcp__linear__save_comment` for the plan body is FORBIDDEN.** Linear hosts the file natively; no external storage.
 - [ ] **15. MANDATORY: Add "AI Plan" label** — ensure `AI Plan` label exists on the team and apply it to the invoked issue (the `linearTaskId` passed to `/plan` — parent task or subtask, whichever was called)
 - [ ] **16. Confirm to user** — list saved plans with summaries and Linear links
@@ -115,11 +115,29 @@ You create plans that are:
 
 ```
 /plan [linearTaskId]
+/plan [linearTaskId] --auto    # Non-interactive mode for CI / GitHub Actions
 ```
 
 ## Parameters
 
 - `linearTaskId` - Linear task ID (e.g., ENG-123)
+- `--auto` - Non-interactive mode: skip ALL `AskUserQuestion` prompts. Auto-approve plans before saving (no review step), auto-delete stale `plan.md` attachments without confirmation, and silently skip when all plans are up to date (no "regenerate anyway?" prompt). Designed for CI / GitHub Actions runs where no human is at the keyboard.
+
+## Auto Mode (`--auto`)
+
+**When `--auto` is set, the skill MUST run end-to-end without any human-in-the-loop prompts.** Apply these overrides:
+
+| Default behavior                                                  | `--auto` override                                                                                |
+| ----------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ |
+| Final approval of generated plan content before saving            | Skip the approval gate; proceed directly to attachment save (auto-approve)                       |
+| Ask user to confirm deletion of old `plan.md` attachments         | Delete old attachments automatically before saving new ones                                      |
+| Ask "regenerate anyway?" when all plans are up-to-date            | Exit cleanly with a Linear comment noting all plans are current; no regeneration                 |
+| Secondary signal prompt (keyword-triggered confirmation to regen) | Ignore the secondary signal; only the mtime rule decides regeneration                            |
+| `AskUserQuestion` for any decision                                | Use the option marked **(Recommended)**; if none, fail fast with a Linear comment explaining why |
+
+**Hard requirement in `--auto`**: every decision (save, replace, skip) MUST be logged as a Linear comment in Polish so the run remains auditable after the fact. The mtime rule remains authoritative — `--auto` does not change _what_ gets regenerated, only that no human is asked.
+
+**Detection**: The flag `--auto` is provided as a positional/named arg. Treat any of `--auto`, `--ci`, `--non-interactive` as equivalent.
 
 ## Angular 14 Legacy Patterns
 
@@ -206,7 +224,10 @@ If `planAttachment` exists and no comment is newer than it, but the user's lates
 - `tasksWithExistingPlan`: Array of task IDs with up-to-date plans
 - `oldPlanAttachments`: Map of task ID → `attachmentId` for plans being replaced
 
-**Important**: If ALL tasks already have up-to-date plans, inform the user and ask if they want to regenerate anyway.
+**Important**: If ALL tasks already have up-to-date plans:
+
+- **Default mode**: Inform the user and ask if they want to regenerate anyway.
+- **`--auto` mode**: Exit cleanly with a Linear comment in Polish noting all plans are current; do NOT regenerate.
 
 ### Step 4: Analyze Previous Commits
 
@@ -525,11 +546,47 @@ _Plan generated by Claude Code (flow-legacy)_
 _Plan generated by Claude Code (flow-legacy)_
 ```
 
+### Step 8a: User Approval of Generated Plan
+
+**MANDATORY.** Before any Linear write (deletion of old `plan.md`, creation of new `plan.md`, label apply), the user MUST approve the generated plan content. This is the gate FRA-126 added.
+
+**`--auto` mode**: Skip this entire step. The plan is auto-approved. Record the auto-approval in the final Linear audit comment (e.g. `Plan zaakceptowany automatycznie (--auto)`). Proceed to Step 9.
+
+**Default mode** (interactive):
+
+1. **Render the full plan(s) in chat.** Print the markdown produced in Step 8 for every task/subtask that needs planning. The `AskUserQuestion` option labels alone do not give the user enough context — the full text must be visible above the prompt.
+
+2. **Ask for approval** via `AskUserQuestion`:
+
+   ```markdown
+   ## Akceptacja planu
+
+   Powyżej znajduje się wygenerowany plan dla zadania <linearTaskId> (oraz <N> podzadań, jeśli dotyczy).
+   Czy akceptujesz plan i mogę zapisać go jako załącznik `plan.md` w Linear?
+   ```
+
+   Options (use exactly these labels for consistency with Step 9):
+
+   - **"Tak, zapisz plan do Linear"** _(Recommended)_ — user accepts. Proceed to Step 9 (delete old attachment if replacing, then save). Existing flow continues unchanged from here.
+   - **"Wygeneruj plan ponownie"** — user wants a different plan. Go to step 3 (regeneration loop) below.
+   - **"Anuluj"** — user rejects. Stop the whole skill. Do NOT delete the existing `plan.md` attachment. Do NOT save a new one. Do NOT apply the `AI Plan` label. Print a short status in Polish (`Plan nie został zapisany. Anulowano na żądanie użytkownika.`) and exit.
+
+3. **Regeneration branch**: if the user chose "Wygeneruj plan ponownie":
+
+   - Ask a follow-up `AskUserQuestion` (or accept the free-text the user typed alongside the rejection) to capture what should change: scope, structure, missed files, wrong approach, etc.
+   - Loop back to **Step 7 (Create Implementation Plans)** with the user's feedback in mind. Do NOT re-run Steps 1–6 — the Linear task, comments, commits, and codebase analysis have not changed.
+   - On the regenerated plan, return to **Step 8a step 1** (render + ask again).
+   - **Cap the loop at 3 regenerations.** On the 3rd rejection, surface the situation to the user (`Plan został odrzucony 3 razy. Przerywam, abyś mógł doprecyzować wymagania.`) and exit without saving.
+
+4. **State invariants on entry to Step 9**: the only path that reaches Step 9 is the explicit "Tak, zapisz plan do Linear" choice (or `--auto`). Treat plan content as final.
+
 ### Step 9: Confirm and Delete Old Plan Attachments
 
 **This step applies only when replacing existing plans** (`oldPlanAttachments` from Step 3a is not empty).
 
-Before saving new plans, ask the user to confirm deletion of old `plan.md` attachments:
+**`--auto` mode**: Skip the confirmation prompt. For each task in `oldPlanAttachments`, delete the Linear attachment via `mcp__linear__delete_attachment({ id: attachmentId })` and proceed directly to Step 9a. Log the deletions in the final summary comment.
+
+**Default mode** (interactive): The plan content was already approved in Step 8a; this prompt is strictly about confirming deletion of the **existing** Linear attachment that will be overwritten. Ask the user:
 
 ```markdown
 ## Zastąpienie istniejących planów
@@ -643,4 +700,9 @@ After saving:
 
 ---
 
-**Important**: Before saving the plans as attachments, show them to the user for review and approval. The plan content is written to `/tmp/claude-plans/<taskId>-plan.md`, base64-encoded, and uploaded as a native Linear attachment via `mcp__linear__create_attachment`. After that, the `AI Plan` label is applied to the invoked issue.
+**Important**:
+
+- **Default mode**: Before saving the plans as attachments, show them to the user for review and approval.
+- **`--auto` mode**: Skip the review step; proceed directly to saving the attachments.
+
+The plan content is written to `/tmp/claude-plans/<taskId>-plan.md`, base64-encoded, and uploaded as a native Linear attachment via `mcp__linear__create_attachment`. After that, the `AI Plan` label is applied to the invoked issue.