create-issue

create-issue is a skill for Claude Code, Codex from MH4GF/claude-code. It costs 111 tokens per session (4,132 once invoked), scanned A, original, MIT.

A Japanese-language workflow for turning a short idea into a well-defined issue, or task record, for a software project.

In plain words
What is it for?
Use it when you want to refine a one-line request through questions and options, then create an issue that another automated worker can implement.
Why use it?
It reduces guesswork by clarifying the desired result, reasons, completion conditions, project context, and possible approaches before the issue is created.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Good fit Use it when you want to refine a one-line request through questions and options, then create an issue that another automated worker can implement.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mh4gf/claude-code/create-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.

Any agent
npx skills add MH4GF/claude-code --skill create-issue
Clone the repo
git clone --depth 1 https://github.com/MH4GF/claude-code

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.

agentmods badge for create-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/mh4gf/claude-code/create-issue/github.svg)](https://agentmods.dev/skills/mh4gf/claude-code/create-issue)
Your own site
<a href="https://agentmods.dev/skills/mh4gf/claude-code/create-issue"><img src="https://agentmods.dev/badge/skills/mh4gf/claude-code/create-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 create-issue

Your own site · 80×15
<a href="https://agentmods.dev/skills/mh4gf/claude-code/create-issue"><img src="https://agentmods.dev/badge/skills/mh4gf/claude-code/create-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,132 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 $0.00111 $0.04132
Opus 5.5 $0.00044 $0.01653
Sonnet 5.5 $0.00022 $0.00826
Haiku 4.5 $0.00011 $0.00413

Measured 1mo ago against content hash e40a7a251b7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-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.

user-scope/skills/create-issue/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

create-issue

ユーザーの一行の意図を、grilling で固めてから issue として起票する skill。issue body は grilling で確定した内容から直接組み立てる。起票先と書き込み手段は実行時に解決する (「起票先を解決する」節)。

Symphony 系の運用へ乗せる前提で、起票先は Symphony の 1 系統と 1 対 1 に対応する。Symphony が次の poll で拾うことを期待する。

なぜ grilling を必須にするか

simple に見える issue ほど、未検証の前提が無駄な実装を生む。issue の Outcome / Why / 完了条件を曖昧なまま起票すると、Symphony が拾った後の実装ワーカーは推測で動く羽目になる。

grilling は設計判断を design tree として展開し、frontier (前提が揃った決定) が空になるまで質問ラウンドを回す。全ての分岐を訪れて暗黙の仮定が残っていない状態が、そのまま issue body の素材になる。

手順

1. grilling で意図を固める

Skill ツール経由で grilling を起動し、ユーザー の一行の意図を渡す。grilling は次を実施する。

  • 意図を design tree へ展開し、前提が揃った決定の集合 (frontier) を洗い出す
  • frontier の質問を 1 ラウンドにまとめ、番号付き・推奨案付きで提示してユーザー の回答を待つ
  • 回答で tree を組み直し、frontier が空になるまでラウンドを繰り返す
  • 環境から取れる事実 (関連ファイル / 先行事例 / 既存 issue) は sub-agent で自分で調べる。ユーザー へ聞くのは決定だけ

注意点:

  • frontier が空になり、shared understanding に達したとユーザー が確認するまでステップ 2 へ進まない。grilling は確認前に動くことを禁じている
  • 議論結果を design doc として別ファイルへ書き出さない。直接 issue description へ統合する

理由: bg session の作業 workspace は origin/main の depth=1 clone なので、scraps/open/ 等へ書いた新規ファイルを bg session 側から読めない。issue body だけが情報源になる前提で組む。

2. 起票先を解決する

起票先は Symphony の 1 系統 = 対象 repo。まず repo を決め、その repo の tracker を決める。

  1. 会話の文脈から対象 repo が自明 (例: 「skills/X への変更」「daily note の cron が…」「unslop の rule 追加」) ならそれを採る。決められないなら AskUserQuestion で確定する
  2. 対象 repo のローカル clone があれば WORKFLOW.md frontmatter の tracker.kind を読む。works repo のみ agents/ai-native/WORKFLOW.md、それ以外は repo root
  3. clone が無い、または読み取れない場合は linear として扱う

以降、kind ごとに「Tracker 別操作」の手段を使う。

3. 重複を検索する

grilling で出てきたキーワード (1〜2 語) で既存 issue を検索する。検索は終端状態 (Done / Canceled) 以外をすべて対象にする。実装中や Human Review の issue と重なることがあり、状態を絞ると取りこぼす。

近い既存 issue が出た場合、新規作成せず該当の identifier と URL をユーザー へ報告して止まる。

4. description を組み立てる

grilling で確定した内容から、次の節構成へ落とす。

  • ## Outcome — 最終状態と価値を箇条書きで 2〜4 点。手順は書かない
  • ## Why — 起票の動機・前例との関係・設計の理由。bg session が edge case で判断するための背景情報
  • ## 参考 — 参照した関連ファイル、関連 issue (実在のみ)、外部 URL。意図にある外部参照を必ず含める
  • ## 完了条件 — 観測可能な状態 (コマンド出力、ファイル存在、tracker / GitHub の見え方) を箇条書き
  • ## スコープ外 — 含めない範囲を箇条書き

Read the full file on GitHub · 193 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 Changed e40a7a251b7a
  2. 1mo ago Changed · +11 lines 6e9963a44252
  3. 1mo ago Changed · +2 lines · -5 tokens per session 9ec26f8f41b5
  4. 2mo ago First seen · 180 lines · 116 tokens per session scan A 28b647635dfb

Subscribe to this mod's changes

create-issue is a skill published in the GitHub repository MH4GF/claude-code (2 stars, last pushed 5d ago), licensed MIT. It adds 111 tokens to every session and 4,132 once invoked, about $0.0004 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.