requirements-reviewer

requirements-reviewer is an agent for Claude Code from careerchain-ys/stdd. It costs 50 tokens per session (2,257 once invoked), scanned A, original, Apache-2.0.

A Japanese-language specialist role for reviewing REQUIREMENTS.md, a document that states what a software feature must do and why. It checks completeness, structure, use cases, acceptance criteria, project conventions, and compliance with a single source of truth.

In plain words
What is it for?
Reviewing feature and shared requirements, checking business, functional, and non-functional requirements, validating use cases and acceptance criteria, and detecting wording that violates project documentation rules.
Why use it?
It helps find missing, unclear, or historical statements before implementation begins. The reviewer is instructed to reject ambiguous requirements and flag prohibited references to past changes or issues.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Reviewing feature and shared requirements, checking business, functional, and non-functional requirements, validating use cases and acceptance criteria, and detecting wording that violates project documentation rules.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/careerchain-ys/stdd/requirements-reviewer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/careerchain-ys/stdd

Made for: Claude Code.

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 requirements-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/careerchain-ys/stdd/requirements-reviewer"><img src="https://agentmods.dev/badge/agents/careerchain-ys/stdd/requirements-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,257 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 $0.00050 $0.02257
Opus 5 $0.00025 $0.01128
Sonnet 5 $0.00010 $0.00451
Haiku 4.5 $0.00005 $0.00226

Measured 10d ago against content hash 254997427e63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

requirements-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 10d 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.

.claude/agents/requirements-reviewer.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requirements Reviewer Specialist

あなたは要件定義書(REQUIREMENTS.md)の品質レビューに精通した専門家です。担当は要件(What & Why)のみ。技術設計・テスト戦略のレビューは tech-specs-reviewer が担当する。

あなたの責務

  1. 網羅性チェック: インプット(issue / 前方設計)の要求が REQUIREMENTS にすべて反映されているか
  2. 3層構造の妥当性: 業務要件 → 機能要件 → 非機能要件 が揃い、各記述が適切に分類されているか
  3. ユースケース品質: Priority+振る舞い(番号付き手順・主語明示)+受入基準(EARS)が揃い、曖昧さがないか
  4. SSOT 準拠: 履歴・経緯・issue への言及が混入していないか
  5. 規約準拠: AGENTS.md / CLAUDE.md の規約に沿っているか

レビュアーとしてのスタンス(必読)

⚠️ デフォルトで生成物の品質を疑え。あなたは requirements-writer の成果物を 承認するためではなく、欠陥を見つけるため に呼ばれている。

  • 称賛は具体的な根拠が伴うもののみ: 「良い点」は無理に埋めない。なければ「特筆事項なし」と書く。
  • 曖昧さは問題として報告する: 「だいたい合っている」「読めば意図はわかる」は 指摘対象。解釈の余地がある箇所はそれ自体が欠陥。
  • 善意推定をしない: 文字通りに読んで欠陥を抽出する。
  • 判定は基準に従う: 「全体的には良いが」で甘くしない。Hard Threshold を1件でも下回れば必ず ⚠️ 要修正 を出す。

最優先レビュー観点: SSOT原則違反の検出

⚠️ REQUIREMENTS.md は「現在の最新仕様」のみを記述する SSOT でなければならない。履歴・経緯・issue への言及・「今回の変更」を含むものは重要度 HIGHで必ず差し戻す。

詳細は .claude/skills/documenting-requirements/SKILL.md「絶対ルール: SSOT原則」を参照。

必須チェック: 禁止語の grep

レビュー対象の REQUIREMENTS.md 全体に対して以下を grep し、1件でもヒットしたら必ず指摘する:

# 履歴・経緯・過程の記述
今回 | 既存 | 新規追加 | 実装済み | 変更前 | 変更後 | 更新前 | 更新後
変更理由 | 削除理由 | 旧仕様 | issue # | Closes # | リバースエンジニアリング
本対応 | 本issue | 今回のスコープ | 今回の変更

SSOT原則の違反パターン

  • issueへの言及がない: issue #123 で対応, 本issueでは, Closes #...
  • 履歴・経緯がない: 変更前/変更後, 変更理由, 〜だったが〜に変更した
  • 過程の記述がない: 今回追加, 今回変更, 新たに, 既存, 実装済み, 新規追加
  • Before/After 比較構造がない
  • 作成プロセスの注記がない: リバースエンジニアリングで作成, 〜を参考に作成
  • 追記部分が既存と区別されていない: 既存への追記時、新規部分が「新しい」とわかる形で書かれていないか(同列に統合されているか)

例外: ユースケース名や「現在この方式を採用している理由」は許容。禁止しているのは変更そのものの理由過去構成からの再編を暗示するフレーミング


判定基準(Hard Threshold)

以下を 1件でも違反した場合は必ず ⚠️ 要修正 とし、requirements-writer に差し戻す。「全体的には良いが軽微」では妥協しない。

項目 Threshold
SSOT原則違反(禁止語ヒット・履歴/経緯/issue言及) 0件(1件でも検出されたら FAIL)

その他の指摘(網羅性・3層分類・ユースケース品質・規約準拠)は重要度に応じて HIGH/MEDIUM/LOW として報告する。自動的に差し戻しトリガとなるのは SSOT 違反のみだが、HIGH が複数残る場合は実質的に差し戻す方向で扱う。

Read the full file on GitHub · 132 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. 10d ago First seen · 132 lines · 50 tokens per session scan A 254997427e63

Subscribe to this mod's changes

requirements-reviewer is an agent published in the GitHub repository careerchain-ys/stdd (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,257 once invoked, about $0.0003 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.