tool-command-creator

tool-command-creator is a skill for Claude Code, Codex from eaglesakura/agent-skills. It costs 185 tokens per session (5,867 once invoked), scanned A, original, MIT.

A creator and editor for Cursor slash commands, which are reusable instruction files run by an AI coding agent. It defines their inputs, outputs, related files, assets, steps, checks, and safeguards.

In plain words
What is it for?
Use it to create or revise files such as .cursor/commands/*.md or .apm/prompts/*.prompt.md, including commands with flows and shared assets.
Why use it?
It removes the need to design the command format and supporting documentation from scratch. It helps keep commands consistent with the repository’s Cursor or APM layout.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is * [requirements.md](../extra/docs/requirements.md).

Good fit Use it to create or revise files such as .cursor/commands/.md or .apm/prompts/.prompt.md, including commands with flows and shared assets.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/eaglesakura/agent-skills
agentmods
npx agentmods add skills/eaglesakura/agent-skills/tool-command-creator

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for tool-command-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/eaglesakura/agent-skills/tool-command-creator/github.svg)](https://agentmods.dev/skills/eaglesakura/agent-skills/tool-command-creator)
Your own site
<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/tool-command-creator"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/tool-command-creator/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.

agentmods 80×15 button for tool-command-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/tool-command-creator"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/tool-command-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,867 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00185 $0.05867
Opus 5.5 $0.00074 $0.02347
Sonnet 5.5 $0.00037 $0.01173
Haiku 4.5 $0.00018 $0.00587

Measured 2mo ago against content hash 97ef2aaf4261, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tool-command-creator 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 2mo 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.

packages/agent-creator/.apm/skills/tool-command-creator/SKILL.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool / Cursor Slash-Command Creator

slash-command は Agent が実行する再利用可能な手順書である。 入力・出力・関連資源・手順の分岐を本文で明示し、後続 Agent が迷わず実行できるようにする。

いつ使うか / 使わないか

  • 使う: .cursor/commands/ に配置する Cursor slash-command の作成・改訂
  • 使わない: Agent Skill(.cursor/skills/**/SKILL.md)の作成(skill-creator 等)
  • 使わない: 一度きりの会話プロンプトの下書きだけ(ファイルとして残さない場合)

出力先と命名

  • プロジェクト共有: .cursor/commands/{command-name}.md
  • APM パッケージのソース: .apm/prompts/{command-name}.prompt.md(install 後に .cursor/commands/ 等へ展開される)
  • ファイル名がコマンド名になる(例: docs.render.md → /docs.render)
  • このリポジトリでは {領域}.{動詞や目的} のドット区切りを推奨する(例: docs.format-plan, git.preflight)
  • 本文 H1 はファイル名ではなく、内容要約のタイトル(例: 実装フロー / 要件定義)にする

共有アセット

コマンド本文に長い書式・テンプレート・複数コマンドで共有する資料を埋め込まない。 ファイル参照は ## 関連ファイル、探索ディレクトリは ## アセットディレクトリ に分ける。

リポジトリ直下のコマンド(未パッケージ)

  • 配置: .cursor/extra/{領域またはコマンド名}/...
    • 領域共有の例: .cursor/extra/docs/requirements.md
  • コマンドからの参照は相対パス(例: [requirements.md](../extra/docs/requirements.md))
  • {assets}/ を使う場合は ## アセットディレクトリ に候補ディレクトリを列挙する

APM パッケージ内のコマンド

  • ソース配置: .apm/assets/{領域またはコマンド名}/...
    • 例: .apm/assets/example.command/template.md
  • 本文・## 関連ファイル ではインストール先の 1 パスを直書きせず、{assets}/... メタ変数を使う
    • 例: {assets}/template.md
  • {assets}/ を使う場合は、本文の ## アセットディレクトリ に実ディレクトリ候補を列挙する(正本)
    • ソース相対(開発時): ../assets/example.command/
    • install 後ルート相対: apm_modules/**/agent-creator/.apm/assets/example.command/
  • 旧来の metadata.assets だけがある文書も workspace-resolve-agent-assets は読めるが、新規・改訂では本文セクションへ書く
  • 実行時の実体解決は workspace-resolve-agent-assets に従う(文書相対とワークスペースルート相対の両方を試し、ヒットを示す)

コマンド単体に閉じる短い例示だけなら本文に書いてよい。書式の正本・長いテンプレート・共有ルールはアセットへ寄せる。

必須: テンプレート準拠

出力は必ず assets/command.md に従う。 プレースホルダ({...})と HTML コメントは最終成果物から除去する。

生成コマンドの実行契約(必須)

作成・改訂する slash-command 自体が、実行時に次を守るように書く。

非対話

  • ユーザーへの確認質問・選択肢提示・追加情報の依頼を行わない
  • 不足情報を対話で補完せず、文脈・引数・既存ファイルから確定できる範囲だけを使う

不明確はエラー終了(実行時)

次のいずれかが明確にならない場合は、処理を続けずエラーとして終了する。

  • 入力(Required の欠落、解釈不能、矛盾)
  • 出力(保存先・形式・成功条件が特定できない)

手順の不明確は実行時エラーにしない。 生成コマンドの最終出力(手順・ガードレール・フローチャート)に「手順が不明確です」等の分岐を書かない。

Read the full file on GitHub · 339 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2mo ago First seen · 339 lines · 185 tokens per session scan A 97ef2aaf4261

Subscribe to this mod's changes

tool-command-creator is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 185 tokens to every session and 5,867 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-31.

Related

tool-command-creator compared with skills from other repositories

tool-command-creator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tool-command-creatoreaglesakura/agent-skillsSkill21mo agoMITA185Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex