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.
npx skills add elvezjp/ixv-agents --skill spec-code-reviewer-skillgit clone --depth 1 https://github.com/elvezjp/ixv-agentsWrote 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/elvezjp/ixv-agents/spec-code-reviewer-skill)<a href="https://agentmods.dev/skills/elvezjp/ixv-agents/spec-code-reviewer-skill"><img src="https://agentmods.dev/badge/skills/elvezjp/ixv-agents/spec-code-reviewer-skill.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00832 |
| Opus 5 | $0.00000 | $0.00416 |
| Sonnet 5 | $0.00000 | $0.00166 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
spec-code-reviewer-skill 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.
What it actually says
Spec-to-Code Semantic Review
Purpose
設計仕様（Markdown）とソースコード実装の間のセマンティックな整合性を検証し、ロジックのギャップを特定する。
Scope / Non-Goals
- Scope: 機能レベル/モジュールレベルのレビュー（仕様セクションと実装コードを比較）
- Non-Goals: フォーマット/スタイルチェック（linter/formatter使用）、大規模バッチ処理（専用ツール使用）
Inputs
- 仕様書（Markdown）
- 要件は明示的に記述（Must/Shall/Should）
- 要件ID（
AUTH-001）またはセクションヘッダーで識別
- ソースコード
- 仕様を実装する関連ファイル/モジュール
- 大きい場合はスコープを絞った抜粋とファイルパスを含める
Outputs
- Summary:
Highly Consistent / Partially Consistent / Inconsistent - Findings table（各行に証拠を引用）:
Requirement ID / SectionStatus（OK / NG / 要確認）Observation（何が欠落/乖離/曖昧か、コードのどこか）
- Suggested Improvements: 次のアクション（実装または仕様の明確化）
Steps
- 入力の収集: 仕様書とソースコードを取得
- Excel仕様の場合:
xlsx2csv spec.xlsx | csvtomdまたは Pandoc で変換
- Excel仕様の場合:
- コンテキスト把握: 仕様を読み、意図、データ構造、エッジケースを理解
- 要件IDの付与（未付与の場合）: セクションヘッダーを識別子として使用（
[AUTH-001],[API-002]） - クロスリファレンス: 仕様の各要件を実装にマッピング
- 分析: 以下を検出
- Missing Logic: 未実装の要件
- Divergent Logic: 仕様と異なる実装
- Ambiguity: 曖昧な仕様による疑わしい実装
- レポート生成: ギャップと改善案を含むレポートを作成
Guardrails
- チャンキング戦略（大きな入力の場合）:
- 仕様: 対象機能に関連するセクションに絞る
- コード: モジュール/クラス/関数境界で分割、10-20行のオーバーラップを維持
- 要件 → ファイルパス → シンボル（関数/クラス）のマッピングを安定させる
- 役割外ファイルの更新禁止
Validation
- 全要件に対して OK/NG/要確認 のいずれかが付与されている
- Summary が適切に判定されている
- Suggested Improvements が具体的なアクションを示している
References
Execution
What ships with it
9 files 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.
- assets/review_prompt.md 1.2 KB
- references/case-study.md 1.1 KB
- references/comparison-report_ja.md 3.8 KB
- references/comparison-report.md 2.9 KB
- references/enterprise-service.md 564 B
- references/human-in-the-loop.md 748 B
- references/review-criteria.md 650 B
- references/role-definition.md 754 B
- references/skill-mapping.md 532 B
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 · 68 lines · 0 tokens per session scan A b271cb670fff
spec-code-reviewer-skill is a skill published in the GitHub repository elvezjp/ixv-agents (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 832 tokens. 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…