start-issue

start-issue is a command for Claude Code from dapi/claude-code-marketplace. It costs 16 tokens per session (1,894 once invoked), scanned A, original, MIT.

A workflow for starting work on a GitHub issue by creating a separate Git worktree and a correctly named branch. A worktree is another working folder connected to the same Git repository.

In plain words
What is it for?
It helps read an issue, determine whether the work is a feature, fix, or maintenance task, create the matching branch, and check whether work is already in progress.
Why use it?
It prepares an isolated workspace for one task and reduces confusion between branches or unfinished changes. It also uses issue labels and descriptions to choose a branch type and name.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Part of the github-workflow plugin — 3 skills, 1 command shipped together

Good fit It helps read an issue, determine whether the work is a feature, fix, or maintenance task, create the matching branch, and check whether work is already in progress.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dapi/claude-code-marketplace/start-issue
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.

Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace

Made for: Claude Code.

Or install github-workflow, the plugin that ships this one along with the rest of its 3 skills, 1 command.

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 start-issue

README.md
[![agentmods](https://agentmods.dev/badge/commands/dapi/claude-code-marketplace/start-issue/github.svg)](https://agentmods.dev/commands/dapi/claude-code-marketplace/start-issue)
Your own site
<a href="https://agentmods.dev/commands/dapi/claude-code-marketplace/start-issue"><img src="https://agentmods.dev/badge/commands/dapi/claude-code-marketplace/start-issue/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.

agentmods 80×15 button for start-issue

Your own site · 80×15
<a href="https://agentmods.dev/commands/dapi/claude-code-marketplace/start-issue"><img src="https://agentmods.dev/badge/commands/dapi/claude-code-marketplace/start-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,894 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.01894
Opus 5.5 $0.00006 $0.00758
Sonnet 5.5 $0.00003 $0.00379
Haiku 4.5 $0.00002 $0.00189

Measured 1mo ago against content hash 0aee92efb7ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

start-issue 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 1mo 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-workflow/commands/start-issue.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start Issue

Начни работу над GitHub issue.

Входные данные

  • ISSUE_URL: $ARGUMENTS (ссылка на GitHub issue)

Формат имени ветки

<тип>/<номер-задачи>-<описание>

Типы веток

Тип Когда использовать
feature Новая функциональность
fix Исправление бага
chore Рефакторинг, зависимости, CI, документация

Определение типа

  1. По labels issue:

    • bug, fix → fix
    • enhancement, feature → feature
    • chore, refactor, docs, ci, dependencies → chore
  2. Если labels нет — определи по заголовку/описанию issue

Формирование описания (slug)

  • Lowercase
  • Пробелы и спецсимволы → дефисы
  • Множественные дефисы → один дефис
  • Максимум 50 символов
  • Убрать дефис в конце

Примеры:

  • feature/123-add-user-authentication
  • fix/456-null-pointer-in-parser
  • chore/789-update-eslint-config

Шаги выполнения

  1. Прочитай GitHub issue по ISSUE_URL:

    • Номер issue
    • Заголовок
    • Labels (для определения типа)
    • Описание (если нужно для понимания типа)
  2. Проверь лейбл progress:

    Если issue уже имеет лейбл progress:

    • Сообщи пользователю: ⚠️ Issue уже имеет лейбл 'progress' — возможно, над ней уже ведётся работа.
    • Спроси: продолжить или отменить?
    • Если пользователь отменяет — заверши выполнение команды
  3. Сформируй имя ветки по шаблону <тип>/<номер>-<slug>

    Slug формируй bash-командой (гарантирует отсутствие trailing hyphen):

    SLUG=$(echo "<title>" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g; s/-\{2,\}/-/g; s/^-//; s/-$//' | cut -c1-50 | sed 's/-$//')
    BRANCH_NAME="<тип>/<номер>-${SLUG}"
    
  4. Создай git worktree от текущей ветки:

    Сформируй переменные:

    • BRANCH_NAME — имя ветки из шага 3 (например fix/123-some-bug)
    • WORKTREE_NAME — имя директории: замени / на - (например fix-123-some-bug)
    • WORKTREE_PATH — полный путь: ~/worktrees/<WORKTREE_NAME>

Read the full file on GitHub · 229 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. 1mo ago First seen · 229 lines · 16 tokens per session scan A 0aee92efb7ff

Subscribe to this mod's changes

start-issue is a command published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,894 once invoked, about $0.0001 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 2026-08-30.