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-pr/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-pr)<a href="https://agentmods.dev/skills/apokamo/kaji/i-pr"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/i-pr/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-pr"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/i-pr.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 | $0.00036 | $0.03607 |
| Opus 5 | $0.00018 | $0.01803 |
| Sonnet 5 | $0.00007 | $0.00721 |
| Haiku 4.5 | $0.00004 | $0.00361 |
Grade A, and why
i-pr 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.
How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
I PR
workflow 共通の PR 作成スキル。 workflow 固有の完了判定は持たず、PR 作成そのものに責務を限定する。
いつ使うか
| タイミング | このスキルを使用 |
|---|---|
i-dev-final-check 完了後 |
✅ 必須 |
i-doc-final-check 完了後 |
✅ 必須 |
provider.type='github' 配下 |
✅ 受理（gh CLI 経由） |
provider.type='local' 配下 |
❌ Step 0 で ABORT。代替は /issue-close（local merge） |
このスキルがやらないこと
- 品質チェック（
make check）の実行 →i-dev-final-check/i-doc-final-checkの責務 - 設計書アーカイブ →
i-dev-final-checkの責務 - エビデンス集約 →
i-dev-final-check/i-doc-final-checkの責務 - PR マージ・ブランチ削除 →
issue-closeの責務
入力
ハーネス経由（コンテキスト変数）
常に注入される変数:
| 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 |
provider_type |
str | github / local のいずれか。Step 0 のガード判定に使用 |
git_remote |
str | git remote 名（provider.<type>.git_remote config から解決。未指定時のフォールバックは kaji_harness/config.py 定義）。Step 4 の git push -u 引数に使用 |
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）。
pr_id / pr_ref / pr_url は本 Skill の Step 4 で kaji pr create の出力から確定する。プロンプトへの自動注入は現時点では行わない（forge 採用先確定時に再評価、draft/design/local-mode/design.md §残課題 参照）。
前提知識の読み込み
- docs/dev/workflow_overview.md
- docs/dev/shared_skill_rules.md
docs/guides/git-commit-flow.md（kaji の Conventional Commits 運用、--no-ffmerge 規約）
前提条件
/issue-startが実行済みであることgit absorbがインストール済みであること（任意）
共通ルール
- _shared/report-unrelated-issues.md — 作業中に発見した無関係な問題の報告ルール
実行手順
Step 0: provider check
本 Skill は forge provider 専用。最初に provider_type を解決し、
github 以外なら 以降のステップに進まず ABORT verdict を出力して終了 する。
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 · 316 lines · 36 tokens per session scan A cb114ca46c78
i-pr is a skill published in the GitHub repository apokamo/kaji (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 3,607 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
superpowers-finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-close-issues
Close resolved Codewhale issues only after verifying the landed commit/behavior, with a positive crediting comment; never from title alone.