kaji: Skill for Claude Code

.claude/skills/issue-design/SKILL.md

issue-design is a skill for Claude Code from apokamo/kaji. It costs 34 tokens per session (11,727 once invoked), scanned A, original, Apache-2.0.

A workflow step that turns a GitHub issue’s requirements into a design document in the project’s draft/design folder. It is intended for the period after work begins but before implementation.

In plain words
What is it for?
Designing a change in an existing issue workflow, provided a worktree—a separate working copy of the repository—already exists.
Why use it?
It gives the implementation a recorded design to follow and review instead of relying on informal decisions.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

This is apokamo/kaji's own configuration. It tells Claude Code how to work on kaji itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kaji configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is (参照: [`docs/dev/shared_skill_rules.md`](../../../docs/dev/shared_skill_rules.md) § auto close keyword 回避規約)。.

Reuse

Borrowing it

Nothing to install: this file belongs to apokamo/kaji. 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/apokamo/kaji/main/.claude/skills/issue-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/apokamo/kaji

Made for: Claude Code.

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 issue-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/apokamo/kaji/issue-design.svg)](https://agentmods.dev/skills/apokamo/kaji/issue-design)
Your own site
<a href="https://agentmods.dev/skills/apokamo/kaji/issue-design"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/issue-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,727 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 $0.00034 $0.11727
Opus 5 $0.00017 $0.05863
Sonnet 5 $0.00007 $0.02345
Haiku 4.5 $0.00003 $0.01173

Measured 7d ago against content hash 4b53072c0ca7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

issue-design 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 7d 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/skills/issue-design/SKILL.md · 726 lines

How it starts

The opening of the file, as written. The whole thing — 726 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Design

指定されたIssueに基づき、設計書(Markdown)を作成します。 設計書は draft/design/ に作成され、i-dev-final-check 時に Issue 本文へアーカイブされます。

いつ使うか

タイミング このスキルを使用
Issue着手後、実装前 ✅ 必須
worktreeが存在しない ❌ 先に /issue-start を実行

ワークフロー内の位置: create → start → design → review-design → implement → review-code → doc-check → i-dev-final-check → i-pr → close

入力

ハーネス経由(コンテキスト変数)

常に注入される変数:

変数 説明
issue_id str 正規化済み Issue ID(GitHub 数値または local ID)
issue_ref str 人間可読の Issue 参照(GitHub では #<issue_id>、local では bare ID)
step_id str 現在のステップ ID

手動実行(スラッシュコマンド)

$ARGUMENTS = <issue_id>

解決ルール

コンテキスト変数 issue_id が存在すればそちらを使用。 なければ $ARGUMENTS の第1引数を issue_id として使用。

issue_ref はハーネス経由ではプロンプトに自動注入される(prompt.py 側で provider 別に整形)。手動実行時は issue_id から導出する: GitHub 数値 ID なら #<issue_id>local-* 形式なら bare ID(# を付けない)。

前提知識の読み込み

以下のドキュメントを Read ツールで読み込んでから作業を開始すること。

共通(常に読み込む)

  1. 開発ワークフロー: docs/dev/development_workflow.md
  2. 重要判断チェックリスト: .claude/skills/_shared/critical-decision-checklist.md
  3. テスト規約: docs/dev/testing-convention.md
  4. コーディング規約: docs/reference/python/python-style.md
    • 必要に応じて docs/reference/python/naming-conventions.md / type-hints.md / docstring-style.md / error-handling.md / logging.md を追加読込

前提条件

  • /issue-start が実行済みであること
  • Issue本文にWorktree情報が記載されていること

設計書ルール

ルール 説明
What & Constraint 入力/出力と制約のみ
Minimal How 実装詳細は方針のみ。疑似コードはOK
Primary Sources 一次情報(公式ドキュメント等)のURL/パスを必ず記載
API仕様 公式リンク参照(コピペ禁止)
Test Strategy ID羅列ではなく検証観点を言語化
Decision Provenance 人間決定の出典、AI の仮定、設計で行った詳細化を分離

本フェーズは重要方針を新たに決める場ではなく、決定済み方針を実装可能な粒度へ 詳細化する場である。詳細化と未決事項の境界は _shared/critical-decision-checklist.md の可逆性基準で判定する。

一次情報のアクセス可能性ルール

重要: レビュワー(agent)がアクセスできない一次情報は使用できません。

Read the full file on GitHub · 726 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. 7d ago First seen · 726 lines · 34 tokens per session scan A 4b53072c0ca7

Subscribe to this mod's changes

issue-design is a skill published in the GitHub repository apokamo/kaji (12 stars, last pushed 6d ago), licensed Apache-2.0. It adds 34 tokens to every session and 11,727 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

software-design-lifecycle-tech-detailed-methodology

Use when an architect must run the detailed-design portion of technical design, preserve the full lifecycle-stage doctrine for detailed design, and define the concrete runtime, project, flow, data, interface, non-functional, security, recovery, hardware, and implementation-plan surfaces needed for execution.

xiaohei-info/oh-my-multica · 65 tokens

software-design-lifecycle-solution-design-biz-arch-diagramming

A method for designing and reviewing a business-solution architecture: a middle-level view that connects confirmed business problems to a solution before technical implementation is designed.

xiaohei-info/oh-my-multica · 57 tokens

software-design-lifecycle-tech-overview-system-arch-diagramming

A guide for architects who draw or review system architecture diagrams during overview design. It explains subsystems, outside dependencies, communication links, and system boundaries without going into every technology detail.

xiaohei-info/oh-my-multica · 49 tokens

creative-claude-design

Design one-off HTML artifacts (landing, deck, prototype).

xiaohei-info/oh-my-multica · 18 tokens

diagram-drawio

Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, network topology, ML/DL model figures (Transformer/CNN/LSTM), mind maps, or any visualization. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that…

xiaohei-info/oh-my-multica · 120 tokens

software-development-norms

Use when writing, reviewing, or refactoring code in any language to apply industrial-grade development norms abstracted from the Alibaba Java Development Handbook. Covers naming, type safety, exceptions, logging, concurrency, databases, project structure, testing, and security with language-agnostic principles and…

xiaohei-info/oh-my-multica · 66 tokens