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/careerchain-ys/stddnpx agentmods add skills/careerchain-ys/stdd/verifying-consistencyWrote 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/careerchain-ys/stdd/verifying-consistency)<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.
<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>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 | $0.00097 | $0.02112 |
| Opus 5 | $0.00048 | $0.01056 |
| Sonnet 5 | $0.00019 | $0.00422 |
| Haiku 4.5 | $0.00010 | $0.00211 |
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.
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.yml の project.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 ID(UC-<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.yml の traceability(enforce / 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
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.
- 8d ago First seen · 138 lines · 97 tokens per session scan A e134408b00bf
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.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.