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/kaji-run-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/kaji-run-verify)<a href="https://agentmods.dev/skills/apokamo/kaji/kaji-run-verify"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/kaji-run-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/kaji-run-verify"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/kaji-run-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 | $0.00059 | $0.02505 |
| Opus 5 | $0.00030 | $0.01252 |
| Sonnet 5 | $0.00012 | $0.00501 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
kaji-run-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 11d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kaji Run Verify
kaji run によるワークフローの手動検証を標準化します。
検証目的の実行であり、エラー発生時はその時点で停止し、原因調査と Issue コメントを優先します。
いつ使うか
| タイミング | このスキルを使用 |
|---|---|
| ワークフロー変更後の実機検証 | ✅ 必須 |
「kaji run .kaji/wf/... <issue> を実行して、結果を Issue に残して」と依頼されたとき |
✅ 推奨 |
| 通常の feature 開発をそのまま進めたいだけ | ⚠️ 任意 |
| 単に YAML の静的検証だけしたい | ❌ kaji validate のみで十分 |
入力
手動実行（スラッシュコマンド）
$ARGUMENTS = <workflow-path> <issue_id> [kaji run options...]
workflow-path(必須): 例.kaji/wf/official/dev.yamlissue_id(必須): GitHub Issue 番号kaji run options...(任意):--from/--step/--workdir/--quietなどをそのまま後続に渡す
例
/kaji-run-verify .kaji/wf/official/dev.yaml 73
/kaji-run-verify .kaji/wf/official/dev.yaml 73 --from fix-code
/kaji-run-verify .kaji/wf/official/dev.yaml 73 --workdir ../kaji-feat-73
前提知識の読み込み
以下を必要に応じて参照すること。
- ワークフロー定義:
docs/dev/workflow-authoring.md - スキル作成規約:
docs/dev/skill-authoring.md - 共通 Worktree 解決:
../_shared/worktree-resolve.md
共通ルール
- エラーが発生したら、追加の
kaji run再実行で先に進めない。まず原因調査と Issue コメントを完了させる。 - 長時間実行中の状態確認は、毎回細かくポーリングせず 2 分程度の間隔 を目安にしてよい。新規出力がなくても
kaji runプロセス自体が継続している限り、即座に停止扱いしない。 - review / fix / verify サイクル中の差し戻しや、agent が自力で修正可能な一時的失敗は、workflow 全体の失敗とみなして過剰に停止しない。
kaji run自体の終了、明確なハング、人手介入必須の異常が確認できた時点で停止判断を行う。 - 成功時も
気になった点と詰まった点を記録する。なければ特になしと明記する。 - Issue コメントには生ログ全文を貼らず、要点と必要な抜粋だけを載せる。
- 原因を断定できない場合は、確定事項 と 仮説 を分けて書く。
実行手順
Step 1: 引数の解析
$ARGUMENTS から以下を取得する。
workflow_pathissue_idextra_args(kaji runにそのまま渡す残りの引数)
workflow_path はメインリポジトリ基準の相対パスとして解決し、ファイルが存在することを確認する。
Step 2: Worktree の解決（--workdir 未指定時のみ）
extra_args に --workdir が含まれていない場合のみ、
_shared/worktree-resolve.md の手順で Issue 本文から Worktree を解決する。
- 解決できた場合:
kaji runに--workdir [resolved-path]を追加する - 解決できない場合:
--workdirなしで続行してよい。ただし Issue コメントにその旨を明記する
Step 3: 事前検証
まず kaji validate を実行する。
cd [main-repo-absolute-path] && source .venv/bin/activate && kaji validate [workflow-path]
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.
- 11d ago First seen · 295 lines · 59 tokens per session scan A 6f15733b8c54
kaji-run-verify is a skill published in the GitHub repository apokamo/kaji (12 stars, last pushed 3d ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,505 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 2026-08-30.
Other skills, from other repositories
software-design-lifecycle-delivery
Use when an architect must decide which architecture lifecycle stage to enter next, route to the correct stage methodology skill, and apply the merged lifecycle backbone as one coherent delivery chain rather than as separate old and new skill systems.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
pm
Generate a PM through guided PM-focused interview with automatic question classification. Use when the user says 'ooo pm', 'prd', 'product requirements', or wants to create a PRD/PM document.
publish
Publish Seed specification as GitHub Issues for team-based project management.