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 skills add sean-sunagaku/claude-code-plugin --skill subagent-best-practicesgit clone --depth 1 https://github.com/sean-sunagaku/claude-code-pluginWrote 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/sean-sunagaku/claude-code-plugin/subagent-best-practices)<a href="https://agentmods.dev/skills/sean-sunagaku/claude-code-plugin/subagent-best-practices"><img src="https://agentmods.dev/badge/skills/sean-sunagaku/claude-code-plugin/subagent-best-practices.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00185 | $0.03185 |
| Opus 5 | $0.00093 | $0.01592 |
| Sonnet 5 | $0.00037 | $0.00637 |
| Haiku 4.5 | $0.00018 | $0.00318 |
Grade A, and why
subagent-best-practices 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 7d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SubAgent Best Practices
Claude Code の agents/*.md ファイルで SubAgent を正しく定義するための実践ガイド。
チーム設計・通信プロトコル・タスク管理は agent-team-guide スキルを参照。
このスキルは「個別 SubAgent の定義品質」に特化している。
SubAgent とは
SubAgent は agents/*.md ファイルで定義された特化型エージェント。
my-skill/
└── agents/
├── researcher.md ← SubAgent 定義
├── writer.md
└── context-manager.md
Claude Code は agents/*.md を自動認識し、subagent_type: "my-skill:researcher" で起動できる。
SubAgent は親のコンテキストを持たない。起動時のプロンプトが唯一の情報源。
subagent_type の種類
| 値 | 動作 |
|---|---|
"my-skill:researcher" |
agents/researcher.md を読んで起動 |
"general-purpose" |
agents/*.md を使わず、プロンプトでロールを定義 |
"Explore" |
コードベース探索に特化した組み込みタイプ |
YAML Frontmatter の書き方
---
name: researcher # 必須: kebab-case の識別名
description: > # 必須: 役割の1〜3行説明
Market research specialist.
Part of the app-naming team.
tools: Read, Grep, Glob, WebSearch, # 推奨: 許可ツールのリスト
SendMessage, TaskList, TaskGet, TaskUpdate
model: sonnet # 推奨: haiku / sonnet / opus / inherit
---
name
subagent_type: "my-skill:{name}"の{name}部分に対応- kebab-case 推奨（
context-manager,bias-reviewer） - SendMessage の送信元名として使われる
description
- エージェントの役割と所属チームを 1〜3 行で説明
subagent_type指定時のマッチングに使われる- 自動委譲を強化する場合は "Use proactively" / "MUST BE USED" を含める
# 自動委譲を意図した description の例
description: >
Expert code review specialist. Use proactively after writing or modifying code.
Triggers: "review", "check", "レビュー"
tools の選び方
| 役割タイプ | 推奨 tools |
|---|---|
| 調査系 | Read, Grep, Glob, WebSearch, SendMessage, TaskList, TaskGet, TaskUpdate |
| 執筆系 | Read, Grep, Glob, Write, Edit, SendMessage, TaskList, TaskGet, TaskUpdate |
| 実行系 | Read, Grep, Glob, Write, Edit, Bash, SendMessage, TaskList, TaskGet, TaskUpdate |
| 分析系（読み取り専用） | Read, Grep, Glob, SendMessage, TaskList, TaskGet, TaskUpdate |
| コンテキスト管理専任 | Read, Write, Edit, SendMessage, TaskList, TaskGet, TaskUpdate |
What ships with it
5 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.
- 7d ago First seen · 281 lines · 185 tokens per session scan A 1e43a9894f5b
subagent-best-practices is a skill published in the GitHub repository sean-sunagaku/claude-code-plugin (36 stars, last pushed 1mo ago), licensed MIT. It adds 185 tokens to every session and 3,185 once invoked, about $0.0009 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
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-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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…