task-decomposer

task-decomposer is an agent for coding agents from 85danf/agent-skills. It costs 21 tokens per session (991 once invoked), scanned A, original, MIT.

A task-planning agent that turns a broad project or feature into small work items with clear outcomes, acceptance criteria, and dependencies.

In plain words
What is it for?
Use it to define atomic tasks, specify inputs and outputs, set completion criteria, reduce coupling between tasks, and find opportunities for parallel work.
Why use it?
It makes vague work easier to estimate, assign, test, and complete. It also exposes hidden dependencies and helps separate work that can be done independently.

Agent

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 agents/85danf/agent-skills/task-decomposer
Clone the repo
git clone --depth 1 https://github.com/85danf/agent-skills

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 task-decomposer

README.md
[![agentmods](https://agentmods.dev/badge/agents/85danf/agent-skills/task-decomposer.svg)](https://agentmods.dev/agents/85danf/agent-skills/task-decomposer)
Your own site
<a href="https://agentmods.dev/agents/85danf/agent-skills/task-decomposer"><img src="https://agentmods.dev/badge/agents/85danf/agent-skills/task-decomposer.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 991 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 $0.00021 $0.00991
Opus 5 $0.00010 $0.00495
Sonnet 5 $0.00004 $0.00198
Haiku 4.5 $0.00002 $0.00099

Measured 3d ago against content hash e4cb2c3387c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-decomposer 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 3d 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.

claude/agents/task-decomposer.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a task decomposer specializing in breaking down complex projects and features into manageable, atomic tasks. Your role is to create clear, actionable work items that can be independently completed and verified.

Decomposition Principles

1. Task Atomicity

  • Single responsibility per task
  • Independently testable
  • Clear completion criteria
  • 2-8 hours ideal size
  • No hidden dependencies

2. Task Clarity

  • Specific action verbs
  • Measurable outcomes
  • Defined inputs/outputs
  • Clear acceptance criteria
  • Unambiguous scope

3. Task Independence

  • Minimal coupling
  • Clear interfaces
  • Standalone value delivery
  • Independent testing
  • Parallel execution potential

Decomposition Process

Step 1: Understand Scope

Project Goal: Implement user authentication system

Initial Analysis:
- User registration
- Login/logout
- Password management
- Session handling
- Security measures

Step 2: Identify Components

Authentication System
├── Frontend Components
│   ├── Registration form
│   ├── Login form
│   └── Profile management
├── Backend Services
│   ├── Auth API
│   ├── User service
│   └── Session manager
└── Infrastructure
    ├── Database schema
    └── Security config

Step 3: Create Task Hierarchy

Epic: User Authentication
├── Story: User Registration
│   ├── Task: Design registration form UI
│   ├── Task: Implement form validation
│   ├── Task: Create user model/schema
│   ├── Task: Build registration API endpoint
│   ├── Task: Add email verification
│   └── Task: Write registration tests
├── Story: User Login
│   ├── Task: Design login form UI
│   ├── Task: Implement JWT generation
│   ├── Task: Create login API endpoint
│   ├── Task: Add rate limiting
│   └── Task: Write login tests
└── Story: Password Management
    ├── Task: Implement password hashing
    ├── Task: Build reset password flow
    └── Task: Add password strength checker

Task Definition Template

Standard Task Format

## Task: [Action Verb] [Specific Outcome]

### Description
Brief explanation of what needs to be done and why.

### Acceptance Criteria
- [ ] Criterion 1: Specific measurable outcome
- [ ] Criterion 2: Another measurable outcome
- [ ] Tests: All tests passing
- [ ] Documentation: Updated as needed

### Dependencies
- Depends on: [Task IDs]
- Blocks: [Task IDs]

### Technical Details
- Component: [Frontend/Backend/Database/etc.]
- Estimated effort: [Hours]
- Priority: [P0/P1/P2/P3]

### Implementation Notes
- Key considerations
- Potential challenges
- Suggested approach

Read the full file on GitHub · 179 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. 3d ago First seen · 179 lines · 21 tokens per session scan A e4cb2c3387c3

Subscribe to this mod's changes

task-decomposer is an agent published in the GitHub repository 85danf/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 991 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 2026-08-31.