verifying-consistency

verifying-consistency is a skill for Claude Code from careerchain-ys/stdd. It costs 97 tokens per session (2,112 once invoked), scanned A, original, Apache-2.0.

A consistency checker for software specifications, tests, and implementation. It compares stable requirement and feature IDs across those layers to find missing or mismatched parts.

In plain words
What is it for?
It helps audit changed features, build a traceability matrix, detect orphaned or duplicate IDs, and run the project’s traceability checks.
Why use it?
It helps reveal when a requirement lacks a design, test plan, test, or implementation, or when documents and code have drifted apart.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .claude/hooks/trace-audit.sh.

Good fit It helps audit changed features, build a traceability matrix, detect orphaned or duplicate IDs, and run the project’s traceability checks.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/careerchain-ys/stdd
agentmods
npx agentmods add skills/careerchain-ys/stdd/verifying-consistency

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 verifying-consistency

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/careerchain-ys/stdd/verifying-consistency"><img src="https://agentmods.dev/badge/skills/careerchain-ys/stdd/verifying-consistency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
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 $0.00097 $0.02112
Opus 5 $0.00048 $0.01056
Sonnet 5 $0.00019 $0.00422
Haiku 4.5 $0.00010 $0.00211

Measured 8d ago against content hash e134408b00bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

verifying-consistency 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 8d 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.

.agents/skills/verifying-consistency/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec・テスト・実装の整合性チェック

このセッション/ブランチで作成・修正した機能について、Spec・テスト・実装の整合性を確認する。

1. 対象ファイルの特定

ブランチ分岐点からの差分を特定

.stdd.config.ymlproject.primary_branch(PR/統合先ブランチ)を読み、その分岐点からの差分を特定する。

# <primary_branch> は .stdd.config.yml の project.primary_branch(例: main / develop)
git fetch origin <primary_branch>
git log --oneline origin/<primary_branch>...HEAD
git diff origin/<primary_branch>...HEAD --name-only

以下を特定:

  • Specドキュメント: docs/ 配下の REQUIREMENTS.md, TECH_DESIGN.md
  • テスト: *.test.ts, *.test.tsx, e2e/tests/**/*.spec.ts
  • 実装: app/, components/, lib/, actions/, domain/ 配下のファイル

2. ID ベース・トレーサビリティ監査(機械的・最優先)

名前一致ではなく安定 IDUC-<feature>-NN / FL-<feature>-NN)で 要件 → 技術設計 → テスト → 実装 を突合する。 検知は共通スキャナ .claude/hooks/trace-audit.sh(依存なし・pre-push / CI と同一ロジック)に委ね、 結果を解釈して報告する。設定は .stdd.config.ymltraceabilityenforce / patterns / scan 等)。

2A. 順方向(抜け漏れ検知)

bash .claude/hooks/trace-audit.sh
  • トレーサビリティ行列(ID × 設計 / テスト計画 / テスト / 実装)と抜け漏れ一覧を出力する。
  • 検知する抜け漏れ: 設計漏れ / テスト計画漏れ / テスト実装漏れ / 実装漏れ(require_impl_annotation 時)/ 孤児参照 / ID 重複。
  • traceability.enforce=block のとき、抜け漏れがあれば非ゼロ終了する(それを NG 判定に用いる)。

2B. 逆方向(テスト/実装起点の改修 → 影響範囲)

このセッション / ブランチの変更ファイル(§1 で取得済み)を渡し、テスト・実装起点の改修がどの要件に波及するか、 および追跡不能変更(どの ID にも紐づかないテスト / 実装変更 = spec-first 逸脱の疑い)を検知する。

# <primary_branch> は .stdd.config.yml の project.primary_branch
CHANGED=$(git diff --name-only origin/<primary_branch>...HEAD)
bash .claude/hooks/trace-audit.sh --changed $CHANGED

# 特定 ID の全リンク先を辿るとき
bash .claude/hooks/trace-audit.sh --impact UC-<feature>-01
  • 各変更が紐づく ID と、その ID の全リンク先(対応要件・技術設計箇所・他テスト / 他実装)を列挙する。
  • ID に解決しないテスト / 実装変更は 追跡不能変更として報告し、spec-first(Spec 起点)に立ち返るよう促す。

トレーサビリティ監査で検知した抜け漏れ・追跡不能変更は、§4 の出力にトレーサビリティ行列・影響範囲サマリとして必ず載せる。以降の §3 は ID では機械化しきれない内容(設計判断の反映・モック整合など)を人/AI が補完的に確認する。

3. 整合性チェック項目(補完・人/AI による確認)

A. REQUIREMENTS.md ⇔ 実装

  • REQUIREMENTS.md のユースケース(振る舞い+受入基準)が実装で網羅されているか
  • REQUIREMENTS.md の画面仕様(ボタン、フォーム、表示項目)が実装と一致しているか
  • REQUIREMENTS.md に記載された機能要件が全て実装されているか

Read the full file on GitHub · 138 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. 8d ago First seen · 138 lines · 97 tokens per session scan A e134408b00bf

Subscribe to this mod's changes

verifying-consistency is a skill published in the GitHub repository careerchain-ys/stdd (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 2,112 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 skills, from other repositories