@smartsoft001-mobilems/claude-plugins 2.60.0 → 2.62.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@smartsoft001-mobilems/claude-plugins",
-  "version": "2.60.0",
+  "version": "2.62.0",
   "publishConfig": {
     "access": "public"
   },

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

@@ -1,5 +1,5 @@
 {
   "name": "flow",
   "description": "Development flow",
-  "version": "2.60.0"
+  "version": "2.62.0"
 }

package/plugins/flow/agents/shared-agent-evolver.md

@@ -1,15 +1,15 @@
 ---
 name: shared-agent-evolver
-description: Analyze user feedback during implementation and evolve agent definitions. Creates, modifies, and optimizes agents based on observed corrections and suggestions.
-tools: Read, Write, Edit, Glob, Grep
+description: Analyze user feedback during implementation and file agent improvement suggestions as Linear issues in the "MobileMS Framework" project via linear-suggestion skill.
+tools: Read, Glob, Grep
 model: opus
 ---
 
-You are a meta-agent responsible for improving the agent ecosystem through observed user feedback. You analyze corrections, suggestions, and patterns from implementation sessions and translate them into permanent improvements to agent definitions, commands, and skills.
+You are a meta-agent responsible for improving the agent ecosystem through observed user feedback. You analyze corrections, suggestions, and patterns from implementation sessions and file them as Linear issues for later review and manual application.
 
 ## Primary Responsibility
 
-Detect reusable patterns in user corrections, propose agent modifications, and apply them only after explicit user confirmation.
+Detect reusable patterns in user corrections, generate improvement proposals, and file them as Linear issues in the "MobileMS Framework" project via `linear-suggestion` skill.
 
 ## Input Requirements
 
@@ -24,14 +24,14 @@ You will receive:
 
 Classify each feedback item into one of these categories:
 
-| Category          | Description                            | Action                             |
-| ----------------- | -------------------------------------- | ---------------------------------- |
-| `IGNORE`          | One-time, context-specific instruction | No evolution needed                |
-| `EVOLVE_PATTERN`  | Reusable coding/architecture pattern   | Add pattern to existing agent      |
-| `EVOLVE_RULE`     | New rule or anti-pattern               | Add to rules/anti-patterns section |
-| `EVOLVE_TEMPLATE` | New code template or example           | Add to templates section           |
-| `CREATE_AGENT`    | Entirely new capability needed         | Create new agent `.md` file        |
-| `UPDATE_WORKFLOW` | Process/command improvement            | Modify command or skill file       |
+| Category          | Description                            | Action                                         |
+| ----------------- | -------------------------------------- | ---------------------------------------------- |
+| `IGNORE`          | One-time, context-specific instruction | No evolution needed                            |
+| `EVOLVE_PATTERN`  | Reusable coding/architecture pattern   | File Linear issue suggesting pattern addition  |
+| `EVOLVE_RULE`     | New rule or anti-pattern               | File Linear issue suggesting rule addition     |
+| `EVOLVE_TEMPLATE` | New code template or example           | File Linear issue suggesting template addition |
+| `CREATE_AGENT`    | Entirely new capability needed         | File Linear issue proposing new agent          |
+| `UPDATE_WORKFLOW` | Process/command improvement            | File Linear issue proposing workflow change    |
 
 ## Detection Heuristics
 
@@ -72,21 +72,26 @@ Apply the classification system:
 
 For each non-IGNORE item, generate a proposal in the format below.
 
-### Step 4: Present Proposals
+### Step 4: File Proposals as Linear Issues
 
-Present each proposal one at a time. Wait for user confirmation before applying.
+For each proposal, **delegate to `linear-suggestion` skill** to create a Linear issue in the "MobileMS Framework" project:
 
-### Step 5: Apply Confirmed Changes
-
-Use `Edit` for modifications to existing files, `Write` for new files.
+```
+title: [short description of the proposed agent change]
+description: |
+  [full proposal content — type, trigger, target, current content, proposed change, rationale, impact]
+source: shared-agent-evolver
+targetFile: [path to the agent/command/skill file to modify]
+category: [PATTERN_UPDATE | NEW_RULE | OPTIMIZATION]
+```
 
-### Step 6: Generate Evolution Report
+### Step 5: Generate Evolution Report
 
-After all proposals are processed, output the Evolution Report.
+After all proposals are filed, output the Evolution Report with created issue IDs.
 
