breakdown

breakdown is a skill for Claude Code from pitimon/8-habit-ai-dev. It costs 45 tokens per session (2,403 once invoked), scanned A, original, MIT.

A task-planning step that splits a feature into small, focused units of work, with dependencies and priorities.

In plain words
What is it for?
Use it after requirements and architecture decisions, before writing implementation briefs or assigning work to coding agents.
Why use it?
It prevents one oversized coding request from mixing unrelated work and makes tasks easier to assign, verify, or run in parallel.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the 8-habit-ai-dev plugin — 24 skills, 2 agents, 1 hook shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pitimon/8-habit-ai-dev
Claude Code
/plugin install 8-habit-ai-dev

Made for: Claude Code.

Or install 8-habit-ai-dev, the plugin that ships this one along with the rest of its 24 skills, 2 agents, 1 hook.

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 breakdown

README.md
[![agentmods](https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/breakdown.svg)](https://agentmods.dev/skills/pitimon/8-habit-ai-dev/breakdown)
Your own site
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/breakdown"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/breakdown.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,403 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 5.1 $0.00045 $0.02403
Opus 5 $0.00023 $0.01202
Sonnet 5 $0.00009 $0.00481
Haiku 4.5 $0.00005 $0.00240

Measured 6d ago against content hash 8c8b6c10c79f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

plugin/skills/breakdown/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step 3: Plan (หั่นงานเป็นชิ้นเล็ก)

Habit: H3 — Put First Things First | Anti-pattern: One giant prompt that tries to do everything at once

Process

  1. Read the requirements/design: Load PRD or design decisions from previous steps.

  2. Decompose into atomic tasks (1 task = 1 focused unit of work):

    ## Task List
    1. [ ] [Task name] — [1-sentence description] | Files: [list] | Depends on: [none or #N]
    2. [ ] [Task name] — [1-sentence description] | Files: [list] | Depends on: [#1]
    ...
    

    For backlog-bound work, prefer vertical slices: each task should deliver a thin but complete path that can be verified or demonstrated on its own. Avoid horizontal layer tasks (schema only, API only, UI only) unless that layer is independently useful and has its own acceptance criteria. A good issue describes end-to-end behavior, not a list of implementation layers.

  3. Prioritize by importance, not interest:

    • Q1 (Urgent + Important): Blocking dependencies, security fixes
    • Q2 (Important, Not Urgent): Core features, tests, docs
    • Q3 (Urgent, Not Important): Nice-to-have polish
    • Q4 (Neither): Skip entirely
  4. Identify parallel work, delegation readiness, and classify orchestration: Tasks with no dependencies can run simultaneously. Also classify whether a task is ready for agent pickup or still needs human input.

    Type When Isolation
    sequential Output of A feeds input of B Run after dependency completes
    parallel-safe Tasks touch completely different files Same repo, concurrent execution
    parallel-worktree Tasks touch overlapping files or shared config Each agent gets isolated git worktree

    Produce an orchestration table for the task list:

Read the full file on GitHub · 161 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. 6d ago First seen · 161 lines · 45 tokens per session scan A 8c8b6c10c79f

Subscribe to this mod's changes

breakdown is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 2,403 once invoked, about $0.0002 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 2026-08-31.