task-breakdown

A planning aid that turns an approved feature design into an ordered `tasks.md` file. It groups work into phases, records dependencies and rough complexity, marks tasks that can run in parallel, and pairs implementation with testing.

In plain words
What is it for?
Use it after a design is approved to prepare implementation tasks, identify independent work, and plan matching test tasks.
Why use it?
It makes a large change easier to execute in the right order and reduces the chance of missing dependent work or tests.

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/nickpolyder/np.copilot.config/task-breakdown
Any agent
npx skills add NickPolyder/NP.CoPilot.Config --skill task-breakdown
Clone the repo
git clone --depth 1 https://github.com/NickPolyder/NP.CoPilot.Config

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 985 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 $0.00032 $0.00985
Opus 5 $0.00016 $0.00492
Sonnet 5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00098

Measured 2d ago against content hash db49df8ae106, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-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 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.

skills/task-breakdown/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Intent (anchor): Convert an approved feature design into an ordered, dependency-aware tasks.md that implementation can execute safely. Always: read the design thoroughly; group work into phases; order by dependency; mark independent work as parallelizable; include paired test work. Never: implement code, silently redesign the feature, or skip dependencies.

Shared policy: Follow instructions/coordination.instructions.md for precedence, invocation, delegation, and handoffs. Apply instructions/workflow.instructions.md for proportional work and verification.

You are translating an approved design into executable work that can be implemented in dependency order.

Your goals are to:

  • Break down the design — turn design sections into concrete implementation and test tasks.
  • Sequence work safely — make dependencies explicit and order tasks within each phase.
  • Expose parallelism — mark independent tasks so multiple agents can work safely when appropriate.
  • Prepare implementation — produce tasks.md suitable for implementation-runner.

When to use this skill

Use this skill whenever:

  • A feature design has been approved and needs implementation tasks.
  • The user asks for a tasks.md, task list, work breakdown, estimates, or dependency ordering.
  • Implementation should be planned before code changes begin.
  • You need the third atomic step in the chain: codebase-researchfeature-design-doctask-breakdownimplementation-runner.

Do not use this skill for:

  • Codebase research — use codebase-research.
  • Writing or revising the feature design — use feature-design-doc.
  • Executing tasks or editing production code — use implementation-runner.
  • End-to-end orchestration — recommend prd-workflow.

Workflow

Break the design into implementable tasks.

  1. Read the design document thoroughly.

  2. Generate docs/features/{feature-name}/tasks.md with:

    • Phases — group tasks into logical phases (e.g., backend, frontend, integration).
    • Task format — each task has: ID, title, description, acceptance criteria, estimated complexity (S/M/L), dependencies.
    • Ordering — tasks within a phase are ordered by dependency. Independent tasks are marked as parallelizable.
    • Test tasks — every implementation task has a corresponding test task or tests are included in the task itself.

Read the full file on GitHub · 106 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. 2d ago First seen · 106 lines · 32 tokens per session scan A db49df8ae106

Subscribe to this mod's changes

task-breakdown is a skill published in the GitHub repository NickPolyder/NP.CoPilot.Config (2 stars, last pushed 7d ago), licensed MIT. It adds 32 tokens to every session and 985 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.