Monomi: Command for Claude Code

.claude/commands/refine-requirements.md

refine-requirements is a command for Claude Code from sumihiro3/Monomi. It costs 50 tokens per session (2,112 once invoked), scanned A, original, MIT.

A guided requirements session for turning a release idea into a clear requirements file before implementation.

In plain words
What is it for?
Use it to clarify a release, record the agreed requirements, check related issues, create the release branch, and start the configured release workflow.
Why use it?
It helps uncover unclear goals, scope, priorities, acceptance checks, and non-functional needs before coding begins. It also uses the project's workflow configuration instead of guessing paths or branches.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the AskUserQuestion tool.

This is sumihiro3/Monomi's own configuration. It tells Claude Code how to work on Monomi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Monomi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sumihiro3/Monomi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sumihiro3/Monomi/main/.claude/commands/refine-requirements.md
Clone the repo
git clone --depth 1 https://github.com/sumihiro3/Monomi

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 refine-requirements

README.md
[![agentmods](https://agentmods.dev/badge/commands/sumihiro3/monomi/refine-requirements.svg)](https://agentmods.dev/commands/sumihiro3/monomi/refine-requirements)
Your own site
<a href="https://agentmods.dev/commands/sumihiro3/monomi/refine-requirements"><img src="https://agentmods.dev/badge/commands/sumihiro3/monomi/refine-requirements.svg" alt="Measured on agentmods" 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 2,112 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 $0.02112
Opus 5 $0.00025 $0.01056
Sonnet 5 $0.00010 $0.00422
Haiku 4.5 $0.00005 $0.00211

Measured 6d ago against content hash 05bba58b6786, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

refine-requirements 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 6d 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/commands/refine-requirements.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/refine-requirements — 要件壁打ちフェーズ

リリース(release-N)単位で要件をユーザーと壁打ちし、確定要件を .claude/workflow.config.jsonrequirementsPath({release} をリリース識別子で置換したパス)に書き出す。 後続の run-release / implement-feature ワークフローはこのファイルを入力として受け取るため、実装可能な粒度まで具体化してから確定させること。

引数: $ARGUMENTS(対象リリース番号や要件の種。例: release-1 ログイン機能。省略時はユーザーに確認)

進め方

  1. config の読込: .claude/workflow.config.json を Read する。以降のパス・ブランチ・自動化設定はすべてこの config から取る(requirementsPathbaseBranchconventionsDocknownIssues.pathautomation.pipeline)。ファイルが無い・読めない場合は「.claude/workflow.config.json がありません。作成してから再実行してください」と明示して中断する(書き出し先やベースブランチを推測で補完しない)
  2. 現状把握: プロジェクトの README / 要件書(あれば)と、対象リリースの既存ドラフト(あれば requirementsPath の該当パス)を読む。関連する実装の現状は conventionsDoc から探索する。あわせて knownIssues.path のバックログを確認し、今回のリリースで対応する既存課題があればその ID を控える
  3. 壁打ち(対話): AskUserQuestion を使い、以下を1テーマずつ詰める。一度に全部聞かない:
    • 解決したい課題と成功基準(誰が・何に困っていて・どうなれば成功か)
    • スコープ(今回やること / 明示的にやらないこと)。割れた論点と最終決定はスコープ確定表の材料として論点・決定のペアで記録する
    • 優先度(必須 / 推奨 / 将来)
    • 受け入れ基準(検証可能な形で。各 AC が自動検証可能か手動検証必須かも判定する。記法は後述)
    • 非機能要件(性能・セキュリティ・互換性)で関係するもの
  4. 調査(必要時): 技術的な実現性・代替案の比較が必要なら、サブエージェント(Explore / general-purpose)や WebSearch で調査してから提案する。推測で断定しない
  5. リリースブランチの作成: リリース識別子(release-N-slug)が確定した時点で、baseBranch を最新化してから同名のブランチを作成しチェックアウトする(git checkout <baseBranch> && git pull && git checkout -b release-N-slug)。以降のステップ(実装・レビュー・doc同期・コミット)はこのブランチ上で行う。既に対象ブランチで作業を再開している場合は作成をスキップする
  6. 確定要件の書き出し: requirementsPath の該当パスに、後述の「requirements.md の構成(実運用フォーマット)」に従って書く
  7. 確定要件のコミット: 書き出した requirements.md を単独の docs コミットにする(例: docs: release-N-slug の確定要件を追加)。run-release の Gate 0 は作業ツリーがクリーンであることを要求するため、未コミットのまま次のステップへ進まない
  8. run-release の起動: config.automation.pipeline の値で分岐する:
    • "auto": 起動確認を挟まず、そのまま次を起動する:
      Workflow({scriptPath: ".claude/workflows/run-release.js", args: {release: "release-N-slug", config: <手順1で読み込んだ config>}})
      
    • "ask": AskUserQuestion で起動可否を確認し、承認された場合のみ上記を起動する。見送られた場合は、上記の起動スニペットと従来の個別実行(implement-feature 以降の各工程)を案内して終了する
    • 起動は常に scriptPath 指定とする(新規ワークフローが同一セッションで name 解決されない既知の罠の構造的回避)

Read the full file on GitHub · 63 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. 6d ago First seen · 63 lines · 50 tokens per session scan A 05bba58b6786

Subscribe to this mod's changes

refine-requirements is a command published in the GitHub repository sumihiro3/Monomi (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 2,112 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.