cli-usage
# MCP-Tasks CLI Reference
What this skill does
# MCP-Tasks CLI Reference
This skill provides comprehensive CLI reference for the mcp-tasks command-line tool.
## Overview
The mcp-tasks CLI provides task management via command-line interface for scripting and automation. For agent workflows, use the MCP server instead.
## Installation
The CLI is distributed as a pre-built Babashka uberscript in this plugin:
```bash
plugins/mcp-tasks-cli/bin/mcp-tasks
```
Add to PATH or invoke directly:
```bash
# Add to PATH (example)
export PATH="$PATH:/path/to/plugins/mcp-tasks-cli/bin"
# Or invoke directly
/path/to/plugins/mcp-tasks-cli/bin/mcp-tasks --help
```
## Configuration Discovery
No `--config-path` required. The CLI automatically searches for `.mcp-tasks.edn`:
- Starts from current directory
- Traverses up directory tree
- Stops at filesystem root or when found
Example:
```bash
# Project structure:
# /project/.mcp-tasks.edn
# /project/src/
# Works from any subdirectory:
cd /project/src
mcp-tasks list # Finds /project/.mcp-tasks.edn
```
## Commands
| Command | Purpose | Required Args | Key Options |
|---------|---------|---------------|-------------|
| `list` | Query tasks with filters | None | `--status`, `--category`, `--type`, `--parent-id`, `--task-id`, `--title-pattern`, `--limit`, `--unique` |
| `show` | Display single task | `--task-id` | `--format` |
| `add` | Create new task | `--category`, `--title` | `--description`, `--type`, `--parent-id`, `--prepend` |
| `complete` | Mark task complete | `--task-id` or `--title` | `--category`, `--completion-comment` |
| `update` | Update task fields | `--task-id` | `--title`, `--description`, `--design`, `--status`, `--category`, `--type`, `--parent-id`, `--meta`, `--relations` |
| `delete` | Delete task | `--task-id` or `--title-pattern` | None |
## Global Options
| Option | Values | Default | Description |
|--------|--------|---------|-------------|
| `--format` | `edn`, `json`, `human` | `edn` | Output format |
| `--help` | - | - | Show help message |
## Command Details
### list
Query tasks with optional filters.
**Usage:**
```bash
mcp-tasks list [options]
```
**Options:**
| Flag | Alias | Type | Description |
|------|-------|------|-------------|
| `--status` | `-s` | keyword | Filter by status: `open`, `closed`, `in-progress`, `blocked`, `any` |
| `--category` | `-c` | string | Filter by category name |
| `--type` | `-t` | keyword | Filter by type: `task`, `bug`, `feature`, `story`, `chore` |
| `--parent-id` | `-p` | integer | Filter by parent task ID |
| `--task-id` | - | integer | Filter by specific task ID |
| `--title-pattern` | `--title` | string | Filter by title pattern (regex or substring) |
| `--limit` | - | integer | Maximum tasks to return (default: 30) |
| `--unique` | - | boolean | Enforce 0 or 1 match (error if >1) |
| `--format` | - | keyword | Output format: `edn`, `json`, `human` |
**Examples:**
```bash
# List open tasks in human format
mcp-tasks list --status open --format human
# List all tasks for a category
mcp-tasks list --status any --category simple
# List story child tasks
mcp-tasks list --parent-id 31 --status open
```
### show
Display a single task by ID.
**Usage:**
```bash
mcp-tasks show --task-id <id> [options]
```
**Options:**
| Flag | Alias | Type | Required | Description |
|------|-------|------|----------|-------------|
| `--task-id` | `--id` | integer | Yes | Task ID to display |
| `--format` | - | keyword | No | Output format: `edn`, `json`, `human` |
**Examples:**
```bash
# Show task in EDN format
mcp-tasks show --task-id 42
# Show task in human-readable format
mcp-tasks show --id 42 --format human
```
### add
Create a new task.