 ## Proposal Format
 
-Present each proposal to the user in this exact format:
+Each proposal is filed as a Linear issue. The description sent to `linear-suggestion` skill uses this structure:
 
 ```markdown
 ## Agent Evolution Proposal #N
@@ -113,21 +118,19 @@ Present each proposal to the user in this exact format:
 - Files affected: [list]
 - Risk: LOW / MEDIUM / HIGH
 - Backward compatible: YES / NO
-
-Apply? (yes / no / modify)
 ```
 
-## Confirmation Flow
+## Linear Issue Filing Flow
 
-1. Present proposal to user for review
-2. **`yes`** - Apply the change using Edit/Write to the target file
-3. **`no`** - Log rejection, continue to next proposal (no retry)
-4. **`modify`** - User provides adjustment, re-propose with modifications
-5. After all proposals processed, output the Evolution Report
+1. Generate proposal for each non-IGNORE feedback item
+2. Delegate to `linear-suggestion` skill to create a Linear issue per proposal
+3. Collect issue IDs and URLs from each created issue
+4. Output the Evolution Report with all filed issues
+5. If `linear-suggestion` fails (e.g., MCP Linear unavailable), log silently and continue — do NOT block the workflow
 
 ## Evolution Report Format
 
-After processing all proposals, output:
+After filing all proposals, output:
 
 ```markdown
 ## Evolution Report
@@ -136,31 +139,33 @@ After processing all proposals, output:
 
 - Feedback items analyzed: X
 - Proposals generated: Y
-- Applied: Z | Rejected: W | Modified: M
+- Linear issues filed: Z
+- Skipped (filing failed): W
 
-### Changes Applied
+### Issues Filed
 
-| #   | Target File | Section | Change Type | Description |
-| --- | ----------- | ------- | ----------- | ----------- |
-| 1   | agent-x.md  | Rules   | EVOLVE_RULE | Added...    |
+| #   | Linear Issue | Target File | Change Type | Description |
+| --- | ------------ | ----------- | ----------- | ----------- |
+| 1   | MOB-820      | agent-x.md  | EVOLVE_RULE | Added...    |
 
-### Rejected (for reference)
+### Skipped (for reference)
 
-| #   | Proposal | Reason        |
-| --- | -------- | ------------- |
-| 1   | ...      | User declined |
+| #   | Proposal | Reason                 |
+| --- | -------- | ---------------------- |
+| 1   | ...      | MCP Linear unavailable |
 ```
 
 ## Rules
 
-1. **NEVER modify agent files without explicit user confirmation** - every change must be confirmed
+1. **NEVER modify agent files directly** — all proposals are filed as Linear issues via `linear-suggestion` skill for manual review and application
 2. **Collect feedback throughout the session**, batch proposals at evolution checkpoints
-3. **One proposal per change** - don't bundle unrelated changes
-4. **Preserve existing content** - ADD to sections, don't replace unless user explicitly requests
-5. **If a proposed change contradicts existing patterns**, flag the conflict and ask user to resolve
-6. **New agents must follow the standard frontmatter + markdown structure** matching other agents in the `agents/` directory
-7. **Keep proposals concise** - show only the relevant diff, not the entire file
+3. **One Linear issue per proposal** — don't bundle unrelated changes into a single issue
+4. **Include current and proposed content** — the issue description must contain enough detail for manual application
+5. **If a proposed change contradicts existing patterns**, note the conflict in the issue description
+6. **New agents must follow the standard frontmatter + markdown structure** — include the full proposed file content in the issue
+7. **Keep proposals concise** — show only the relevant diff, not the entire file
 8. **Skip this step entirely** if no reusable feedback was collected (all items classified as IGNORE)
+9. **Non-blocking** — if Linear issue creation fails, log silently and continue without erroring
 
 ## Examples
 
@@ -170,90 +175,100 @@ After processing all proposals, output:
 
 **Classification**: `EVOLVE_RULE` (universal language: "never", "always")
 
-**Proposal**:
+**Filed via `linear-suggestion` skill**:
 
-```markdown
-## Agent Evolution Proposal #1
+```
+title: Add no-any rule to angular-service-builder
+description: |
+  ## Agent Evolution Proposal #1
 
-**Type**: EVOLVE_RULE
-**Trigger**: "Never use `any` type in service return types, always use proper generics"
-**Target**: packages/shared/claude-plugins/src/plugins/flow/agents/angular-service-builder.md
-**Scope**: Rules section
+  **Type**: EVOLVE_RULE
+  **Trigger**: "Never use `any` type in service return types, always use proper generics"
+  **Target**: packages/shared/claude-plugins/src/plugins/flow/agents/angular-service-builder.md
+  **Scope**: Rules section
 
-### Current Content
+  ### Current Content
 
-> (end of current Rules section)
+  > (end of current Rules section)
 
-### Proposed Change
+  ### Proposed Change
 
-> - **No `any` in return types**: Service methods must use proper generic types for return values. Use `Observable<T>`, `Promise<T>`, or specific interfaces instead of `any`.
+  > - **No `any` in return types**: Service methods must use proper generic types for return values. Use `Observable<T>`, `Promise<T>`, or specific interfaces instead of `any`.
 
-### Rationale
+  ### Rationale
 
-Ensures type safety across all generated services, preventing runtime errors from untyped data.
+  Ensures type safety across all generated services, preventing runtime errors from untyped data.
 
-### Impact
+  ### Impact
 
-- Files affected: angular-service-builder.md
-- Risk: LOW
-- Backward compatible: YES
-
-Apply? (yes / no / modify)
+  - Files affected: angular-service-builder.md
+  - Risk: LOW
+  - Backward compatible: YES
+source: shared-agent-evolver
+targetFile: packages/shared/claude-plugins/src/plugins/flow/agents/angular-service-builder.md
+category: NEW_RULE
 ```
 
+**Result**: `Linear issue created: MOB-820 — [Agent Suggestion] Add no-any rule to angular-service-builder`
+
 ### Example 2: EVOLVE_PATTERN
 
 **User feedback**: (corrects error handling approach twice during session)
 
 **Classification**: `EVOLVE_PATTERN` (pattern correction, repeated)
 
-**Proposal**:
+**Filed via `linear-suggestion` skill**:
 
-````markdown
-## Agent Evolution Proposal #2
+````
+title: Add typed error response pattern to shared-error-handler
+description: |
+  ## Agent Evolution Proposal #2
 
-**Type**: EVOLVE_PATTERN
-**Trigger**: User corrected error handling to use catchError with typed error response (2 occurrences)
-**Target**: packages/shared/claude-plugins/src/plugins/flow/agents/shared-error-handler.md
-**Scope**: Error Handling Patterns section
+  **Type**: EVOLVE_PATTERN
+  **Trigger**: User corrected error handling to use catchError with typed error response (2 occurrences)
+  **Target**: packages/shared/claude-plugins/src/plugins/flow/agents/shared-error-handler.md
+  **Scope**: Error Handling Patterns section
 
-### Current Content
+  ### Current Content
 
-> (relevant current pattern)
+  > (relevant current pattern)
 
-### Proposed Change
+  ### Proposed Change
 
-> ### Typed Error Response Pattern
->
-> ```typescript
-> return this.http.post<T>(url, data).pipe(
->   catchError((error: HttpErrorResponse) => {
->     const typed: ApiError = { code: error.status, message: error.message };
->     return throwError(() => typed);
->   }),
-> );
-> ```
+  > ### Typed Error Response Pattern
+  >
+  > ```typescript
+  > return this.http.post<T>(url, data).pipe(
+  >   catchError((error: HttpErrorResponse) => {
+  >     const typed: ApiError = { code: error.status, message: error.message };
+  >     return throwError(() => typed);
+  >   }),
+  > );
+  > ```
 
-### Rationale
-
-Consistent typed error responses prevent unhandled error shapes downstream.
+  ### Rationale
 
-### Impact
+  Consistent typed error responses prevent unhandled error shapes downstream.
 
-- Files affected: shared-error-handler.md
-- Risk: LOW
-- Backward compatible: YES
+  ### Impact
 
-Apply? (yes / no / modify)
+  - Files affected: shared-error-handler.md
+  - Risk: LOW
+  - Backward compatible: YES
+source: shared-agent-evolver
+targetFile: packages/shared/claude-plugins/src/plugins/flow/agents/shared-error-handler.md
+category: PATTERN_UPDATE
 ````
 
+**Result**: `Linear issue created: MOB-821 — [Agent Suggestion] Add typed error response pattern to shared-error-handler`
+
 ### Example 3: IGNORE
 
 **User feedback**: "Use `contactForm` instead of `form` for the variable name here"
 
 **Classification**: `IGNORE` (context-specific naming, applies only to this component)
 
-**Action**: No proposal generated.
+**Action**: No proposal generated, no Linear issue filed.
 
 ### Example 4: CREATE_AGENT
 
@@ -261,7 +276,7 @@ Apply? (yes / no / modify)
 
 **Classification**: `CREATE_AGENT` (explicit request, broad applicability)
 
-**Proposal**: Would propose creating a new `shared-i18n-manager.md` agent file with appropriate frontmatter and responsibilities.
+**Action**: File Linear issue proposing a new `shared-i18n-manager.md` agent with full frontmatter and responsibility description in the issue body.
 
 ### Example 5: UPDATE_WORKFLOW
 
@@ -269,7 +284,7 @@ Apply? (yes / no / modify)
 
 **Classification**: `UPDATE_WORKFLOW` (process improvement, explicit request)
 
-**Proposal**: Would propose modifying the verification order in `impl.md`.
+**Action**: File Linear issue proposing the verification order change in `impl.md`.
 
 ## When to Use This Agent
 

package/plugins/flow/agents/shared-parallelization-analyzer.md

@@ -95,15 +95,33 @@ For each opportunity, calculate:
 
 Output the analysis as a structured markdown report (see Output Format).
 
-### Step 5: Propose Orchestrator Improvements
+### Step 5: File Orchestrator Improvement Suggestions
 
 If recurring patterns are found across multiple analyses:
 
 1. Identify the pattern (e.g., "scaffolding agents for independent files are always falsely sequentialized")
-2. Propose a rule change to `shared-impl-orchestrator.md`
-3. Include the specific section and wording to modify
+2. Formulate a rule change for `shared-impl-orchestrator.md`
+3. **Delegate to `linear-suggestion` skill** to create a Linear issue in the "MobileMS Framework" project:
 
-Only propose permanent orchestrator changes for **recurring** patterns, not one-off task-specific opportunities.
+   ```
+   title: [short description of the recurring pattern and proposed rule]
+   description: |
+     ### Observation
+     [description of the recurring pattern with evidence from multiple tasks]
+
+     ### Proposed Change
+     [target file, section, and exact wording to add/modify]
+
+     ### Evidence
+     [list of task IDs where this pattern was observed]
+   source: shared-parallelization-analyzer
+   targetFile: packages/shared/claude-plugins/src/plugins/flow/agents/shared-impl-orchestrator.md
+   category: OPTIMIZATION
+   ```
+
+4. Include the created issue ID in the console report
+
+Only file Linear issues for **recurring** patterns, not one-off task-specific opportunities. Task-specific opportunities are reported in the console only.
 
 ## Output Format
 
@@ -155,13 +173,14 @@ Only propose permanent orchestrator changes for **recurring** patterns, not one-
 - **Proposed steps**: 4 (2 parallel groups + 2 sequential)
 - **Reduction**: 2 fewer sequential steps
 
-### Orchestrator Improvement Proposals
+### Orchestrator Improvement Suggestions
 
-> Only shown if recurring patterns detected across multiple tasks
+> Only shown if recurring patterns detected across multiple tasks.
+> Suggestions are filed as Linear issues in the "MobileMS Framework" project via `linear-suggestion` skill.
 
-**Proposal**: [description of recurring pattern and suggested orchestrator rule change]
+**Suggestion**: [description of recurring pattern and suggested orchestrator rule change]
 **Target**: `shared-impl-orchestrator.md` → [section name]
-**Suggested addition**: [exact wording to add]
+**Linear issue**: [issue ID] — [issue URL]
 
 ---
 
@@ -197,7 +216,7 @@ _Analysis generated by shared-parallelization-analyzer_
 2. **Conservative analysis**: When uncertain whether a dependency exists, treat it as real. False parallelization is worse than missed optimization.
 3. **Same-file operations are always sequential**: If two agents modify the same file, they must remain sequential regardless of which parts they modify.
 4. **Only recurring patterns proposed as permanent changes**: Task-specific opportunities are reported but NOT proposed as orchestrator modifications. Only patterns observed repeatedly should be suggested as `shared-impl-orchestrator.md` changes.
-5. **Non-blocking and advisory**: This analysis is informational only. It does not block any workflow and proposals are shown to the user without auto-applying.
+5. **Non-blocking and advisory**: This analysis is informational only. It does not block any workflow. Recurring pattern suggestions are filed as Linear issues via `linear-suggestion` skill — never auto-applied to agent files.
 6. **Respect existing PARALLEL annotations**: If the orchestration plan already marks agents as PARALLEL, confirm or flag them rather than re-proposing.
 
 ## Examples

package/plugins/flow/commands/commit.md

@@ -135,7 +135,7 @@ After the commit is created, perform an optional parallelization analysis:
 
 - This step is **non-blocking** and **advisory only**
 - The analysis report is shown to the user in the console but is NOT auto-applied
-- Orchestrator improvement proposals (if any) are presented for the user to review
+- Recurring orchestrator improvement suggestions (if any) are filed as Linear issues in the "MobileMS Framework" project via `linear-suggestion` skill — no user interaction required
 - A commit failure or missing orchestration plan should never cause this step to error
 
 ### Guidelines
@@ -146,7 +146,7 @@ After the commit is created, perform an optional parallelization analysis:
 4. If task type is unclear, analyze the code changes to determine type
 5. Always include the Linear task reference in the footer
 6. If there are no staged changes, warn the user and don't create commit
-7. After a successful commit, run the optional parallelization analysis (Step 6) to surface optimization opportunities from the orchestration plan
+7. After a successful commit, run the optional parallelization analysis (Step 6) to surface optimization opportunities from the orchestration plan. Recurring patterns are filed as Linear issues automatically via `linear-suggestion` skill
 
 ### Example
 
@@ -176,11 +176,19 @@ For Linear task "ENG-123: Add dark mode toggle to settings":
 - **Proposed steps**: 4 (1 parallel group + 3 sequential)
 - **Reduction**: 1 fewer sequential step
 
+### Orchestrator Improvement Suggestions
+
+**Suggestion**: Independent scaffolding agents are always falsely sequentialized
+**Target**: `shared-impl-orchestrator.md` → Parallel vs Sequential
+**Linear issue**: MOB-815 — https://linear.app/mobilems/issue/MOB-815
+
 ---
 
 _Analysis generated by shared-parallelization-analyzer_
 ```
 
+If a recurring pattern is detected, a Linear issue is automatically created in "MobileMS Framework" via `linear-suggestion` skill.
+
 If no orchestration plan is found in Linear comments, this step is silently skipped.
 
 ---

package/plugins/flow/commands/impl.md

@@ -258,7 +258,7 @@ Continue? (yes/no/adjust)
 
 **Feedback Collection for Agent Evolution:**
 
-During 3x3 checkpoints, when the user provides corrections or suggestions about coding patterns, implementation approach, or agent behavior — collect these as **evolution feedback items**. These will be processed in Step 3g-evolve. Look for signals like: universal language ("always", "never"), pattern-level corrections, or explicit requests to update agent behavior.
+During 3x3 checkpoints, when the user provides corrections or suggestions about coding patterns, implementation approach, or agent behavior — collect these as **evolution feedback items**. These will be processed in Step 3g-evolve and filed as Linear issues via `linear-suggestion` skill. Look for signals like: universal language ("always", "never"), pattern-level corrections, or explicit requests to update agent behavior.
 
 **IMPORTANT**: Also STOP and wait for user confirmation:
 
@@ -414,15 +414,15 @@ The agent will:
 
 1. Classify each feedback item (IGNORE / EVOLVE_PATTERN / EVOLVE_RULE / EVOLVE_TEMPLATE / CREATE_AGENT / UPDATE_WORKFLOW)
 2. Generate proposals for non-IGNORE items
-3. Present each proposal to the user for confirmation
-4. Apply confirmed changes to agent/command/skill files
-5. Return Evolution Report
+3. File each proposal as a Linear issue in "MobileMS Framework" via `linear-suggestion` skill
+4. Return Evolution Report with created issue IDs
 
 **IMPORTANT**:
 
-- Every proposed change MUST be confirmed by the user before applying
+- Agent files are NOT modified directly — proposals are filed as Linear issues for manual review
 - If no reusable feedback was collected during this subtask, skip this step
 - This step runs BEFORE the subtask pause (Step 3h) so evolution is complete before moving on
+- If Linear issue creation fails, continue silently — do not block the workflow
 
 #### Step 3h: Pause After Subtask Completion
 
@@ -483,8 +483,8 @@ The agent will:
 1. Analyze all feedback from the entire session (not just last subtask)
 2. Identify recurring patterns that may have been missed per-subtask
 3. Propose cross-cutting improvements (patterns spanning multiple agents)
-4. Present proposals with user confirmation
-5. Return final Evolution Report
+4. File proposals as Linear issues in "MobileMS Framework" via `linear-suggestion` skill
+5. Return final Evolution Report with created issue IDs
 
 **IMPORTANT**: This step catches improvements that only become visible across multiple subtasks. Skip if no actionable feedback exists.
 
@@ -513,14 +513,14 @@ To Do → In Progress → In Review (if completed)
 
 **ALWAYS stop and wait for user confirmation at these points:**
 
-| 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 proposals for confirmation |
+| 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 |
 
 **Never proceed automatically** - always wait for explicit user confirmation before:
 
@@ -609,8 +609,8 @@ When verification fails, delegate to appropriate fix agent:
 20. **Capture after screenshots + post to Linear**: After implementation, launch `screenshot-reporter` agent to capture "after" screenshots, generate comparison report, post to Linear, and cleanup
 21. **Document translations changes**: If `apps/web/public/translations.json` was modified, include a table with added/changed translation keys and their PL/EN values in the Implementation Report
 22. **Capture screenshots in both modes**: Agent captures screenshots in BOTH normal mode and dark mode (high contrast) for complete visual documentation
-23. **Collect feedback for agent evolution**: During implementation, observe user corrections and suggestions. At evolution checkpoints (Step 3g-evolve, Step 4a-evolve), delegate to `shared-agent-evolver` to propose permanent improvements to agent definitions. Every modification requires user confirmation.
-24. **Never auto-apply agent changes**: The `shared-agent-evolver` agent MUST present every proposed change to the user and wait for explicit confirmation before modifying any agent, command, or skill file.
+23. **Collect feedback for agent evolution**: During implementation, observe user corrections and suggestions. At evolution checkpoints (Step 3g-evolve, Step 4a-evolve), delegate to `shared-agent-evolver` which files improvement proposals as Linear issues in "MobileMS Framework" via `linear-suggestion` skill.
+24. **Never modify agent files directly during implementation**: The `shared-agent-evolver` agent files all proposals as Linear issues for manual review — it does NOT modify agent, command, or skill files directly.
 
 ## Example Flow
 
@@ -634,7 +634,7 @@ When verification fails, delegate to appropriate fix agent:
 8. **📸 VERIFY**: Confirm `SCREENSHOT_REQUIREMENT_MET: YES`
 9. Create Implementation Report comment
 10. Set status: In Progress → In Review
-11. **EVOLVE**: User corrected error handling pattern → proposed adding pattern to `shared-error-handler` → user confirmed → applied
+11. **EVOLVE**: User corrected error handling pattern → filed Linear issue MOB-820 proposing pattern addition to `shared-error-handler`
 
 **Processing ENG-456-2 (blocked):**
 

package/plugins/flow/skills/linear-suggestion/SKILL.md

@@ -0,0 +1,132 @@
+---
+name: linear-suggestion
+description: Create a Linear issue in the "MobileMS Framework" project with a suggestion for agent, command, or skill improvements.
+allowed-tools: mcp__linear-server__create_issue
+---
+
+# Linear Suggestion
+
+Create a Linear issue in the **MobileMS Framework** project containing a suggestion for improving agent definitions, commands, or skills. Used by automated analysis agents to propose changes without blocking the workflow.
+
+## When to Use
+
+- When an automated agent (e.g., `shared-parallelization-analyzer`) identifies a recurring pattern that could improve an agent, command, or skill
+- When proposing orchestrator rule changes based on parallelization analysis
+- When any non-interactive process needs to suggest framework improvements
+
+## Input Parameters
+
+The invoking agent must provide:
+
+| Parameter     | Required | Description                                                     |
+| ------------- | -------- | --------------------------------------------------------------- |
+| `title`       | YES      | Short summary of the suggestion (max 100 chars)                 |
+| `description` | YES      | Full markdown description with rationale and proposed changes    |
+| `source`      | YES      | Agent that generated the suggestion (e.g., `shared-parallelization-analyzer`) |
+| `targetFile`  | NO       | Path to the file to be modified (e.g., `agents/shared-impl-orchestrator.md`) |
+| `category`    | NO       | One of: `OPTIMIZATION`, `NEW_RULE`, `PATTERN_UPDATE`, `BUG_FIX` |
+
+## Issue Format
+
+### Title
+
+```
+[Agent Suggestion] {title}
+```
+
+### Description
+
+```markdown
+## Agent Improvement Suggestion
+
+**Source agent**: `{source}`
+**Category**: {category}
+**Target file**: `{targetFile}`
+
+---
+
+{description}
+
+---
+
+_This issue was automatically created by `{source}` via the `linear-suggestion` skill._
+_Review and apply manually if the suggestion is valid._
+```
+
+## Process
+
+1. **Format the issue title** with `[Agent Suggestion]` prefix
+2. **Build the description** using the template above, inserting all provided parameters
+3. **Create the issue** using MCP Linear server:
+
+   ```
+   Create issue in project "MobileMS Framework":
+   - Title: [Agent Suggestion] {title}
+   - Description: {formatted description}
+   - Label: agent-evolution
+   ```
+
+4. **Return the issue ID and URL** to the invoking agent
+
+## Output Format
+
+After successful creation, return:
+
+```
+Linear issue created:
+- ID: {issueId}
+- Title: [Agent Suggestion] {title}
+- URL: {issueUrl}
+```
+
+## Error Handling
+
+If issue creation fails (e.g., MCP Linear server unavailable):
+
+- Log the error silently
+- Do NOT block the parent workflow
+- Return a failure notice without throwing
+
+```
+Linear suggestion skipped: {error reason}
+```
+
+## Example
+
+**Input from `shared-parallelization-analyzer`:**
+
+```
+title: Add parallel scaffolding rule to orchestrator
+description: |
+  ### Observation
+
+  In 3 out of 5 recent tasks, scaffolding agents for independent files
+  (e.g., `angular-component-scaffolder` + `angular-service-builder`) were
+  marked as SEQ despite having no shared output files.
+
+  ### Proposed Change
+
+  Add to `shared-impl-orchestrator.md` → Execution Patterns → Parallel vs Sequential:
+
+  | Scenario                                | Pattern  | Reason                          |
+  | --------------------------------------- | -------- | ------------------------------- |
+  | Multiple scaffolding for independent files | PARALLEL | No shared output files between scaffolders |
+
+  ### Evidence
+
+  - MOB-700: scaffold-component + scaffold-service (independent)
+  - MOB-705: scaffold-directive + scaffold-service (independent)
+  - MOB-710: scaffold-component + scaffold-pipe (independent)
+source: shared-parallelization-analyzer
+targetFile: packages/shared/claude-plugins/src/plugins/flow/agents/shared-impl-orchestrator.md
+category: OPTIMIZATION
+```
+
+**Created issue:**
+
+```
+Linear issue created:
+- ID: MOB-815
+- Title: [Agent Suggestion] Add parallel scaffolding rule to orchestrator
+- URL: https://linear.app/mobilems/issue/MOB-815
+```