Borrowing it
Nothing to install: this file belongs to apokamo/kaji. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/apokamo/kaji/main/.claude/skills/i-doc-verify/SKILL.mdgit clone --depth 1 https://github.com/apokamo/kajiWrote 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/apokamo/kaji/i-doc-verify)<a href="https://agentmods.dev/skills/apokamo/kaji/i-doc-verify"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/i-doc-verify/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/apokamo/kaji/i-doc-verify"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/i-doc-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00828 |
| Opus 5 | $0.00015 | $0.00414 |
| Sonnet 5 | $0.00006 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
i-doc-verify 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 9d 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
I Doc Verify
重要: このスキルは更新/修正を行ったセッションとは別のセッションで実行することを推奨します。
docs 修正後の確認を行う。 新規指摘は行わず、前回レビューの指摘が解消したかのみ確認する。
いつ使うか
| タイミング | このスキルを使用 |
|---|---|
i-doc-fix 後の確認 |
✅ 必須 |
ワークフロー内の位置: review-doc → fix-doc → verify-doc → i-doc-final-check → i-pr
入力
ハーネス経由（コンテキスト変数）
| 変数 | 型 | 説明 |
|---|---|---|
issue_id |
str | 正規化済み Issue ID（GitHub 数値または local ID） |
issue_ref |
str | 人間可読の Issue 参照（GitHub では #<issue_id>、local では bare ID） |
step_id |
str | 現在のステップ ID |
cycle_count |
int | 現在のイテレーション |
max_iterations |
int | 上限回数 |
previous_verdict |
str | 前ステップの verdict |
手動実行（スラッシュコマンド）
$ARGUMENTS = <issue_id>
解決ルール
コンテキスト変数 issue_id が存在すればそちらを使用。
なければ $ARGUMENTS の第1引数を issue_id として使用。
issue_ref はハーネス経由ではプロンプトに自動注入される（prompt.py 側で provider 別に整形）。手動実行時は issue_id から導出する: GitHub 数値 ID なら #<issue_id>、local-* 形式なら bare ID（# を付けない）。
前提知識の読み込み
実行手順
- 前回の
i-doc-review/i-doc-fixコメントを確認 - 指摘事項ごとに OK / NG を判定
- 必要最小限で根拠となる実装 / docs / workflow / AGENTS.md / CLAUDE.md を再確認
- 変更ファイルに絞ったリンクチェック結果を確認:
cd [worktree_dir] && python3 scripts/check_doc_links.py [changed-markdown-files...] - 新規発見事項があっても今回の判定には含めない
- 結果を Issue にコメント
Verdict 出力
---VERDICT---
status: PASS
reason: |
前回の docs review 指摘は適切に修正されている
evidence: |
Must Fix 項目の解消を確認した。新規指摘は判定に含めていない
suggestion: |
---END_VERDICT---
status の選択基準
| status | 条件 |
|---|---|
| PASS | 前回指摘が解消 |
| RETRY | 修正不足 |
| ABORT | 継続が危険 |
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.
- 9d ago First seen · 84 lines · 31 tokens per session scan A 6647c8ee3c86
i-doc-verify is a skill published in the GitHub repository apokamo/kaji (12 stars, last pushed 2d ago), licensed Apache-2.0. It adds 31 tokens to every session and 828 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
software-design-lifecycle-tech-detailed-methodology
Use when an architect must run the detailed-design portion of technical design, preserve the full lifecycle-stage doctrine for detailed design, and define the concrete runtime, project, flow, data, interface, non-functional, security, recovery, hardware, and implementation-plan surfaces needed for execution.
software-design-lifecycle-solution-design-biz-arch-diagramming
A method for designing and reviewing a business-solution architecture: a middle-level view that connects confirmed business problems to a solution before technical implementation is designed.
software-design-lifecycle-tech-overview-system-arch-diagramming
A guide for architects who draw or review system architecture diagrams during overview design. It explains subsystems, outside dependencies, communication links, and system boundaries without going into every technology detail.
creative-claude-design
Design one-off HTML artifacts (landing, deck, prototype).
diagram-drawio
Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, network topology, ML/DL model figures (Transformer/CNN/LSTM), mind maps, or any visualization. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that…
software-development-norms
Use when writing, reviewing, or refactoring code in any language to apply industrial-grade development norms abstracted from the Alibaba Java Development Handbook. Covers naming, type safety, exceptions, logging, concurrency, databases, project structure, testing, and security with language-agnostic principles and…