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/review-starter-update/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/review-starter-update)<a href="https://agentmods.dev/skills/apokamo/kaji/review-starter-update"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/review-starter-update/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/review-starter-update"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/review-starter-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00653 |
| Opus 5 | $0.00017 | $0.00327 |
| Sonnet 5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
review-starter-update 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 8d 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.
What it actually says
Review Starter Update
update-starter と別 session で、updater の結論を正解とせず starter candidate を独立 review する。
入力
/review-starter-update <tracking_issue_id>。tracking Issue、対象 kaji tag、starter remote main の
base SHA、starter local main の candidate SHA を固定する。target は tracking Issue 本文（v1 schema）
の現在の syncing batch から決定的に求まる active_target（batch 内 target の最大値）と一致する
ことを要求する。update-starter の verdict marker meta.target は当該 batch の active_target と
完全一致で報告されているため、marker meta と本文由来の active_target の不一致は fail-closed で
ABORT する。
実行順
- tracking Issue と starter sync runbook を読み、
target（= 本文の
active_target） / base / candidate と checkout identity を確認する。 - updater の分類表を見ずに、target tag、CHANGELOG、upstream diff から調査集合を独立に再構成する。
- この時点で初めて review rubric を読み、全件 3 区分、移植の完全性、 過剰コピー、dependency / lock / docs、template cleanliness、quality gate evidence を照合する。
- review 中に starter のファイルを修正しない。candidate SHA が変わったら review を中止して ABORT。
- target tag、base SHA、candidate SHA を evidence に含むレビュー報告を tracking Issue に投稿する。
判定
PASS: 全 rubric を満たし、candidate が固定されている。RETRY: 修正または分類の再検討で収束できる。/update-starter再実行後は candidate が変わるため再 review。ABORT: 一次情報・identity・固定 SHA を安全に確定できない。
Verdict
PASS | RETRY | ABORT。status に関係なくコメントコマンドへ以下を付ける。
--verdict-step review-starter-update --verdict-status <STATUS> \
--verdict-meta target=<tag> --verdict-meta base=<SHA> --verdict-meta candidate=<SHA>
共通 schema は変更せず、target / base / candidate は marker meta と人間可読 evidence の両方へ残す。
コメント末尾、stdout、注入時は最後に verdict_path の pure YAML へ同じ verdict を保存する。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago Changed · +4 lines 76f71b8d3fa7
- 12d ago First seen · 42 lines · 34 tokens per session scan A 49379e55fca9
review-starter-update is a skill published in the GitHub repository apokamo/kaji (12 stars, last pushed 5d ago), licensed Apache-2.0. It adds 34 tokens to every session and 653 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.
Other skills, from other repositories
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.
superpowers-verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
superpowers-receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.