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 agentmods add skills/aiya000/dotfiles/verify-git-command-locationnpx skills add aiya000/dotfiles --skill verify-git-command-locationgit clone --depth 1 https://github.com/aiya000/dotfilesWhat 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 | $0.00040 | $0.00431 |
| Opus 5 | $0.00020 | $0.00216 |
| Sonnet 5 | $0.00008 | $0.00086 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
verify-git-command-location 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 2d 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
check-git-on-windows
When the working directory is on a Windows filesystem, WSL's native git may fail with errors.
Avoid this by using the appropriate git binary.
Step 1: Check if you are on a Windows filesystem
Run git rev-parse --show-toplevel.
If the output starts with a Windows drive letter (C:, D:, etc.), you are on a Windows filesystem.
If it shows a normal UNIX path (e.g. /home/...), stop here — the rest of this skill does not apply.
Step 2: Confirm the current directory is under /mnt/c/
Run pwd.
The current working directory should start with /mnt/c/ or a similar WSL mount path.
If it does not, notify the user.
Step 3: Check where the git command is from
Run which git.
If the location is not in a user-placed path like ~/bin/git, stop here.
If it is in a user-placed path, check whether it looks like a WSL-to-Windows filesystem bridge script:
Run ls -l $(which git).
# Example of a WSL-to-Windows filesystem bridge script
lrwxrwxrwx 1 aiya000 aiya000 80 Jan 25 12:17 /home/aiya000/bin/git -> /home/aiya000/Repository/git_bridge_wsl2_and_windows/git_bridge_wsl2_and_windows
If it does not appear to be such a bridge script, stop here.
Last: If no bridge is found
If no suitable method is found, notify the user and explain what they need to set up.
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.
- 2d ago First seen · 46 lines · 40 tokens per session scan A 37de4bfbdddb
verify-git-command-location is a skill published in the GitHub repository aiya000/dotfiles (19 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 431 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
coding
Principles for writing and designing code, covering API and abstraction design, naming, comment discipline, and standards of evidence for claims about code behavior. Use whenever the task is to write or modify code, design an API or software architecture, or review code.
restart__pull_request
乱れた (fix-up コミット過多・議論の脱線・大規模な書き直し) プルリクエストを、 ユーザーが "restart" / "やり直し" したいときに起動する。既存 PR を close し、 ブランチを新ブランチ上の単一のクリーンなコミットに squash し、過去の PR 議論 (レビューコメント・スレッド・リアクション) を統合した説明文で新しい PR を作成する。 元のブランチを force-push してはならない。必ず新しいブランチを作成する。.
validate__japanese
日本語の Markdown 文書 (README・ドキュメント・ブログ下書き・.md) を編集した後に起動する。textlint の ja-technical-writing / ja-spacing プリセットで、長すぎる一文・読点過多・文体の混在・全角半角スペースを検出する。さらに文中ハードラップ (文末でない位置で折り返した、意味のない改行) を検出し、段落・箇条書き項目を 1 行に連結して調整する。1 行に文を積み上げた箇所は、箇条書きへの変換候補として検出する。実在のシンボルを指すコードスニペットへ参照リンクも付与する。日本語の .md を変更したときに使用する。.
prepare__issue
あなたは要件定義済みの Issue を実装着手可能な状態へ引き上げるオーケストレーターである。 対象は status:acknowledged の Issue であり、完了時に status:ready へ遷移させる。.
rescue__pull_request_review
GitHub PR にレビュアー (人間または AI) がコメントを残した後に起動する。 レビューコメントを読み取り、要求されたコード変更を適用し、コミットして push する。 レビューフィードバックの各ラウンドごとに繰り返す。ユーザーの確認は不要 — Claude がこのプロセス全体を自律的に起動・実行する。.
submit__pull_request
プルリクエストを作成から完了まで一貫して提出するときに起動する。ナラティブ型の PR 説明文を生成し、PR を作成し、CI チェックを監視し、CI の失敗を自動修正する。 PR ナラティブと CI 修正のワークフローを 1 つの自律フローに統合する。.