Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/karaage0703/ai-assistant-workspacenpx agentmods add skills/karaage0703/ai-assistant-workspace/xs-code-reviewerWrote 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/karaage0703/ai-assistant-workspace/xs-code-reviewer)<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-code-reviewer"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-code-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.
<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-code-reviewer"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-code-reviewer.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 | $0.00087 | $0.01835 |
| Opus 5 | $0.00044 | $0.00918 |
| Sonnet 5 | $0.00017 | $0.00367 |
| Haiku 4.5 | $0.00009 | $0.00184 |
Grade A, and why
xs-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 11d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
プルリクエストコードレビュー
GitHub CLIを使用してプルリクエストを分析し、バグ・リスク・回帰・不足テストを優先してレビューする。
重要: デフォルトはチャット上でのレビュー報告。GitHubへのコメント投稿、review投稿、approve/request changes は外部状態変更なので、ユーザーの明示OKを取ってから行う。
使用方法
PR#123をレビューして
owner/repo の PR#123 をレビューして
このPRを複数AIで見て
レビュー完了の定義
通常レビュー:
- PR情報と差分を確認した
- 必要に応じて
xs-multi-agentで外部AIにも見せた - findings を重要度順に統合した
- チャットでレビュー結果を報告した
GitHub投稿まで依頼された場合:
- 投稿対象(repo / PR / コメント種別)を明示してユーザーのOKを取った
- GitHubに投稿した
- 投稿URLまたはPR URLを報告した
レビュー手順
Step 1: PR情報の確認
# PRテンプレートがあれば確認
test -f .github/pull_request_template.md && cat .github/pull_request_template.md
# PR詳細
gh pr view <PR番号> --repo <owner>/<repo> --json title,body,headRefOid,baseRefName,headRefName,files,additions,deletions,url
# 差分
gh pr diff <PR番号> --repo <owner>/<repo>
# 変更ファイル一覧
gh pr diff <PR番号> --repo <owner>/<repo> --name-only
--repo <owner>/<repo> を明示する。remote が複数ある環境では、gh が別リポジトリを選ぶ事故が起きやすい。
Step 2: ファイル別詳細分析
各変更ファイルについて必要に応じて確認する。
gh pr diff <PR番号> --repo <owner>/<repo> -- <ファイルパス>
ローカルにブランチを取得する場合は、既存未コミット変更を確認してから行う。
Step 3: レビュー観点
優先順位:
- セキュリティ、データ損失、権限、公開範囲の問題
- バグ、回帰、エラーハンドリング不足
- テスト不足、検証不足
- 仕様・ドキュメントとの不整合
- 保守性、可読性、設計上の懸念
- 好みの問題や軽微なスタイル
コードレビューでは、良い点より先に findings を出す。問題がない場合は「ブロッカーなし」と明示し、残るリスクや未検証項目を書く。
Step 4: マルチエージェント検証
複数AIで見る依頼、重要PR、大きめの差分では xs-multi-agent を併用する。
CONFIG_PATH="$(bash skills/xs-multi-agent/scripts/check_agents.sh)"
cat "$CONFIG_PATH"
依頼プロンプトはファイルに保存してから、利用可能な外部エージェントへ渡す。
cat > /tmp/pr-review-prompt.txt <<'EOF'
以下のPR差分をレビューしてください。
バグ、セキュリティ、回帰、不足テストを優先し、好みの指摘は後回しにしてください。
<PR情報と差分>
EOF
bash skills/xs-multi-agent/scripts/run_agent.sh codex /tmp/pr-review-prompt.txt "$PWD"
外部AIが使えない場合は、自分だけでレビューしてよい。その場合は「外部AIは検出したが使用できなかった」と報告する。
Step 5: 結果統合
複数AIの意見はそのまま並べず、重複をまとめて重要度順に統合する。
重要度:
blocker: セキュリティ、データ損失、明確なバグ、重大な回帰major: 修正した方がよい設計・仕様・テスト不足minor: 軽微な改善nit: 好みや表記揺れ。必要な時だけ
誤検出の可能性がある指摘は、必ず差分やファイルを再確認してから出す。
出力フォーマット
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.
- 11d ago First seen · 212 lines · 87 tokens per session scan A de64b529adbc
xs-code-reviewer is a skill published in the GitHub repository karaage0703/ai-assistant-workspace (137 stars, last pushed 23d ago), licensed MIT. It adds 87 tokens to every session and 1,835 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 skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.