A task-decomposition skill that turns an approved implementation plan into small, ordered tasks with dependencies, estimates, and acceptance-criteria links.

Use it to break a planned feature into T### tasks, mark tasks that can run in parallel, and identify tasks needing user sign-off.

It prevents work from being started without a clear source plan and makes the implementation sequence easier to follow and check.

How zexion7873/copilot-setting configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to zexion7873/copilot-setting. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zexion7873/copilot-setting/main/.github/skills/tasks/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/zexion7873/copilot-setting

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zexion7873/copilot-setting/tasks/github.svg)](https://agentmods.dev/skills/zexion7873/copilot-setting/tasks)

Your own site

<a href="https://agentmods.dev/skills/zexion7873/copilot-setting/tasks"><img src="https://agentmods.dev/badge/skills/zexion7873/copilot-setting/tasks/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zexion7873/copilot-setting/tasks"><img src="https://agentmods.dev/badge/skills/zexion7873/copilot-setting/tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 761 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00076	$0.00761
Opus 5.5	$0.00030	$0.00304
Sonnet 5.5	$0.00015	$0.00152
Haiku 4.5	$0.00008	$0.00076

Measured 2mo ago against content hash 0719e8aca5f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tasks 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 2mo 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.

.github/skills/tasks/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tasks — Workflow

Atomic task decomposition from an approved plan.

Phase 1 — Parse Source

Locate the approved plan at docs/plans/<feature>/plan.md (the plan skill writes there, one folder per feature/change). If the user named a feature, read that folder's plan.md. If exactly one plan folder exists, use it. If none exists or the source is ambiguous, stop and ask — do not invent a task list from scratch; redirect to the plan skill when no plan exists yet.

From the plan, extract: phases/goals, file list, dependencies, constraints, and Acceptance Criteria (AC-NNN). Record the plan's path in the source: field of the output.

Phase 2 — Decompose

Break each phase into atomic tasks. Each task must be:

One action: a single file change or closely related set
Verifiable: clear done-when condition
Estimated: S (< 30 min) / M (30–120 min) / L (> 2 hours)

Phase 3 — Order by Dependency

Build dependency graph (T001 must complete before T002)
Mark parallel-safe tasks with [P]
Mark tasks requiring user sign-off with [US]
Number sequentially: T001, T002, ...

Phase 4 — Validate

Every task maps to ≥1 requirement
Every requirement maps to ≥1 task
Every plan Acceptance Criterion (AC-NNN) is covered by ≥1 task
No circular dependencies
Size estimates on every task

Output Template

Write the task breakdown to tasks.md in the same feature folder as the source plan (docs/plans/<feature>/tasks.md), so the source: link resolves to the sibling ./plan.md.

---
source: ./plan.md
date: <YYYY-MM-DD>
---

# Task Breakdown

## Tasks

| ID | Task | Size | Depends On | Markers | Done When |
|---|---|---|---|---|---|
| T001 | <action on specific file/module> | S/M/L | — | | <verifiable condition> |
| T002 | ... | S | T001 | | ... |
| T003 | ... | M | T001 | [P] | ... |
| T004 | ... | S | T002, T003 | [US] | ... |

### Markers

- `[P]` — parallel-safe at same dependency level
- `[US]` — requires user sign-off

## Dependency Graph

T001 → T002 → T004
T001 → T003 ──┘

## Coverage Matrix

Map every plan requirement AND Acceptance Criterion to the tasks that satisfy it.

| Plan item | Tasks |
|---|---|
| REQ-001 | T001, T002 |
| AC-001 | T001, T002 |
| AC-002 | T003 |

Read the full file on GitHub · 84 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.

2mo ago First seen · 84 lines · 76 tokens per session scan A 0719e8aca5f1

Subscribe to this mod's changes

tasks is a skill published in the GitHub repository zexion7873/copilot-setting (1 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 761 once invoked, about $0.0003 per session on Opus 5.5. 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.

Java Planning Project management ai-agents copilot-instructions github-copilot hibernate prompt-engineering

tasks next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
taskszexion7873/copilot-setting	Skill	1	1mo ago	MIT	A	76	Claude Code, Codex
jira-cliCode-and-Sorts/awesome-copilot-agents	Skill	593	6mo ago	CC0-1.0	A	60	Claude Code, Codex
azure-pricesCode-and-Sorts/awesome-copilot-agents	Skill	593	6mo ago	CC0-1.0	A	90	Claude Code, Codex
calculatorCode-and-Sorts/awesome-copilot-agents	Skill	593	6mo ago	CC0-1.0	A	50	Claude Code, Codex
az-cliCode-and-Sorts/awesome-copilot-agents	Skill	593	6mo ago	CC0-1.0	A	79	Claude Code, Codex
plan-tasksavedpixel/ai-agent-rules-generator	Skill	8	6mo ago	MIT	A	45	Claude Code, Codex
commitsavedpixel/ai-agent-rules-generator	Skill	8	6mo ago	MIT	A	40	Claude Code, Codex

copilot-setting: Skill for Claude Code