A command for checking that a development task is complete and updating its related records before committing the code. A commit is a saved set of changes in version control.

Use it after implementation and review to update TodoWrite, issue trackers, the project memory, and the task’s Git commit.

It reduces the chance of leaving unfinished checks, stale task records, or outdated project notes behind. It also provides a checklist for code quality and documentation.

finish-task — Command by rmartynenko

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/finish-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 658 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00658
Opus 5	$0.00000	$0.00329
Sonnet 5	$0.00000	$0.00132
Haiku 4.5	$0.00000	$0.00066

Measured 2d ago against content hash 4bc5809e19e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finish-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/finish-task.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Команда: Завершение задачи

Назначение

Корректное завершение задачи с обновлением всех артефактов.

Когда использовать

После успешного завершения задачи
После прохождения code review
Перед коммитом

Действия

1. Проверка завершённости

## Чек-лист завершения

### Код
- [ ] Все изменения внесены
- [ ] syntaxcheck пройден
- [ ] Code review пройден (для feature-development)

### Качество
- [ ] Код соответствует стандартам
- [ ] Нет TODO без номера задачи
- [ ] Нет закомментированного кода

### Документация
- [ ] Комментарии добавлены где нужно
- [ ] API документация обновлена (если применимо)

2. Обновление TodoWrite

Отметить задачу как completed:

TodoWrite:
- [completed] {ID}: {Описание}

3. Обновление трекера (если настроен)

# Yougile
$YOUGILE_CLI task move <task_id> --column-id <done_id>
$YOUGILE_CLI task complete <task_id>

# GitHub Issues
gh issue close <number> --comment "Выполнено в коммите {hash}"

4. Создание коммита

git add <файлы>
git commit -m "{type}({scope}): {описание}

{Подробное описание если нужно}

Refs: {ID}"

5. Обновление Memory Bank

activeContext.md

Убрать задачу из активных
Обновить текущий фокус

progress.md

Добавить запись:

## [YYYY-MM-DD] — {ID}: {Краткое описание}

### Что сделано
- {Пункт 1}
- {Пункт 2}

### Изменённые файлы
- {Файл 1}
- {Файл 2}

### Ключевые решения
- {Решение}: {Обоснование}

6. Удаление TASK.md (если был создан)

Или архивирование в .claude/archive/ если нужно сохранить.

7. Вывод результата

## Задача завершена

### ID
{ID}

### Описание
{Описание}

### Результат
{Краткое описание что сделано}

### Изменённые файлы
- {Файл 1}
- {Файл 2}

### Коммит
{hash} — {message}

---
Что дальше?

Пример вызова

Завершить задачу FEAT-123

или

/finish FEAT-123

Автоматическое завершение

Если задача была в TodoWrite и все шаги выполнены:

Задача выполнена, завершаю.

Read the full file on GitHub · 140 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.

2d ago First seen · 140 lines · 0 tokens per session scan A 4bc5809e19e7

Subscribe to this mod's changes

finish-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 658 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.

Code review Memory and context Project management

finish-task