task-generation

A task-generation guide for turning a Product Requirements Document (PRD) into small, checkable Claude Code tasks.

In plain words
What is it for?
Use it to break features into implementation layers, define acceptance criteria, estimate task size, and record dependencies and PRD references.
Why use it?
It provides a consistent way to split requirements, connect dependent work, and keep each task linked to its source requirements.

Skill for Claude CodeCodex

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 skills/sequenzia/claude-plugins/task-generation
Any agent
npx skills add sequenzia/claude-plugins --skill task-generation
Clone the repo
git clone --depth 1 https://github.com/sequenzia/claude-plugins

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,225 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 $0.00033 $0.01225
Opus 5 $0.00016 $0.00613
Sonnet 5 $0.00007 $0.00245
Haiku 4.5 $0.00003 $0.00122

Measured yesterday against content hash d47ced4fe228, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-generation 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 yesterday.

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.

plugins/prd-tools/skills/task-generation/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Generation Skill

This skill provides structured knowledge for transforming Product Requirements Documents into Claude Code native Tasks with proper dependencies, metadata, and acceptance criteria.

Core Principles

1. Atomic Task Decomposition

Tasks should be:

  • Single Responsibility: Each task accomplishes one specific outcome
  • Independent: Minimal coupling with other tasks where possible
  • Verifiable: Clear completion criteria that can be objectively assessed
  • Estimable: Complexity can be reasonably assessed (XS/S/M/L/XL)

2. Layered Architecture Pattern

Decompose features following natural implementation layers:

Data Model → API/Service → Business Logic → UI/Frontend → Tests

This pattern ensures:

  • Dependencies flow in one direction
  • Each layer can be implemented and tested independently
  • Integration points are well-defined

3. PRD-to-Task Traceability

Every task should trace back to the source PRD:

  • Reference specific section numbers
  • Quote relevant user stories
  • Link acceptance criteria to PRD requirements

Task Schema

Each task created via TaskCreate follows this structure:

TaskCreate:
  subject: "Create User data model"                    # Imperative mood
  description: |
    Define the User data model based on PRD section 7.3.

    Fields:
    - id: UUID (primary key)
    - email: string (unique, required)
    - passwordHash: string (required)
    - createdAt: timestamp

    Acceptance Criteria:
    - [ ] Schema defined with all required fields
    - [ ] Indexes created for email lookup
    - [ ] Migration script created

    Source: specs/PRD-Auth.md Section 7.3
  activeForm: "Creating User data model"              # Present continuous
  metadata:
    priority: critical                                # From PRD P0-P3
    complexity: S                                     # XS/S/M/L/XL
    source_section: "7.3 Data Models"                 # PRD section reference
    prd_path: "specs/PRD-Auth.md"                     # Source PRD
    feature_name: "User Authentication"               # Parent feature
    task_uid: "specs/PRD-Auth.md:user-auth:model:001" # Unique ID for merge

Read the full file on GitHub · 151 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 151 lines · 33 tokens per session scan A d47ced4fe228

Subscribe to this mod's changes

task-generation is a skill published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 1,225 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens