linear-subagent-guide
Guides optimal Linear operations usage with caching, performance patterns, and error handling. Auto-activates when implementing CCPM commands that interact with Linear. Prevents usage of non-existent Linear MCP tools.
What this skill does
# Linear Subagent Guide
## ⛔ EXACT LINEAR MCP PARAMETERS (VERIFIED)
**These are the EXACT parameter names from `get_server_tools`. Copy exactly.**
### Most Common Operations
```javascript
// GET ISSUE - uses "id"
mcp__agent-mcp-gateway__execute_tool({
server: "linear",
tool: "get_issue",
args: { id: "WORK-26" } // ✅ CORRECT - "id" not "issueId"
})
// UPDATE ISSUE - uses "id"
mcp__agent-mcp-gateway__execute_tool({
server: "linear",
tool: "update_issue",
args: {
id: "WORK-26", // ✅ CORRECT - "id" not "issueId"
description: "...",
state: "In Progress"
}
})
// CREATE COMMENT - uses "issueId"
mcp__agent-mcp-gateway__execute_tool({
server: "linear",
tool: "create_comment",
args: {
issueId: "WORK-26", // ✅ CORRECT - "issueId" for comments
body: "Comment text"
}
})
// LIST COMMENTS - uses "issueId"
mcp__agent-mcp-gateway__execute_tool({
server: "linear",
tool: "list_comments",
args: { issueId: "WORK-26" } // ✅ CORRECT
})
```
### Parameter Reference Table
| Tool | Required Parameter | Example Args |
|------|-------------------|--------------|
| `get_issue` | `id` | `{ id: "WORK-26" }` |
| `update_issue` | `id` | `{ id: "WORK-26", ... }` |
| `create_comment` | `issueId`, `body` | `{ issueId: "WORK-26", body: "..." }` |
| `list_comments` | `issueId` | `{ issueId: "WORK-26" }` |
| `create_issue` | `title`, `team` | `{ title: "...", team: "..." }` |
| `get_project` | `query` | `{ query: "ProjectName" }` |
| `get_team` | `query` | `{ query: "TeamName" }` |
| `get_user` | `query` | `{ query: "me" }` |
---
## Overview
The **Linear subagent** (`ccpm:linear-operations`) is a dedicated MCP handler that optimizes all Linear API operations in CCPM. Rather than making direct Linear MCP calls, commands should delegate to this subagent, which provides:
- **50-60% token reduction** (15k-25k → 8k-12k per workflow)
- **Session-level caching** with 85-95% hit rates
- **Performance**: <50ms for cached operations (vs 400-600ms direct)
- **Structured error handling** with actionable suggestions
- **Centralized logic** for Linear operations consistency
## When to Use the Linear Subagent
**Use the subagent for:**
- Reading issues, projects, teams, statuses
- Creating or updating issues, projects
- Managing labels and comments
- Fetching documents and cycles
- Searching Linear documentation
**Never use the subagent for:**
- Local file operations
- Git commands
- External API calls (except Linear)
---
## ⚠️ CRITICAL: Parameter Name Gotcha
**Different Linear MCP tools use different parameter names for issue IDs:**
| Tool | Parameter | WRONG | CORRECT |
|------|-----------|-------|---------|
| `get_issue` | `id` | `{ issueId: "X" }` ❌ | `{ id: "X" }` ✅ |
| `update_issue` | `id` | `{ issueId: "X" }` ❌ | `{ id: "X" }` ✅ |
| `create_comment` | `issueId` | `{ id: "X" }` ❌ | `{ issueId: "X" }` ✅ |
| `list_comments` | `issueId` | `{ id: "X" }` ❌ | `{ issueId: "X" }` ✅ |
**First-call failures** are often caused by using `issueId` instead of `id` for `get_issue`/`update_issue`.
---
## Available Linear MCP Tools (Complete Reference)
Linear MCP provides **23 tools** for interacting with Linear. This is the complete, validated list.
---
### 1. Comments (2 tools)
#### `list_comments`
List comments for a specific Linear issue.
**Parameters:**
- `issueId` (string, required) - The issue ID
**Example:**
```javascript
mcp__linear__list_comments({ issueId: "PSN-41" })
```
#### `create_comment`
Create a comment on a specific Linear issue.
