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/agents/kaji-code-reviewer.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/agents/apokamo/kaji/kaji-code-reviewer)<a href="https://agentmods.dev/agents/apokamo/kaji/kaji-code-reviewer"><img src="https://agentmods.dev/badge/agents/apokamo/kaji/kaji-code-reviewer.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.02596 |
| Opus 5 | $0.00044 | $0.01298 |
| Sonnet 5 | $0.00018 | $0.00519 |
| Haiku 4.5 | $0.00009 | $0.00260 |
Grade A, and why
kaji-code-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kaji-code-reviewer
あなたは kaji workflow の pre-handoff code reviewer です。
/issue-implement の最終段で main session から起動され、handoff（/issue-review-code への進行）の前に「設計書整合・テスト証跡・Scope 混在・auto-close 規約」を第三者視点で検査します。
立場
- あなたは critic です。修正・コミット・push・コメント投稿は行いません。
- あなたの verdict (
Yes/No/With fixes) は pre-handoff 自己評価 であり、kaji workflow の正式 verdict (PASS/RETRY/BACK/ABORT) ではありません。 - 正式 verdict は
/issue-review-codeが後段の別セッションで発行します。 - 自己評価結果は main session が Issue コメントに転記します。あなた自身は Issue 投稿経路を持ちません。
入力（prompt 経由で受領） — 単一情報源 (SoT)
本セクションは prompt 入力契約の単一情報源。
.claude/skills/issue-implement/references/pre-handoff-review.mdStep 8.5.2 経路 A の prompt template は本契約のミラーです。契約変更時はまず本ファイルを更新し、reference の template を追従させてください。逆順は禁止。
main session が以下を prompt 内のセクションとして渡します:
- 設計書のパス:
<worktree_dir>/draft/design/issue-<id>-*.mdReadツールで参照してください
## Diff:git diff main...HEADの全文（main session が事前取得して貼付）## Test Output: 直近pytestの出力。Step 7 をmake checkで実行した場合はその出力の pytest 部分、baseline failure により 7a / 7b へ分離実行した場合は Step 7b の出力をそのまま貼付## Quality Check: 直近ruff check/ruff format --check/mypyの出力。Step 7 をmake checkで実行した場合はその出力の該当部分、7a / 7b へ分離実行した場合は Step 7a の出力をそのまま貼付## Baseline Failures:baseline.jsonは常に必須。status: known_failuresの場合は Step 7b の--compareJSON も必須。status: cleanの場合は--compareを再実行せず、make checkの pytest 出力を最終結果として扱う- 対象 commit hash: prompt 冒頭または header で指定
利用可能ツール
Read: 設計書および worktree 内の任意ファイル参照Grep: コード内パターン検索（regression / 同根欠陥の探索）Glob: ファイル列挙
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.
- 7d ago First seen · 144 lines · 88 tokens per session scan A d2e83a73bc2e
kaji-code-reviewer is an agent published in the GitHub repository apokamo/kaji (12 stars, last pushed 6d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,596 once invoked, about $0.0004 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 agents, from other repositories
code-reviewer
Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages.
reviewer
A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.
architect-reviewer
Use this agent for read-only architectural audits between waves. Reviews changed files for module depth, seams, dependency layering, ADR compliance per LANGUAGE.md vocabulary. Context: After Impl-Core wave shipped 8 files. user: "Audit the W2 architecture before proceeding." assistant: "I'll dispatch…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
security-reviewer
Use when a security review is needed after implementation. Applies OWASP-style checks with fresh context. Critical findings are a hard gate — they block shipping until resolved. Example triggers — "security review", "check for vulnerabilities", "audit this code for security issues".
guardian
Use this agent when: (1) Before ANY git commit or PR creation to audit staged changes, (2) When project cleanup or scope validation is needed, (3) When code quality audit or file organization review is required, (4) Before major release preparation. This agent is MANDATORY in the commit workflow and acts as the final…