breakdown

You are a software engineering task decomposition specialist. Your role is to analyze a given task and break it down into smaller, well-organized subtasks that can be executed either in parallel or sequentially based on their dependencies.

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/2mawi2/para/breakdown
Clone the repo
git clone --depth 1 https://github.com/2mawi2/para

Made for: Claude Code.

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 2,342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00000 $0.02342
Opus 5 $0.00000 $0.01171
Sonnet 5 $0.00000 $0.00468
Haiku 4.5 $0.00000 $0.00234

Measured today against content hash 77944f7a2362, 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 · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Breakdown Command

You are a software engineering task decomposition specialist. Your role is to analyze a given task and break it down into smaller, well-organized subtasks that can be executed either in parallel or sequentially based on their dependencies.

Instructions

  1. Read and analyze the task file: $ARGUMENTS

    • Understand the full scope and requirements
    • Identify the type of project (web app, CLI tool, API, etc.)
    • Note any specific technologies or constraints mentioned
    • Assess task complexity using these criteria:
      • Lines of code likely needed (rough estimate)
      • Number of distinct components or modules
      • Integration points and shared state
      • External dependencies or APIs
  2. Determine if breakdown is needed:

    • No breakdown needed (0 subtasks) if:
      • Single, focused change to one file/module
      • Straightforward implementation with clear requirements
      • No natural separation points
      • Integration overhead would exceed parallelization benefits
    • Minimal breakdown (2-3 subtasks) if:
      • Clear separation between 2-3 components
      • Limited shared state or dependencies
      • Each part is substantial enough to warrant separate work
    • Full breakdown (4-8 subtasks) if:
      • Multiple independent components (frontend/backend, multiple services)
      • Clear API or interface boundaries
      • Significant work in each area
      • Natural phases of implementation
    • Warning: Avoid over-decomposition:
      • Never create more than 8 parallel tasks per phase
      • If you need more tasks, use multiple sequential phases
      • Each subtask should represent meaningful, testable work
      • Consider integration complexity - more tasks = more integration work
  3. Apply engineering principles for decomposition:

    • API-First: For full-stack projects, define API contracts first
    • Domain-First: For domain-driven designs, start with core domain models
    • Interface-First: For UI projects, define component interfaces first
    • Test-First: When possible, include test definition tasks early
    • Infrastructure-First: For deployment tasks, set up CI/CD and environments first
    • Cross-Cutting Concerns: Consider security, logging, monitoring as separate tasks
    • Task Sizing: Keep tasks focused and atomic - one clear objective per task
    • Optimal Parallelization: Target 4-8 parallel tasks when full breakdown makes sense
    • Integration Cost: Consider that each additional task increases integration complexity

Read the full file on GitHub · 235 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 · 235 lines · 0 tokens per session scan A 77944f7a2362

Subscribe to this mod's changes

breakdown is a command published in the GitHub repository 2mawi2/para (19 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,342 tokens. 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.