spec-driven-task-decomposer

spec-driven-task-decomposer is a skill for Claude Code, Codex from lindoelio/spec-driven-steroids. It costs 61 tokens per session (2,380 once invoked), scanned A, original, MIT.

A planning skill that turns approved requirements and technical design into a structured tasks.md implementation plan. It breaks the work into small, ordered tasks linked back to specific requirements and design decisions.

In plain words
What is it for?
Use it after requirements and design are approved to prepare an executable task list, organize dependencies, and define testing coverage before final verification.
Why use it?
It prevents important work and acceptance tests from being missed when a larger software change is handed to an implementation agent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after requirements and design are approved to prepare an executable task list, organize dependencies, and define testing coverage before final verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lindoelio/spec-driven-steroids/spec-driven-task-decomposer
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.

Any agent
npx skills add lindoelio/spec-driven-steroids --skill spec-driven-task-decomposer
Clone the repo
git clone --depth 1 https://github.com/lindoelio/spec-driven-steroids

Made for: Claude Code, Codex.

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 spec-driven-task-decomposer

README.md
[![agentmods](https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/spec-driven-task-decomposer.svg)](https://agentmods.dev/skills/lindoelio/spec-driven-steroids/spec-driven-task-decomposer)
Your own site
<a href="https://agentmods.dev/skills/lindoelio/spec-driven-steroids/spec-driven-task-decomposer"><img src="https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/spec-driven-task-decomposer.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00061 $0.02380
Opus 5 $0.00030 $0.01190
Sonnet 5 $0.00012 $0.00476
Haiku 4.5 $0.00006 $0.00238

Measured 8d ago against content hash 0f89b3e1c686, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spec-driven-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 8d 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.

packages/cli/templates/universal/skills/spec-driven-task-decomposer/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Driven Task Decomposer Skill

Write a tasks.md document that turns approved requirements and design elements into an ordered, traceable implementation plan.

Your job is to produce a task artifact that:

  • is easy for an implementation agent to execute in sequence
  • keeps tasks small, concrete, and dependency-aware
  • preserves traceability from tasks to DES-* and REQ-*
  • includes explicit acceptance-criteria test coverage before final verification

Default path: read approved requirements and design, group work into practical phases, create atomic tasks, add acceptance-criteria testing, validate tasks.md, and return a short review-ready summary.

Read references/task-patterns.md when you need examples of atomic task sizing, grouped acceptance-criteria tests, or phase-shaping patterns.

Shared Protocol

Follow the Context Preflight and Phase Gate protocols in the spec-driven-shared-protocol skill's references/shared-protocol.md.

Per-Phase Todo List

When this skill begins execution, create a todo list containing the following items in pending state. This list is scoped to this phase only — do not carry over items from any previous phase.

  1. Read requirements.md and design.md
  2. Read project guidelines
  3. Retrieve contextual memory (workflow)
  4. Execute non-exhaustive Code Anatomy Discovery Targets and record evidence
  5. Define implementation phases
  6. Create atomic tasks
  7. Add per-phase test tasks
  8. Add acceptance criteria testing phase
  9. Add final checkpoint phase
  10. Save tasks.md
  11. Run CLI validation (sds validate tasks + sds validate spec)
  12. Complete quality bar self-check
  13. Fix validation failures (if any)
  14. Declare verdict

Progress Rules

  • Mark an item in_progress when starting that work step.
  • Mark an item completed only after the work step has been verified.
  • Do not mark an item completed until verification passes.
  • Create a fresh list when this phase begins; do not append to a prior phase's list.

Read the full file on GitHub · 246 lines

Files

What ships with it

1 file 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. 8d ago First seen · 246 lines · 61 tokens per session scan A 0f89b3e1c686

Subscribe to this mod's changes

spec-driven-task-decomposer is a skill published in the GitHub repository lindoelio/spec-driven-steroids (54 stars, last pushed 29d ago), licensed MIT. It adds 61 tokens to every session and 2,380 once invoked, about $0.0003 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 2026-08-30.