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 s977043/PlanGate --skill subagent-team-designgit clone --depth 1 https://github.com/s977043/PlanGateWrote 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/s977043/plangate/subagent-team-design)<a href="https://agentmods.dev/skills/s977043/plangate/subagent-team-design"><img src="https://agentmods.dev/badge/skills/s977043/plangate/subagent-team-design/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/s977043/plangate/subagent-team-design"><img src="https://agentmods.dev/badge/skills/s977043/plangate/subagent-team-design.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 | $0.00152 | $0.01758 |
| Opus 5 | $0.00076 | $0.00879 |
| Sonnet 5 | $0.00030 | $0.00352 |
| Haiku 4.5 | $0.00015 | $0.00176 |
Grade A, and why
subagent-team-design 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 9d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Team Design
タスクの規模・モードに応じて最適なマルチエージェントチームを設計し、各メンバーへの委譲準備を行うスキル。
Common Rationalizations
| こう思ったら | 現実 |
|---|---|
| 「全部 implementer に任せれば速い」 | ロール分離がない実行は品質保証がない。チーム設計が速度を生む |
| 「チーム設計は時間がかかる」 | 役割が明確なほど各エージェントの出力品質が上がり、手戻りが減る |
| 「standard 以下でもチームを組む」 | ultra-light/light は 1 エージェントで完結。チーム設計はオーバーキル |
ステップ 1: チームが必要か判定する
| モード | チーム設計 |
|---|---|
| ultra-light / light | 不要。単一エージェントで完結 |
| standard | 実装 + レビューの 2 体が基本 |
| high-risk | 実装 + レビュー + テスト確認の 3 体以上 |
| critical | 全ロール（planner / implementer / reviewer / security-reviewer / test-reviewer）を配置 |
ステップ 2: ロール定義を確認する
以下の 6 ロールを使用する。本節が 6 ロール定義の正本である。
旧正本
plugin/plangate/rules/subagent-roles.mdは削除済み（TASK-0124 /2645848, 2026-06-02 の plugin 初回同期適用）。ロール定義は本節が引き継いだ。 派遣プロンプトの契約（必須 8 要素 / OUTCOME 契約 / 行動規範）はdocs/ai/subagent-delegation/README.mdを参照（ロール定義は含まない）。
参照解決順（導入先で必ずこの順に探す）: 本 Skill が参照する docs/** は上流リポジトリ基準の相対パスであり、install.sh --claude / plugin（Claude marketplace）/ Codex の 3 経路とも配布対象外（解決不可）。(1) 導入先リポジトリの同名パスを探す → (2) 見つからなければ 「正本 <path> を参照できなかった」と明示し、本 Skill 内の記述を代替正本として扱い、推測で内容を補わない。plugin root 配下の探索は docs/** には適用しない: plugin が配布するのは agents / commands / skills / rules 等の定義ディレクトリのみで docs/ を配布対象として認識せず、plugin root 配下に相当する配布物が存在しないため、plugin root 段を置いても必ず空振りする（クラス A の rules 参照が plugin root 配下で解決できるのは rules/ が実際に配布されるからであり、この非対称を docs/** に持ち込まない）。
| ロール | 責務 | 対応 subagent_type |
|---|---|---|
| planner | 要件分析・実行計画策定 | Plan または plangate:spec-writer |
| implementer | コード実装 | plangate:implementer または implementation-agent |
| reviewer | 設計・コード品質レビュー | plangate:acceptance-tester または qa-reviewer |
| security-reviewer | セキュリティ観点レビュー | security-auditor |
| test-reviewer | テスト品質・カバレッジ確認 | test-engineer |
| documentation-reviewer | ドキュメント整合性確認 | documentation-writer |
ステップ 3: チーム構成を決定する
タスクの Work Breakdown（plan.md）を元にチームを設計する。
出力フォーマット
team:
- role: planner
agent: plangate:spec-writer
tasks: [TA-01]
run_in_background: false
- role: implementer
agent: plangate:implementer
tasks: [TA-02, TA-03]
depends_on: [planner]
run_in_background: true
- role: reviewer
agent: plangate:acceptance-tester
tasks: [TA-04]
depends_on: [implementer]
run_in_background: false
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.
- 9d ago First seen · 124 lines · 152 tokens per session scan A c9ae96ea9724
subagent-team-design is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed today), licensed MIT. It adds 152 tokens to every session and 1,758 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
skill-maintenance
Automated skill maintenance tool (v6 — Unified Registry + Snapshots). Full scan: [Orphan] migrate misplaced skills from category dirs OR standalone skills/<name>/ to auto-generated/, [Sync] auto-generated/ vs registry lifecycle diff (new/deleted/revived + description auto-sync via lifecycle field), [Reg]…
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.