**Usage:**
```bash
mcp-tasks add --category <name> --title <title> [options]
```
**Options:**
| Flag | Alias | Type | Required | Description |
|------|-------|------|----------|-------------|
| `--category` | `-c` | string | Yes | Task category (e.g., `simple`, `medium`, `large`) |
| `--title` | `-t` | string | Yes | Task title |
| `--description` | `-d` | string | No | Task description |
| `--type` | - | keyword | No | Task type (default: `task`). Options: `task`, `bug`, `feature`, `story`, `chore` |
| `--parent-id` | `-p` | integer | No | Parent task ID (for child tasks) |
| `--prepend` | - | boolean | No | Add task at beginning instead of end |
| `--format` | - | keyword | No | Output format: `edn`, `json`, `human` |
**Examples:**
```bash
# Create simple task
mcp-tasks add --category simple --title "Fix parser bug"
# Create task with description
mcp-tasks add -c medium -t "Add auth" -d "Implement JWT auth"
# Create child task
mcp-tasks add --category simple --title "Subtask" --parent-id 31
```
### complete
Mark a task as complete and move to archive.
**Usage:**
```bash
mcp-tasks complete (--task-id <id> | --title <pattern>) [options]
```
**Options:**
| Flag | Alias | Type | Required | Description |
|------|-------|------|----------|-------------|
| `--task-id` | `--id` | integer | * | Task ID to complete |
| `--title` | `-t` | string | * | Task title pattern (alternative to task-id) |
| `--category` | `-c` | string | No | Task category (for verification) |
| `--completion-comment` | `--comment` | string | No | Optional completion comment |
| `--format` | - | keyword | No | Output format: `edn`, `json`, `human` |
\* At least one of `--task-id` or `--title` required.
**Examples:**
```bash
# Complete by ID
mcp-tasks complete --task-id 42
# Complete by title with comment
mcp-tasks complete --title "Fix bug" --comment "Fixed via PR #123"
# Complete with category verification
mcp-tasks complete --id 42 --category simple
```
### update
Update task fields.
**Usage:**
```bash
mcp-tasks update --task-id <id> [options]
```
**Options:**
| Flag | Alias | Type | Required | Description |
|------|-------|------|----------|-------------|
| `--task-id` | `--id` | integer | Yes | Task ID to update |
| `--title` | `-t` | string | No | New task title |
| `--description` | `-d` | string | No | New task description |
| `--design` | - | string | No | New task design notes |
| `--status` | `-s` | keyword | No | New status: `open`, `closed`, `in-progress`, `blocked` |
| `--category` | `-c` | string | No | New task category |
| `--type` | - | keyword | No | New task type: `task`, `bug`, `feature`, `story`, `chore` |
| `--parent-id` | `-p` | integer/string | No | New parent task ID (pass `"null"` to remove) |
| `--meta` | - | JSON string | No | New metadata as JSON object (replaces entire map) |
| `--relations` | - | JSON string | No | New relations as JSON array (replaces entire vector) |
| `--format` | - | keyword | No | Output format: `edn`, `json`, `human` |
**Examples:**
```bash
# Update status
mcp-tasks update --task-id 42 --status in-progress
# Update title and description
mcp-tasks update --id 42 --title "New title" --description "New desc"
# Update metadata
mcp-tasks update --task-id 42 --meta '{"priority":"high"}'
# Remove parent relationship
mcp-tasks update --task-id 42 --parent-id "null"
```
### delete
Delete a task from tasks.ednl (archives to complete.ednl with `:status :deleted`).
**Usage:**
```bash
mcp-tasks delete (--task-id <id> | --title-pattern <pattern>) [options]
```
**Options:**
| Flag | Alias | Type | Required | Description |
|------|-------|------|----------|-------------|
| `--task-id` | `--id` | integer | * | Task ID to delete |
| `--title-pattern` | `--title` | string | * | Title pattern to match (alternative to task-id) |
| `--format` | - | keyword | No | Output format: `edn`, `json`, `human` |
\* At least one of `--task-id` or `--title-pattern` required.
**Constraints:**
- Cannot delete tasks with non-closed children (must complete or delete children first)
**Examples:**
```bash
# Delete by ID
mcp-tasks delete --task-id 42
# Delete by title pattern
mcp-tasks delete --title-pattern "old-task"
# Delete with human-readable output
mcp-tasks delete --id 42 --format human
```
## Output Formats
### EDN (Default)
Clojure EDRelated 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.