autotask-mcp1: Command for Claude Code

.claude/commands/tm/expand/expand-task.md

expand-task is a command for Claude Code from haxos-anon/autotask-mcp1. It costs 0 tokens per session (248 once invoked), scanned A, a copy of expand-task, Apache-2.0.

A command that breaks a complex task into a short sequence of smaller tasks with implementation order and acceptance criteria.

In plain words
What is it for?
Use it to expand feature, bug-fix, or refactoring tasks into actionable subtasks and identify dependencies or the critical path.
Why use it?
It makes large work easier to estimate, assign, test, and track by separating setup, implementation, testing, and integration.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is haxos-anon/autotask-mcp1's own configuration. It tells Claude Code how to work on autotask-mcp1 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything autotask-mcp1 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to haxos-anon/autotask-mcp1. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/haxos-anon/autotask-mcp1/main/.claude/commands/tm/expand/expand-task.md
Clone the repo
git clone --depth 1 https://github.com/haxos-anon/autotask-mcp1

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for expand-task

README.md
[![agentmods](https://agentmods.dev/badge/commands/haxos-anon/autotask-mcp1/expand-task/github.svg)](https://agentmods.dev/commands/haxos-anon/autotask-mcp1/expand-task)
Your own site
<a href="https://agentmods.dev/commands/haxos-anon/autotask-mcp1/expand-task"><img src="https://agentmods.dev/badge/commands/haxos-anon/autotask-mcp1/expand-task/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for expand-task

Your own site · 80×15
<a href="https://agentmods.dev/commands/haxos-anon/autotask-mcp1/expand-task"><img src="https://agentmods.dev/badge/commands/haxos-anon/autotask-mcp1/expand-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 248 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00248
Opus 5 $0.00000 $0.00124
Sonnet 5 $0.00000 $0.00050
Haiku 4.5 $0.00000 $0.00025

Measured 8d ago against content hash b2940e636cff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

expand-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to expand-task — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/tm/expand/expand-task.md · 49 lines

What it actually says

Break down a complex task into subtasks.

Arguments: $ARGUMENTS (task ID)

Intelligent Task Expansion

Analyzes a task and creates detailed subtasks for better manageability.

Execution

task-master expand --id=$ARGUMENTS

Expansion Process

  1. Task Analysis

    • Review task complexity
    • Identify components
    • Detect technical challenges
    • Estimate time requirements
  2. Subtask Generation

    • Create 3-7 subtasks typically
    • Each subtask 1-4 hours
    • Logical implementation order
    • Clear acceptance criteria
  3. Smart Breakdown

    • Setup/configuration tasks
    • Core implementation
    • Testing components
    • Integration steps
    • Documentation updates

Enhanced Features

Based on task type:

  • Feature: Setup → Implement → Test → Integrate
  • Bug Fix: Reproduce → Diagnose → Fix → Verify
  • Refactor: Analyze → Plan → Refactor → Validate

Post-Expansion

After expansion:

  1. Show subtask hierarchy
  2. Update time estimates
  3. Suggest implementation order
  4. Highlight critical path
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 49 lines · 0 tokens per session scan A b2940e636cff

Subscribe to this mod's changes

expand-task is a command published in the GitHub repository haxos-anon/autotask-mcp1 (0 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 248 tokens. A static security scan graded it A with 0 findings. It is 100% identical to expand-task, differing in 0 lines, and is treated as a copy.