**Parameters:**
- `issueId` (string, required) - The issue ID
- `body` (string, required) - The content of the comment as Markdown
- `parentId` (string, optional) - A parent comment ID to reply to
**Linear's Native Collapsible Syntax:**
Use `+++` to create collapsible sections (starts collapsed, native Linear feature):
```
+++ Section Title
Content here (multi-line markdown supported)
+++
```
**Example (simple):**
```javascript
mcp__linear__create_comment({
issueId: "PSN-41",
body: "## Progress Update\n\nCompleted first phase."
})
```
**Example (with collapsible section):**
```javascript
mcp__linear__create_comment({
issueId: "PSN-41",
body: `🔄 **Progress Update**
Completed first phase, all tests passing
+++ 📋 Detailed Context
**Changed Files:**
- src/auth.ts
- src/tests/auth.test.ts
**Next Steps:**
- Implement phase 2
- Update documentation
+++`
})
```
---
### 2. Cycles (1 tool)
#### `list_cycles`
Retrieve cycles for a specific Linear team.
**Parameters:**
- `teamId` (string, required) - The team ID
- `type` (string, optional) - "current", "previous", or "next"
**Example:**
```javascript
mcp__linear__list_cycles({ teamId: "team-123", type: "current" })
```
---
### 3. Documents (2 tools)
#### `get_document`
Retrieve a Linear document by ID or slug.
**Parameters:**
- `id` (string, required) - The document ID or slug
**Example:**
```javascript
mcp__linear__get_document({ id: "doc-abc-123" })
```
#### `list_documents`
List documents in the user's Linear workspace.
**Parameters:**
- `limit` (number, optional, max 250, default 50)
- `before` (string, optional) - An ID to end at
- `after` (string, optional) - An ID to start from
- `orderBy` (string, optional) - "createdAt" or "updatedAt" (default: "updatedAt")
- `query` (string, optional) - Search query
- `projectId` (string, optional) - Filter by project ID
- `initiativeId` (string, optional) - Filter by initiative ID
- `creatorId` (string, optional) - Filter by creator ID
- `createdAt` (string, optional) - ISO-8601 date-time or duration (e.g., "-P1D")
- `updatedAt` (string, optional) - ISO-8601 date-time or duration
- `includeArchived` (boolean, optional, default false)
**Example:**
```javascript
mcp__linear__list_documents({ projectId: "proj-123", limit: 20 })
```
---
### 4. Issues (4 tools)
#### `get_issue`
Retrieve detailed information about an issue by ID.
**Parameters:**
- `id` (string, required) - The issue ID (e.g., "PSN-41")
**Example:**
```javascript
mcp__linear__get_issue({ id: "PSN-41" })
```
#### `list_issues`
List issues in the user's Linear workspace. Use "me" for assignee to get your issues.
**Parameters:**
- `limit` (number, optional, max 250, default 50)
- `before` (string, optional)
- `after` (string, optional)
- `orderBy` (string, optional) - "createdAt" or "updatedAt"
- `query` (string, optional) - Search title or description
- `team` (string, optional) - Team name or ID
- `state` (string, optional) - State name or ID
- `cycle` (string, optional) - Cycle name or ID
- `label` (string, optional) - Label name or ID
- `assignee` (string, optional) - User ID, name, email, or "me"
- `delegate` (string, optional) - Agent name or ID
- `project` (string, optional) - Project name or ID
- `parentId` (string, optional) - Parent issue ID
- `createdAt` (string, optional) - ISO-8601 date-time or duration
- `updatedAt` (string, optional) - ISO-8601 date-time or duration
- `includeArchived` (boolean, optional, default true)
**Example:**
```javascript
mcp__linear__list_issues({ assignee: "me", state: "In Progress" })
```
#### `create_issue`
Create a new Linear issue.
**Parameters:**
- `title` (string, required)
- `team` (string, required) - Team name or ID
- `description` (string, optional) - Markdown description
- `cycle` (string, optional) - Cycle name, number, or ID
- `priority` (number, optional) - 0=None, 1=Urgent, 2=High, 3=Normal, 4=Low
- `project` (string, optional) - Project name or ID
- `state` (string, optional) - State type, name, or ID
- `assignee` (string, optional) - User ID, name, email, or "me"
- `delegate` (string, optional) - Agent name, displayName, or ID
- `labels` (array of strings, optional) - Label names or IDs
- `dueDate` (string, optional) - ISO format date
- `parentId` (string, optional) - Parent issue ID for sub-issues
- `links` (array of objects, optional) - Each object needs `url` and `title`
**Example:**
```javascript
mcp__linear__create_issue({
title: "Fix auRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.