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.
curl -O https://raw.githubusercontent.com/apokamo/kaji/main/.claude/skills/issue-small-change-review/SKILL.mdgit clone --depth 1 https://github.com/apokamo/kajiWrote 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.
[](https://agentmods.dev/skills/apokamo/kaji/issue-small-change-review)<a href="https://agentmods.dev/skills/apokamo/kaji/issue-small-change-review"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/issue-small-change-review/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.
<a href="https://agentmods.dev/skills/apokamo/kaji/issue-small-change-review"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/issue-small-change-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00066 | $0.04448 |
| Opus 5.5 | $0.00026 | $0.01779 |
| Sonnet 5.5 | $0.00013 | $0.00890 |
| Haiku 4.5 | $0.00007 | $0.00445 |
Grade A, and why
issue-small-change-review 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 25d 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Small Change Review
dev-small（.kaji/wf/custom/dev/dev-small.yaml）の review-change / verify-change step。
実装した session と同じ context ではレビューしない（workflow では別 session で起動される）。
Issue の決定事項・受け入れ条件と実 diff を照合し、HEAD に対して自分で品質検証を 1 回実行し、
PR 前提と完了条件を確認して判定する。修正が必要なら実装側（fix-change）へ戻す。
いつ使うか
| タイミング | このスキル |
|---|---|
dev-small の review-change（change PASS 後）/ verify-change（fix-change PASS 後） |
✅ |
| 標準 dev のコードレビュー | ❌ /issue-review-code |
| PR 上のレビュー | ❌ /review / /pr-verify |
ワークフロー内の位置: change → review-change → (fix-change → verify-change) → pr → review-poll → close
入力
ハーネス経由（コンテキスト変数）
| 変数 | 用途 |
|---|---|
issue_id / issue_ref / step_id / verdict_path |
対象 Issue、phase（review-change / verify-change）、verdict 保存先 |
worktree_dir / branch_name / default_branch |
レビュー対象 |
cycle_count / max_iterations |
参照可 |
design_path は注入されても使わない。
手動実行（スラッシュコマンド）
$ARGUMENTS = <issue_id>
worktree_dir が無い場合だけ _shared/worktree-resolve.md で絶対パスを得る。
step_id が無い場合は verdict marker から phase を決める: 最新 fix-change PASS が最新の review 系報告より新しければ
verify-change、それ以外は review-change（kaji issue resolve-verdict [issue_id] --step <step> の created_at を比較）。
marker が欠落して source: "artifact" で返った場合は
ended_at を ISO 8601 の時刻として比較し、null（時刻不明）で比較が必要なら推測せず停止する。
以降の [worktree_dir] は注入値または解決した絶対パス。Bash は毎回 cd [worktree_dir] && ... で実行する。
読み込み条件
| 区分 | 読むもの | 条件 |
|---|---|---|
| 通常 | Issue 本文・labels（kaji issue view [issue_id] --json title,body,labels） |
常時 |
| 通常 | 最新の change PASS 報告 |
review-change |
| 通常 | 最新の fix-change PASS 報告と、それが対応した直前の最新 review 系 RETRY 報告 |
verify-change |
| 通常 | git diff [default_branch]...HEAD と変更ファイル実体 |
review-change |
| 通常 | git diff <全体レビュー済み SHA>..HEAD と変更ファイル実体 |
verify-change（起点は下記） |
| 通常 | 自身の検証出力（成功時は終了状態・集計・JSON） | 常時 |
| 例外 | docs/dev/baseline-check.md |
known_failures / baseline 不整合 |
| 例外 | 失敗した検証の関連ログ全文 | 検証失敗時 |
| 例外 | docs/dev/testing-convention.md / docs/reference/python/*.md 該当節 |
テストの妥当性・規約逸脱の判断が必要な場合 |
| 例外 | docs/dev/shared_skill_rules.md § auto close keyword 回避 |
hazard pattern の判定に迷う場合 |
| 例外 | docs/dev/workflow_completion_criteria.md § 本文にチェックボックスがない場合 |
完了条件がチェックボックス形式でない場合 |
| 例外 | _shared/report-unrelated-issues.md | 無関係な問題を発見した場合 |
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.
- 25d ago Changed · +12 lines 3eaed53e0f5b
- 28d ago Changed · +2 lines 2ca9aa3ff3b3
- 1mo ago First seen · 232 lines · 66 tokens per session scan A f52f2f77050a
issue-small-change-review is a skill published in the GitHub repository apokamo/kaji (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 66 tokens to every session and 4,448 once invoked, about $0.0003 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 2026-09-29.
Other skills, from other repositories
orchestrated-execution
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
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…
software-development-pragmatic-programmer
Apply meta-principles of software craftsmanship: DRY, orthogonality, tracer bullets, and design by contract. Use when the user mentions "best practices", "pragmatic approach", "broken windows", "tracer bullet", "software craftsmanship", "technical debt prevention", "prototype vs tracer bullet", or "code ownership".…
software-design-patterns-and-refactoring
Use when architecture or backend work needs pre-code structural guidance from design patterns, or post-code cleanup guidance from refactoring and code-smell-driven improvement.