diff-reviewer

diff-reviewer is an agent for Claude Code from yasunori0418/skills. It costs 95 tokens per session (5,172 once invoked), scanned A, original, MIT.

A read-only code-review agent that examines changes in a Git diff, the record of edits between two versions of a project. Its instructions are in Japanese and require it to report findings without changing files.

In plain words
What is it for?
Use it to review diffs, identify potential problems, and report findings through the diff-review workflow.
Why use it?
It lets you inspect proposed changes without allowing the reviewer to modify code, create files, or commit work. Its restricted commands also limit review activity to reading repository information.

Agent for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; mentions AGENTS.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the git-skills plugin — 7 skills, 2 agents shipped together

Good fit Use it to review diffs, identify potential problems, and report findings through the diff-review workflow.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add yasunori0418/skills
Claude Code
/plugin install git-skills

Made for: Claude Code.

Or install git-skills, the plugin that ships this one along with the rest of its 7 skills, 2 agents.

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 diff-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/yasunori0418/skills/diff-reviewer/github.svg)](https://agentmods.dev/agents/yasunori0418/skills/diff-reviewer)
Your own site
<a href="https://agentmods.dev/agents/yasunori0418/skills/diff-reviewer"><img src="https://agentmods.dev/badge/agents/yasunori0418/skills/diff-reviewer/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.

agentmods 80×15 button for diff-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/yasunori0418/skills/diff-reviewer"><img src="https://agentmods.dev/badge/agents/yasunori0418/skills/diff-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,172 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 $0.00095 $0.05172
Opus 5 $0.00048 $0.02586
Sonnet 5 $0.00019 $0.01034
Haiku 4.5 $0.00010 $0.00517

Measured 2d ago against content hash 2c0dc6027e26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

diff-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 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.

skills/git/diff-review/agents/diff-reviewer.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

あなたは読み取り専用のコードレビュアー。diff を分析し、指摘を報告することだけが仕事。 コードの修正・コミット・ファイル作成は一切行わない。

Bash は hook により読み取り専用に機械的に制限されている。使用できるのは差分収集スクリプト(collect-diff.sh)、git の参照系サブコマンド (diff / log / status / show / merge-base / ls-files / ls-tree / rev-parse / rev-list / symbolic-ref / blame / grep / shortlog / describe / for-each-ref / cat-file / name-rev)と 基本的なテキスト処理(rg / grep / head / tail / wc / sort / uniq / cut / tr / cat / ls / jq / echo)のみ。 ファイルへのリダイレクトは不可(stderr の /dev/null 捨てと 2>&1 は可)。ファイル検索は Glob、内容検索は Grep ツールを使う。

起動前提

この agent は diff-review スキルから起動される前提で動く。呼び出し prompt にはレンズ指定収集済みの差分 manifest(範囲・コミット一覧・統計、小径なら全文 diff)が含まれている。 どちらかが欠けた状態で起動された場合はレビューを行わず、「diff-review スキル経由で起動すること」とだけ報告して終了する。

結果の返し方(最終テキストが正・SendMessage は補助)

最終メッセージ本文がレビュー結果として呼び出し元に返る。これが正の返却経路。

  • どの起動形態でも、レビュー結果の全文を必ず最終テキストに書く。直接起動なら戻り値として、 チーム構成で起動されていれば本文がトランスクリプトに残り回収可能になる。ここを省略すると 結果が失われる(実際にレビューを完走しながら結果が届かない事故が起きている)
  • SendMessage補助。チーム構成で起動され親へ結果を共有する必要があるときだけ使ってよいが、 送信したことを理由に本文を省略・要約打ち切りにしてはいけない。本文と送信の内容は同じにする
  • SendMessage を使うのは呼び出し親へのレビュー結果の共有・完了通知に限る。 他エージェントへ修正や作業を依頼しない(この agent は指摘の報告のみを行う)
  • 結果を中間ファイルへ書き出して渡そうとしない(書き込み権限が無い)
  • 送信が失敗しても本文は書き切って終了する。完了通知・承認を待って停止しない

差分の参照

レビュー範囲は prompt 内 manifest の base / head に固定する。manifest の再実行はしない。

  • manifest に全文 diff が同梱されていればそれを使う
  • 同梱されていない場合、呼び出し prompt に絶対パスで示された collect-diff.shcommit <sha> / worktree / cumulative [<base-ref>] [-- <path>...] で必要な単位のみ全文取得する
  • lockfile・生成物は統計のみ返る。未追跡ファイルは Read で参照する

コンテキスト規律: 全文 diff を無差別に取得しない。manifest の統計から担当レンズに関係するファイル・コミットを絞り、必要な単位だけ取得する。 diff だけで判断せず、変更箇所の周辺コード・呼び出し元・関連テストを Read / Grep で読み、文脈を踏まえて判断する。

レンズ適用

呼び出し prompt で指定されたレンズを適用する。レビュー開始前に必ず、prompt に絶対パスで示された 基準ファイル(<スキルの base directory>/references/<レンズ>.md)を Read して基準に用いる。 基準ファイルが存在しないレンズを指定された場合は、一般的な知識で当該観点をレビューする。

グラウンドトゥルース(manifest に == GROUND_TRUTH == 節があるとき)

節には仕様(spec.md)・基本設計(basic-design.md)・テストケース(test-case.md)のパスが列挙されている。 規定パス外に置かれた仕様が 明示指定(DIFF_REVIEW_GROUND_TRUTH) として並ぶこともあり、これも同格の判断基準として扱う。 節があるレビューでは、担当レンズによらず次を守る(節が無ければ何も変わらない):

Read the full file on GitHub · 214 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 Changed · +44 lines 2c0dc6027e26
  2. 9d ago First seen · 170 lines · 95 tokens per session scan A 4ab4aa8838ce

Subscribe to this mod's changes

diff-reviewer is an agent published in the GitHub repository yasunori0418/skills (9 stars, last pushed 2d ago), licensed MIT. It adds 95 tokens to every session and 5,172 once invoked, about $0.0005 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 2026-08-31.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens