tool-skill-creator-extension

tool-skill-creator-extension is a skill for Claude Code, Codex from eaglesakura/agent-skills. It costs 290 tokens per session (4,664 once invoked), scanned A, original, MIT.

Supplementary instructions for creating or revising agent skills. They define how to write command examples, reference shared assets, and declare dependencies between skill packages.

In plain words
What is it for?
Reviewing skill documentation, normalising commands, adding shared asset references, and checking that references between skills match the package dependency declarations.
Why use it?
They reduce portability and maintenance problems caused by project-specific command wrappers, hard-coded asset paths, or undeclared references to other skills.

Skill for Claude CodeCodex

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is * `../../assets/`.

Good fit Reviewing skill documentation, normalising commands, adding shared asset references, and checking that references between skills match the package dependency declarations.

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-skill-creator-extension

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-skill-creator-extension

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/tool-skill-creator-extension"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/tool-skill-creator-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 290 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,664 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 $0.00290 $0.04664
Opus 5 $0.00145 $0.02332
Sonnet 5 $0.00058 $0.00933
Haiku 4.5 $0.00029 $0.00466

Measured 12d ago against content hash 1a4e1750c524, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tool-skill-creator-extension 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 12d 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-skill-creator-extension/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool / Skill Creator Extension

SKILL はリポジトリ横断・環境横断で再利用される。ツールチェイン管理(mise / fvm / asdf 等)の prefix・wrapper は プロジェクト固有の実行規約 であり、SKILL 本文に焼き付けると他環境でノイズになる。 コマンド例は素のツール呼び出しだけを書き、実行時の wrapper は各プロジェクトのルール(AGENTS.md 等)に任せる。

共有アセット(テンプレート・雛形・パッケージ配下の .apm/assets/ 等)を参照する場合も、 インストール先の 1 パスを直書きせず、{assets}/## アセットディレクトリ で解決できるようにする。

さらに SKILL 本文から他 package の SKILL / command / パスを参照する場合は、 編集対象 package の apm.yml が宣言する依存グラフに従う。ワークスペースに兄弟 package が並んで見えても、 未宣言の参照や逆依存を残すと、導入した第三者が混乱する。

本 SKILL は skill-creator の補足である。SKILL を新規作成・改訂するときは本ルールも適用する。

いつ使うか

  • 新規 SKILL の SKILL.md / references/ にシェルコマンド例を書くとき
  • 既存 SKILL から mise exec -- 等の project-local wrapper を除去・正規化するとき
  • skill-creator のドラフト・レビューで「コマンドの書き方」を点検するとき
  • SKILL 本文から共有アセット(テンプレート等)を参照するとき
  • {assets}/## アセットディレクトリ を追加・移行するとき
  • SKILL 本文で他 SKILL / command 名を明示参照するとき
  • 他 package パスを本文や例に書くとき
  • apm.yml の依存と SKILL 参照の整合・未宣言依存・逆依存を点検・修正するとき

コアルール

frontmatter(license / metadata

  • name / description 以外の frontmatter は Optional
  • licensemetadatametadata.author 含む)は、ユーザーが明示指定したときだけ書く
  • 既定値(例: MIT Licenseauthor: "@eaglesakura")で勝手に埋め込まない
  • 指定が無い新規・改訂では、これらのキーを frontmatter に残さない(削除してよい)

SKILL に書くコマンド(portable)

  • ツール本体の呼び出しだけを書く(dart / flutter / go / npm / npx など)
  • プロジェクト固有のツールチェイン wrapper・prefix・suffix は 含めない
    • 例: mise exec -- / mise run / fvm / asdf exec / direnv exec / nix-shell --run
DO: ツール本体だけを書く
dart -h
flutter --version
go test ./...
npx markdownlint-cli2 --fix path/to/file.md
DO NOT: ツールチェイン wrapper を埋め込む
mise exec -- dart -h
fvm flutter --version
asdf exec go test ./...

実行時(runtime)の扱い

SKILL を 実際に実行する ときは、この限りではない。

  • 作業対象リポジトリに mise / fvm 等の規定があれば、そのプロジェクトルールに従う
  • 規定の所在は AGENTS.md・リポジトリ README・既存スクリプトを優先して確認する
  • SKILL 本文を「実行用の最終コマンド」と同一視しない(本文は portable、実行は local policy)

必要なら SKILL 側に次のような一文を置いてよい(具体的な wrapper 名は書かない)。

コマンド実行時は、プロジェクト規定のツールチェイン(あれば)に従う。

Read the full file on GitHub · 253 lines

Files

What ships with it

1 file 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. 12d ago First seen · 253 lines · 290 tokens per session scan A 1a4e1750c524

Subscribe to this mod's changes

tool-skill-creator-extension is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 290 tokens to every session and 4,664 once invoked, about $0.0014 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens