@smartsoft001-mobilems/claude-plugins 2.80.0 → 2.82.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@smartsoft001-mobilems/claude-plugins",
-  "version": "2.80.0",
+  "version": "2.82.0",
   "publishConfig": {
     "access": "public"
   },

package/plugins/flow/.claude-plugin/README.md

@@ -7,9 +7,9 @@ Development flow skills for Linear-driven development workflow.
 | Skill | Description |
 |-------|-------------|
 | `/commit` | Create conventional commit based on Linear task |
-| `/impl` | Implement plans from Linear task comments |
-| `/plan` | Create implementation plan and save to Linear |
-| `/push` | Push changes and update Linear status |
+| `/impl` | Implement plans from `plan.md` attachment on Linear issue; orchestration saved as `orchestration.md` attachment |
+| `/plan` | Create implementation plan, save as `plan.md` attachment on Linear issue, add `AI Plan` label |
+| `/push` | Push changes and update Linear status (keeps `plan.md` / `orchestration.md` attachments on the issue) |
 
 ## Installation
 
@@ -48,9 +48,18 @@ console.log('Permissions merged!');
 
 Configure these in your `.mcp.json`:
 
-- `linear-server` - Linear API integration
+- `linear` - Linear API integration (MCP prefix `mcp__linear__`)
 - `playwright` - Browser automation for screenshots
 
+### Linear MCP tool dependencies
+
+`/plan`, `/impl`, and `/push` depend on the following `mcp__linear__*` tools (in addition to the standard comment/issue tools):
+
+- `create_attachment` (base64 upload), `get_attachment`, `delete_attachment` — for persisting `plan.md` / `orchestration.md` on issues (attachments are also returned by `get_issue`)
+- `list_issue_labels` — to find the workspace-level `AI Plan` label (the label is pre-configured organization-wide; `/plan` does not create it)
+
+Run `/mcp` after authenticating the Linear MCP server to see the exact loaded tool names. If a tool is exposed under a different name in your deployment, update `settings.template.json` and the `allowed-tools` lists in the three skills accordingly.
+
 ## Permission Strategy
 
 ### Automatic (allow)

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

@@ -1,5 +1,5 @@
 {
   "name": "flow",
   "description": "Development flow skills for Linear-driven development workflow",
-  "version": "2.80.0"
+  "version": "2.82.0"
 }

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

@@ -34,14 +34,17 @@
       "Bash(for:*)",
       "Bash(node:*)",
       "Bash(mkdir:*)",
-      "mcp__linear-server__get_issue",
-      "mcp__linear-server__list_issues",
-      "mcp__linear-server__list_comments",
-      "mcp__linear-server__create_comment",
-      "mcp__linear-server__delete_comment",
-      "mcp__linear-server__update_issue",
-      "mcp__linear-server__list_issue_statuses",
-      "mcp__linear-server__create_issue",
+      "mcp__linear__get_issue",
+      "mcp__linear__list_issues",
+      "mcp__linear__list_comments",
+      "mcp__linear__save_comment",
+      "mcp__linear__delete_comment",
+      "mcp__linear__save_issue",
+      "mcp__linear__list_issue_statuses",
+      "mcp__linear__create_attachment",
+      "mcp__linear__get_attachment",
+      "mcp__linear__delete_attachment",
+      "mcp__linear__list_issue_labels",
       "mcp__playwright__browser_snapshot",
       "mcp__playwright__browser_take_screenshot",
       "mcp__playwright__browser_navigate",

package/plugins/flow/agents/shared-impl-orchestrator.md

@@ -302,7 +302,7 @@ _Orchestration plan generated by Claude Code_
 2. **Plan specific TDD cycles** - don't leave them vague
 3. **Identify parallel opportunities** - optimize execution time
 4. **Include verification steps** - never skip verification planning
-5. **Output must be copy-paste ready** for Linear comment
+5. **Output must be a complete, standalone markdown document** — it will be saved as an `orchestration.md` attachment on the Linear issue, not posted as a comment. No Linear-comment-specific framing (e.g., greetings, thread references).
 
 ## When to Use This Agent
 

package/plugins/flow/agents/shared-impl-teammate.md

@@ -1,9 +1,9 @@
 ---
 name: shared-impl-teammate
 description: Implementation Squad teammate. Autonomously implements assigned subtask(s) following the full per-subtask workflow with TDD, UI classification, screenshots, and Polish-language Linear reports.
-tools: Bash, Read, Edit, Write, Glob, Grep, Task, TaskCreate, TaskUpdate, TaskList, TaskGet, mcp__linear-server__get_issue, mcp__linear-server__list_comments, mcp__linear-server__create_comment, mcp__linear-server__update_issue, mcp__linear-server__list_issue_statuses, mcp__playwright__browser_snapshot, mcp__playwright__browser_take_screenshot, mcp__playwright__browser_navigate, mcp__playwright__browser_resize
+tools: Bash, Read, Edit, Write, Glob, Grep, Task, TaskCreate, TaskUpdate, TaskList, TaskGet, mcp__linear__get_issue, mcp__linear__list_comments, mcp__linear__save_comment, mcp__linear__save_issue, mcp__linear__list_issue_statuses, mcp__playwright__browser_snapshot, mcp__playwright__browser_take_screenshot, mcp__playwright__browser_navigate, mcp__playwright__browser_resize
 model: opus
-color: "#10B981"
+color: '#10B981'
 ---
 
