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/no-editnpx skills add aiya000/dotfiles --skill no-editgit clone --depth 1 https://github.com/aiya000/dotfilesWrote 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/aiya000/dotfiles/no-edit)<a href="https://agentmods.dev/skills/aiya000/dotfiles/no-edit"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/no-edit.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 | $0.00059 | $0.00585 |
| Opus 5 | $0.00030 | $0.00293 |
| Sonnet 5 | $0.00012 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
no-edit 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 5d 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
no-edit
Everything written after /no-edit (same line or following lines) is the actual task.
Perform it under the following investigation-only restriction: no writing or editing
anywhere except /tmp (or $TMPDIR).
Behavior
- Editing/writing is forbidden outside
/tmp($TMPDIR)Edit/Writetool calls are restricted to/tmp/$TMPDIRpaths for the duration of this skill (enforced viaallowed-toolsabove)- Do not run any Bash command that creates, modifies, deletes, moves, or stages files
outside
/tmp/$TMPDIR— this also coversgit add/commit/push, package installs, config edits, dotfile changes, etc. - Read-only tools and commands (Read, Grep, Glob, WebFetch, WebSearch,
git status/diff/log, etc.) are unrestricted — investigate freely
- Investigation scripts go in
/tmp/$TMPDIRonly- If the task needs a throwaway script (e.g. to parse logs, reproduce a bug, probe an
API), write it under
/tmp/$TMPDIR
- If the task needs a throwaway script (e.g. to parse logs, reproduce a bug, probe an
API), write it under
- Clean up before reporting
- Before giving the final result, delete every file/script you created during the
investigation with:
~/.dotfiles/bash-toys/bin/rm-dust <path>... - Never use plain
rmfor this — see the [[fd]] alternative-commands convention - Do this even if the task ended in an error, as long as files were created
- Before giving the final result, delete every file/script you created during the
investigation with:
- Report the findings as usual
When the task itself requires an edit outside /tmp
Do not silently perform it, and do not silently skip it either. Stop, tell the user that
/no-edit is blocking it, and ask how they'd like to proceed (e.g. drop /no-edit for
this request, or scope the write to /tmp instead).
Does Not
- Does not persist beyond the current task — applies only to the instructions given
directly after
/no-editin this invocation - Does not restrict read-only investigation
- Does not modify sandbox or permission settings
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.
- 5d ago First seen · 48 lines · 59 tokens per session scan A 09897b042e2a
no-edit is a skill published in the GitHub repository aiya000/dotfiles (19 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 585 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
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。.
write__structured_comment
ソースコードを編集・作成した後、cleancommentout の前に起動する。 デフォルトはコメント 0。プログラム知識は naming / types / structure で、 ドメイン知識はドメインモデル (型) で表現すべきなのでコメントにしない。 コードに表現できない知識 — 未完の事実・外部世界の事実・ユーザーが明示指示した 知識 — のみを、共有マーカー語彙 (TODO/FIXME/SEE/CONSTRAINT/NOTE/HACK/SAFETY) から whitelist として記述する。各コメントは必ずマーカーで始め、1 論理コメントは 2 行 以内・1 行 70 文字以内に収め、issue/PR…