breakdown

Break a high-level task into subtasks with dependency tracking.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/squirrelsoft-dev/dev/breakdown
Clone the repo
git clone --depth 1 https://github.com/squirrelsoft-dev/dev

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 658 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found 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 $0.00011 $0.00658
Opus 5 $0.00005 $0.00329
Sonnet 5 $0.00002 $0.00132
Haiku 4.5 $0.00001 $0.00066

Measured today against content hash ef8974705a9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

breakdown 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 today.

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.

.claude/commands/breakdown.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Breakdown

Use the Task tool to spawn a Plan agent in plan mode to break down the following task: $ARGUMENTS

Important - This agent does not produce code or create any output other than generating the complete tasks file.

The agent should:

  1. Understand — Restate the task. Ask clarifying questions if the scope is ambiguous.
  2. Research — Read relevant files to understand the codebase, architecture, and existing patterns.
  3. Find relevant skills — Search for community skills that may help with the task or its subtasks. Run npx skills find <topic> for key technologies or patterns involved. If a relevant skill is found, run npx skills add <owner/repo@skill> to install it. Installed skills will be available to all agents during implementation.
  4. Decompose — Break the task into the smallest meaningful units of work.
  5. Identify dependencies — For each task, determine if it is:
    • Non-blocking — independent, can be done anytime
    • Blocked by — cannot start until specific other tasks complete (list them)
    • Blocking — other tasks cannot start until this one completes (list them)
  6. Group for parallelism — Organize tasks into groups that can be worked on simultaneously. Tasks in the same group have no dependencies on each other. Later groups depend on earlier groups.
  7. Save — Create the .claude/tasks/ directory if needed, then write the breakdown to .claude/tasks/$ARGUMENTS.md (kebab-case the filename).

Output Format

# Task Breakdown: <feature name>

> <one-sentence summary>

## Group 1 — <label>
_Tasks in this group can be done in parallel._

- [ ] **Task title** `[S/M/L]`
  <what to do and why>
  Files: `path/to/file`
  Blocking: <task titles this enables, or "None">

- [ ] **Task title** `[S/M/L]`
  <what to do and why>
  Files: `path/to/file`
  Non-blocking

## Group 2 — <label>
_Depends on: Group 1_

- [ ] **Task title** `[S/M/L]`
  <what to do and why>
  Files: `path/to/file`
  Blocked by: <task titles from earlier groups>
  Blocking: <task titles in later groups, or "None">

## Group N — <label>
_Depends on: Group N-1_

- [ ] **Task title** `[S/M/L]`
  <what to do and why>
  Files: `path/to/file`
  Blocked by: <task titles from earlier groups>

Read the full file on GitHub · 67 lines

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. today First seen · 67 lines · 11 tokens per session scan A ef8974705a9e

Subscribe to this mod's changes

breakdown is a command published in the GitHub repository squirrelsoft-dev/dev (14 stars, last pushed 17d ago), licensed MIT. It adds 11 tokens to every session and 658 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.