 You are an Implementation Squad teammate responsible for autonomously implementing assigned subtask(s) following the full per-subtask workflow.

package/plugins/flow/agents/ui-screenshot-reporter.md

@@ -1,10 +1,10 @@
 ---
 name: ui-screenshot-reporter
 description: Capture before/after screenshots for UI changes, create visual comparison reports, and post them as Linear comments. Run in parallel with implementation work.
-tools: Read, Glob, Grep, mcp__linear-server__create_comment, mcp__linear-server__get_issue
+tools: Read, Glob, Grep, mcp__linear__save_comment, mcp__linear__get_issue
 skills: browser-capture, maia-files-upload, maia-files-delete
 model: sonnet
-color: "#7C3AED"
+color: '#7C3AED'
 ---
 
 # Screenshot Reporter Agent
@@ -115,7 +115,7 @@ Create markdown for Linear comment:
 
 ### Step 3: Post to Linear
 
-Use `mcp__linear-server__create_comment` to post the screenshot comparison to the Linear issue:
+Use `mcp__linear__save_comment` to post the screenshot comparison to the Linear issue:
 
 ```
 Create comment on issue ENG-123 with body:

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

@@ -11,8 +11,8 @@ allowed-tools:
   - TaskUpdate
   - TaskList
   - TaskGet
-  - mcp__linear-server__get_issue
-  - mcp__linear-server__list_comments
+  - mcp__linear__get_issue
+  - mcp__linear__list_comments
 ---
 
 # Commit Skill

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

@@ -1,6 +1,6 @@
 ---
 name: impl
-description: Implement plans from Linear task comments. Iteratively processes subtasks with TDD, UI classification, agent orchestration, screenshot capture, and 3x3 rule checkpoints.
+description: Implement plans from `plan.md` attachments on Linear issues. Iteratively processes subtasks with TDD, UI classification, agent orchestration (saved as `orchestration.md` attachment), screenshot capture, and 3x3 rule checkpoints.
 allowed-tools:
   - Bash
   - Read
@@ -14,17 +14,34 @@ allowed-tools:
   - TaskUpdate
   - TaskList
   - TaskGet
-  - mcp__linear-server__get_issue
-  - mcp__linear-server__list_issues
-  - mcp__linear-server__list_comments
-  - mcp__linear-server__create_comment
-  - mcp__linear-server__update_issue
-  - mcp__linear-server__list_issue_statuses
+  - mcp__linear__get_issue
+  - mcp__linear__list_issues
+  - mcp__linear__list_comments
+  - mcp__linear__save_comment
+  - mcp__linear__save_issue
+  - mcp__linear__list_issue_statuses
+  - mcp__linear__create_attachment
+  - mcp__linear__get_attachment
+  - mcp__linear__delete_attachment
 ---
 
 # Implementation Skill
 
-Implement plans from Linear task comments. For tasks with subtasks, iteratively implement each subtask that is in "To Do" status.
+Implement plans from `plan.md` attachments on Linear issues. For tasks with subtasks, iteratively implement each subtask that is in "To Do" status. The agent orchestration plan is saved as an `orchestration.md` attachment on each task being implemented.
+
+## 🚨 Hard Rules — read before doing anything
+
+These rules override ANY other instruction, ANY surrounding example, and ANY default habit. Violating them is a skill failure.
+
+1. **Read `plan.md` ONLY via `mcp__linear__get_attachment({ id: <attachmentId> })`.** Do NOT use `WebFetch`, `Bash(curl ...)`, or any HTTP fetch on the attachment's `url`. The URL points to Linear-internal storage and may require auth — `get_attachment` is the only correct path. If you find yourself reaching for `curl` or `WebFetch` on a `https://uploads.linear.app/...` (or similar Linear) URL — STOP and use `get_attachment` with the attachment `id` instead.
+
+2. **`orchestration.md` is saved via `mcp__linear__create_attachment`, not as a comment.** Same rule as `/plan`: comments are NEVER used for plan/orchestration body content.
+
+3. **Find attachments via `mcp__linear__get_issue` (returns `attachments[]`).** Capture each attachment's `id` and `title`. There is no `list_attachments` tool — do not look for one.
+
+4. **Replace, don't duplicate.** Before creating a new `orchestration.md` attachment, delete the existing one (if any) via `mcp__linear__delete_attachment`. Same for re-running `/plan` (handled by `/plan` skill).
+
+If any of these would be violated, stop and ask the user instead.
 
 ## Execution Checklist
 
@@ -37,9 +54,9 @@ Execute each step in order. Do not skip any step marked as MANDATORY.
