issue-fix-code

A review-response workflow for deciding whether to change code after a reviewer raises an issue, or to explain why the requested change is not technically needed.

In plain words
What is it for?
Use it after code review requests changes, or when responding to human review comments in an Issue-based development workflow.
Why use it?
It prevents review comments from being accepted blindly and separates valid fixes from disagreements that need a reasoned response.

Skill for Claude CodeCodex

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 skills/apokamo/kaji/issue-fix-code
Any agent
npx skills add apokamo/kaji --skill issue-fix-code
Clone the repo
git clone --depth 1 https://github.com/apokamo/kaji

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,063 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 $0.00038 $0.02063
Opus 5 $0.00019 $0.01032
Sonnet 5 $0.00008 $0.00413
Haiku 4.5 $0.00004 $0.00206

Measured 2d ago against content hash 03c64f5d5be4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-fix-code 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/skills/issue-fix-code/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Fix Code

実装に対するレビュー指摘事項に基づき、修正対応を行います。 指摘を盲目的に受け入れるのではなく、技術的な妥当性を検討し、必要な修正と反論を使い分けます。

いつ使うか

タイミング このスキルを使用
/issue-review-code で Changes Requested 後 ✅ 必須
人間からのレビューコメントへの対応 ✅ 使用可

ワークフロー内の位置: implement → review-code → (fix → verify) → 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

条件付きで注入される変数:

変数 条件 説明
previous_verdict str resume 指定ステップ 前ステップの verdict
cycle_count int サイクル内ステップのみ 現在のイテレーション番号
max_iterations int サイクル内ステップのみ サイクルの上限回数

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。

  1. 開発ワークフロー: docs/dev/development_workflow.md
  2. テスト規約: docs/dev/testing-convention.md
  3. Python スタイル: docs/reference/python/python-style.md(必要に応じて他の docs/reference/python/*.md も追加読込)

共通ルール

実行手順

Step 1: コンテキスト取得

  1. _shared/worktree-resolve.md の手順に従い、Worktree の絶対パスを取得。

  2. レビュー結果の取得:

    1. コンテキスト変数 previous_verdict が存在する場合はそれを確認(ハーネス経由)
    2. 存在しない場合は Issue コメントから最新のレビュー結果を取得(手動実行時)
  3. レビュー内容の取得:

    kaji issue view [issue_id] --comments
    

    最新の「コードレビュー結果」を取得。

  4. 現状把握: 指摘されている該当コード周辺を確認。

Step 2: 対応方針の検討

各指摘事項について、以下の基準で1つずつ検討してください。

  • A: 対応する (Agree)
    • 指摘が正しく、修正により品質・安全性が向上する場合。
    • 改善提案 (Should Fix) の場合:
      • メリットが明確な場合は積極的に採用
      • 大規模なリファクタリングを伴う場合や高リスクな場合は見送り可

Read the full file on GitHub · 206 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 · 206 lines · 38 tokens per session scan A 03c64f5d5be4

Subscribe to this mod's changes

issue-fix-code is a skill published in the GitHub repository apokamo/kaji (12 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,063 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.