new-task

A command for turning a new request into a clearly described task, classifying its type and priority, and choosing a suitable workflow. A workflow is the set of steps used to complete a task.

In plain words
What is it for?
Use it when a user reports new work, when you discover follow-up work, or when breaking a large task into smaller ones.
Why use it?
It prevents vague requests from entering development without a clear outcome or plan. It also helps decide whether the work is a small change or a larger feature.

Command for Claude Code

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 commands/rmartynenko/workflow-dev-1c-claude-code/new-task
Clone the repo
git clone --depth 1 https://github.com/rmartynenko/workflow-dev-1c-claude-code

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 990 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 $0.00000 $0.00990
Opus 5 $0.00000 $0.00495
Sonnet 5 $0.00000 $0.00198
Haiku 4.5 $0.00000 $0.00099

Measured 2d ago against content hash be33702208c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-task 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.

.claude/commands/new-task.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Команда: Регистрация новой задачи

Назначение

Формализация и регистрация новой задачи с выбором подходящего workflow.

Когда использовать

  • При получении новой задачи от пользователя
  • При выявлении необходимости доработки в процессе работы
  • При декомпозиции большой задачи на подзадачи

Действия

1. Сбор информации о задаче

Уточнить у пользователя (если не указано):

## Информация о задаче

### Описание
[Что нужно сделать?]

### Тип задачи
- [ ] Новая функциональность (FEAT)
- [ ] Исправление ошибки (FIX)
- [ ] Рефакторинг (REFACTOR)
- [ ] Документация (DOC)
- [ ] Метаданные (META)

### Приоритет
- [ ] Critical — блокирует работу
- [ ] High — важная функциональность
- [ ] Medium — стандартная задача
- [ ] Low — улучшения

### Ожидаемый результат
[Как понять, что задача выполнена?]

2. Классификация задачи

Критерий Значение Workflow
Затрагивает файлов 1-3 small-changes
Затрагивает файлов 4+ feature-development
Требует архитектуры Да feature-development
Требует исследования Да feature-development
Время выполнения < 1 час small-changes
Время выполнения > 1 час feature-development

3. Генерация ID задачи

Формат: {TYPE}-{NUMBER}

FEAT-1, FIX-23, REFACTOR-5, DOC-3, META-12

4. Создание записи в TodoWrite

TodoWrite:
1. [pending] {ID}: {Краткое описание}
   - Подзадача 1 (если есть)
   - Подзадача 2 (если есть)

5. Регистрация в трекере (если настроен)

# Yougile
$YOUGILE_CLI task create --title "{ID}: {Описание}" --column-id <todo_id>

# GitHub Issues
gh issue create --title "{ID}: {Описание}" --body "..."

6. Обновление activeContext.md

Добавить задачу в раздел "Активные задачи".

7. Создание TASK.md (для сложных задач)

Если выбран workflow feature-development:

# Задача: {ID} — {Название}

## Описание
[Подробное описание]

## Требования
- [ ] Требование 1
- [ ] Требование 2

## Контекст
- Связанные файлы: ...
- Зависимости: ...

## План реализации
[Заполняется на фазе 4 — Architecture Design]

## Прогресс
[Обновляется по ходу работы]

Read the full file on GitHub · 189 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 · 189 lines · 0 tokens per session scan A be33702208c4

Subscribe to this mod's changes

new-task is a command published in the GitHub repository rmartynenko/workflow-dev-1c-claude-code (40 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 990 tokens. 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.