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.
git clone --depth 1 https://github.com/eaglesakura/agent-skillsnpx agentmods add skills/eaglesakura/agent-skills/tool-sub-agent-creatorWrote 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/eaglesakura/agent-skills/tool-sub-agent-creator)<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/tool-sub-agent-creator"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/tool-sub-agent-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.
<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/tool-sub-agent-creator"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/tool-sub-agent-creator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00156 | $0.03258 |
| Opus 5 | $0.00078 | $0.01629 |
| Sonnet 5 | $0.00031 | $0.00652 |
| Haiku 4.5 | $0.00016 | $0.00326 |
Grade A, and why
tool-sub-agent-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 8d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool / Cursor Sub Agent Creator
Sub Agent はクリーンコンテキストで動く特化 Agent である。 ロール・職能・実施タスク・出力・ガードレールを定義ファイルに固定し、親が Task で委任したとき迷わず動けるようにする。
いつ使うか / 使わないか
- 使う:
.cursor/agents/に配置するカスタム Sub Agent の作成・改訂 - 使わない: slash-command(
tool-command-creator) - 使わない: Agent Skill(
skill-creator/tool-skill-creator-extension) - 使わない: 親が Task 起動時に SKILL をサジェストする手順そのもの(
agent-call-sub-agent)
出力先と命名
- プロジェクト共有のみ:
.cursor/agents/{agent-name}.md - ファイル名(拡張子除く)と frontmatter
nameを一致させる - 命名は
{領域}.{役割}のドット区切りを推奨する- 例:
docs-assistant.writer、docs-assistant.plan-reviewer
- 例:
- 本文 H1 はファイル名ではなく
{ロール} / {職能} / {実施するタスク}の三段とする- 例:
ジュニアエンジニア / 実装アシスタント / 承認済み計画ステップの実装
- 例:
必須: テンプレート準拠
出力は必ず assets/subagent.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。
frontmatter の書き方
| フィールド | 役割 | デフォルト |
|---|---|---|
name |
Sub Agent 識別子。ファイル名と一致 | (必須・個別) |
model |
使用モデル。inherit または具体 ID |
inherit |
description |
親が委譲判断に使う。ロール・入出力・いつ使うかを具体的に | (必須・個別) |
readonly |
書き込み制限 | true |
is_background |
親をブロックせず背景実行するか | false |
license |
任意 | 省略可。入れるなら MIT License 等 |
metadata.author |
任意 | ユーザー指定時のみ |
readonly / is_background / model は用途に応じて個別判断する。
判断材料が無いときの初期値は上表(テンプレートどおり)とする。
metadata.author は省略してよい。ユーザーが指示したときだけ書く。
必須・任意の SKILL は frontmatter ではなく本文 ## 追加コンテキスト に書く(後述)。
{assets}/ の探索先は frontmatter ではなく本文 ## アセットディレクトリ に書く。
旧 metadata.required_skills / metadata.assets / metadata.references は新規・改訂の正本にしない(後方互換で読まれる場合があっても、こちらから新規に書かない)。
description の記載規則
親 Agent の委譲判断に使われるため、曖昧な一文にしない。
- ロール(誰として動くか)
- 主タスク(何をするか)
- 入出力の概略(何を受け何を返すか)
- トリガー語(いつ委任すべきか)
# DO NOT
description: コードを手伝う Agent
# DO
description: >-
ジュニアエンジニアとして承認済み計画の指定ステップのみ実装する Sub Agent。
計画ファイルとステップ番号を受け取り、範囲外変更なしで実装差分と検証結果を返す。
「ジュニアに実装委任」「ステップ単位で実装」では使う。
本文セクション
テンプレートの見出し順を守る。slash-command のような Mermaid 必須・バリデーション表・非対話エラー終了契約は 載せない。
- タイトル(H1) —
{ロール} / {職能} / {実施するタスク} - 専門性 — 役割・職能・自立性の有無などを箇条書き
- 追加コンテキスト — 必須。次を含める
What ships with it
2 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.
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.
- 8d ago First seen · 197 lines · 156 tokens per session scan A 85468d4c0b64
tool-sub-agent-creator is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 156 tokens to every session and 3,258 once invoked, about $0.0008 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…