spec-task-management

A guide for turning a specification—such as a product requirements document or technical design—into a structured list of coding tasks. The tasks are written so coding agents can work on them independently and verify the results.

In plain words
What is it for?
Use it to analyze specifications, break down product requirements, create implementation tasks, and organize work that can be done in parallel.
Why use it?
It removes the need to turn broad requirements into smaller work items by hand. It also helps reveal unstated technical needs, constraints, error handling, and what is outside the project scope.

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

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,819 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 $0.00074 $0.01819
Opus 5 $0.00037 $0.00910
Sonnet 5 $0.00015 $0.00364
Haiku 4.5 $0.00007 $0.00182

Measured 2d ago against content hash 0ec4c108e7bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-task-management 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 2d 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.

plugins/task-manager/skills/spec-task-management/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Task Management

Transform specification documents (PRDs, Technical Specifications, Design Documents) into structured task lists that AI coding agents can execute independently or in parallel.

Core Workflow

1. Document Analysis

Parse the specification document to extract:

  • Explicit requirements: Stated features, functionality, acceptance criteria
  • Implicit requirements: Technical considerations, infrastructure needs, error handling
  • Constraints: Technology choices, performance requirements, compatibility needs
  • Scope boundaries: What is and isn't included in the specification

Read the source document thoroughly. Identify section headings, numbered requirements, user stories, acceptance criteria, and technical specifications. Note any cross-references between sections.

2. Task Decomposition

Break requirements into atomic tasks with these characteristics:

Characteristic Description
Single responsibility Each task addresses one specific piece of functionality
Independence Tasks can be worked on by different agents without coordination
Clear boundaries Well-defined start and end conditions
Testable Verifiable completion criteria exist

Decomposition process:

  1. Identify each distinct requirement in the specification
  2. Determine if the requirement is atomic or needs splitting
  3. Create task entries with unique IDs (TASK-001, TASK-002, etc.)
  4. Ensure each task maps to specific specification sections

3. Dependency Mapping

Identify three types of dependencies between tasks:

  • Hard dependencies: Task B cannot start until Task A completes
  • Soft dependencies: Task B benefits from Task A being complete but can proceed
  • Resource dependencies: Tasks share files, modules, or services

Populate dependencies.hard and dependencies.soft arrays. Calculate blocked_by (incomplete hard dependencies) and blocks (tasks depending on this one).

For detailed dependency patterns, consult references/dependency-patterns.md.

Read the full file on GitHub · 231 lines

Files

What ships with it

3 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. 2d ago First seen · 231 lines · 74 tokens per session scan A 0ec4c108e7bd

Subscribe to this mod's changes

spec-task-management is a skill published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 74 tokens to every session and 1,819 once invoked, about $0.0004 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.