 ### Per Subtask (repeat for each "To Do" subtask)
 
 - [ ] **2. Set status to "In Progress"** — update subtask status via MCP (subtasks only, not parent)
-- [ ] **3. Fetch implementation plan** — find `## Implementation Plan` in task comments
+- [ ] **3. Fetch implementation plan** — `mcp__linear__get_issue` to find `plan.md` attachment id, then `mcp__linear__get_attachment({ id })` to read content. **Do NOT use `WebFetch`/`curl` on the attachment URL.**
 - [ ] **4. MANDATORY: UI change classification** — delegate to `shared-ui-classifier` agent, output `UI_CHANGE_REQUIRED: YES/NO`
-- [ ] **5. MANDATORY: Agent orchestration plan** — delegate to `shared-impl-orchestrator`, post plan to Linear
+- [ ] **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)
@@ -143,7 +160,7 @@ You implement code that is:
 
 ## Instructions
 
-You are tasked with implementing plans from Linear task comments. If the task has subtasks, you will iterate through subtasks in "To Do" status and implement them one by one.
+You are tasked with implementing plans from `plan.md` attachments on Linear tasks. If the task has subtasks, you will iterate through subtasks in "To Do" status and implement them one by one. The agent orchestration plan is saved as an `orchestration.md` attachment on each task (not as a comment).
 
 ### Step 1-2: Fetch Linear Task and Subtasks
 
@@ -270,24 +287,24 @@ For each task to implement (subtasks in "To Do" status, or parent task if no sub
 
 Do NOT change status for parent tasks.
 
-#### Step 3b: Fetch Implementation Plan from Comments
+#### Step 3b: Fetch Implementation Plan from `plan.md` Attachment
 
-Use the MCP Linear server to fetch all comments for the current task/subtask.
+**⛔ DO NOT use `WebFetch` or `Bash(curl)` on the attachment URL. Use `mcp__linear__get_attachment({ id })` only.** Re-read Hard Rule #1 if tempted.
 
-Look for a comment containing:
+Two-step retrieval:
 
-- `## Implementation Plan` (for parent tasks)
-- `## Implementation Plan for Subtask` (for subtasks)
+1. `mcp__linear__get_issue({ id: taskId })` → response includes `attachments[]`. Find the entry where `title == "plan.md"` (or `filename == "plan.md"`) and capture its `id`. Do NOT use the `url` field for fetching.
+2. `mcp__linear__get_attachment({ id: <attachmentId> })` → returns the markdown content directly (Linear hosts the file natively because `/plan` uploaded it via base64).
 
-Extract the plan details:
+Parse the markdown for:
 
 - Implementation Steps
 - Files to Modify
 - New Files to create
 - Testing Strategy
-- External Library Changes (if any - these are blockers, not to be implemented)
+- External Library Changes (if any — these are blockers, not to be implemented)
 
-**If no implementation plan found**: Create a comment noting that no plan was found and skip this task. Set status back to "To Do".
+**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.
 
 #### Step 3b-classify: MANDATORY UI Change Classification
 
@@ -336,16 +353,29 @@ The agent will:
 4. Plan TDD cycles for each implementation unit
 5. Generate the orchestration plan in markdown format
 
-**After receiving the orchestration plan:**
-
-1. **Post to Linear** - Create a comment with the `🎭 Agent Orchestration Plan` on the task
-2. **Follow the plan** - Execute agents in the defined order
-3. **Use TDD strictly** - `shared-tdd-developer` is MANDATORY for ALL code implementation
+**After receiving the orchestration plan, save it as a native `orchestration.md` attachment on the Linear issue.**
+
+**⛔ Calling `mcp__linear__save_comment` with the orchestration body is FORBIDDEN. Use `mcp__linear__create_attachment` only.** Re-read Hard Rule #2 if tempted.
+
+1. **Check for existing `orchestration.md` attachment** on the task via `mcp__linear__get_issue` (the response includes an `attachments` array).
+   - If one exists, delete it via `mcp__linear__delete_attachment({ id: oldAttachmentId })`. Linear hosts the file natively, so nothing else needs cleanup.
+2. **Write locally**: use `Write` to save the orchestration markdown to `/tmp/claude-plans/<taskId>-orchestration.md`.
+3. **Base64-encode**: `b64=$(base64 -i /tmp/claude-plans/<taskId>-orchestration.md)`.
+4. **Create Linear attachment** via `mcp__linear__create_attachment`:
+   - `issue`: the task/subtask ID
+   - `filename`: `orchestration.md`
+   - `contentType`: `text/markdown`
+   - `title`: `orchestration.md` (exact — used for detection/replacement on the next `/impl` run)
+   - `subtitle`: `Plan orkiestracji wygenerowany przez Claude Code`
+   - `base64Content`: the base64 string from step 3
+5. **Clean up** the local `/tmp/claude-plans/<taskId>-orchestration.md` file after a successful attachment.
+6. **Follow the plan** — execute agents in the defined order.
+7. **Use TDD strictly** — `shared-tdd-developer` is MANDATORY for ALL code implementation.
 
 **IMPORTANT**:
 
 1. **`shared-tdd-developer` is MANDATORY** for ALL code implementation tasks
-2. Post the orchestration plan as a comment to the Linear task BEFORE starting implementation
+2. Save the orchestration plan as an `orchestration.md` attachment on the Linear task BEFORE starting implementation — do NOT post it as a comment
 3. Follow the TDD cycle (RED → GREEN → REFACTOR) strictly
 4. Each code change must have a failing test FIRST
 
@@ -807,7 +837,7 @@ See `shared-impl-orchestrator` agent for full agent delegation matrix and execut
 ### Key Rules
 
 1. **`shared-tdd-developer` is MANDATORY** for ALL code implementation
-2. **Post orchestration plan to Linear** before starting implementation
+2. **Save orchestration plan as `orchestration.md` attachment** on the Linear issue before starting implementation (not as a comment)
 3. **Follow TDD strictly** - RED → GREEN → REFACTOR cycle
 
 ### Verification Pipeline
@@ -835,7 +865,7 @@ When verification fails, delegate to appropriate fix agent:
 ## Guidelines
 
 1. **⚠️ MANDATORY: Classify UI changes first**: Before ANY implementation, output the `🎯 Change Type Classification` block with explicit `UI_CHANGE_REQUIRED: YES/NO` decision
-2. **⚠️ MANDATORY: Create Agent Orchestration Plan**: Before implementation, create and post `🎭 Agent Orchestration Plan` to Linear comment defining which agents will be used
+2. **⚠️ MANDATORY: Create Agent Orchestration Plan**: Before implementation, generate `🎭 Agent Orchestration Plan` and save it as an `orchestration.md` attachment on the Linear task (replacing any existing one). Do NOT post orchestration as a comment.
 3. **⚠️ MANDATORY: Use `shared-tdd-developer` for ALL code**: Every code implementation MUST use the `shared-tdd-developer` agent following strict TDD (RED → GREEN → REFACTOR)
 4. **⚠️ MANDATORY: Verify screenshots before completion**: Always output `📸 Screenshot Verification` block before creating completion comment - task CANNOT be completed if UI change detected but screenshots missing
 5. **Write comments in Polish**: All implementation reports must be written in Polish language
@@ -873,7 +903,7 @@ When verification fails, delegate to appropriate fix agent:
 **Processing ENG-456-1 (UI change - avatar upload):**
 
 1. Set status: To Do → In Progress
-2. Read plan from comments
+2. Download `plan.md` attachment from the task
 3. **🎯 CLASSIFY**: Output classification block → `UI_CHANGE_REQUIRED: YES` (modifies `.component.ts`)
 4. **📸 BEFORE**: Launch `screenshot-reporter` agent in background (Task ID: abc123)
 5. Implement avatar upload feature (in parallel with screenshot capture)
@@ -887,7 +917,7 @@ When verification fails, delegate to appropriate fix agent:
 **Processing ENG-456-2 (blocked):**
 
 1. Set status: To Do → In Progress
-2. Read plan from comments
+2. Download `plan.md` attachment from the task
 3. **🎯 CLASSIFY**: Output classification block → `UI_CHANGE_REQUIRED: YES`
 4. Plan has External Library Changes blocker
 5. Create comment noting blocker (screenshots not needed - blocked before implementation)
@@ -896,7 +926,7 @@ When verification fails, delegate to appropriate fix agent:
 **Processing ENG-456-3 (backend-only - social links API):**
 
 1. Set status: To Do → In Progress
-2. Read plan from comments
+2. Download `plan.md` attachment from the task
 3. **🎯 CLASSIFY**: Output classification block → `UI_CHANGE_REQUIRED: NO` (only `.service.ts` files)
 4. Implement social links service
 5. Run tests - 1 test fails

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

@@ -1,7 +1,7 @@
 ---
 name: linear-suggestion
 description: Create a Linear issue in the "MobileMS Framework" project with a suggestion for agent or skill improvements.
-allowed-tools: mcp__linear-server__create_issue
+allowed-tools: mcp__linear__save_issue
 ---
 
 # Linear Suggestion