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/s977043/PlanGatenpx agentmods add skills/s977043/plangate/subagent-delegation-briefWrote 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-delegation-brief)<a href="https://agentmods.dev/skills/s977043/plangate/subagent-delegation-brief"><img src="https://agentmods.dev/badge/skills/s977043/plangate/subagent-delegation-brief/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-delegation-brief"><img src="https://agentmods.dev/badge/skills/s977043/plangate/subagent-delegation-brief.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 | $0.00177 | $0.02996 |
| Opus 5 | $0.00088 | $0.01498 |
| Sonnet 5 | $0.00035 | $0.00599 |
| Haiku 4.5 | $0.00018 | $0.00300 |
Grade A, and why
subagent-delegation-brief 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 10d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Delegation Brief
委譲すると決めた後に、派遣プロンプト 1 通を組み立てて送り、返ってきた報告を受理するまでの実行入口。
サブエージェントは会話履歴を持たない。書かれていない情報は「無い」ものとして扱われる。 このスキルは「何を書くか」のチェックリストであり、契約本文は持たない(正本を複製すると drift する)。
正本(定義はすべてここにある / 本ファイルで再定義しない)
| 正本 | 何が書いてあるか |
|---|---|
docs/ai/subagent-delegation/dispatch-template.md |
必須 8 要素の定義・省略時の実害・用途別テンプレート本体(調査 / 実装 / レビュー / 追指示) |
docs/ai/subagent-delegation/outcome-contract.md |
OUTCOME の表記ルール・P0/P1/P2 の定義・検証状態 4 区分・review=true・受け入れ確認 5 項目の判定基準 |
docs/ai/subagent-delegation/behavior-norms.md |
行動規範(軽量版 / フル版) |
docs/ai/subagent-delegation/examples.md |
フルサンプル |
docs/ai/subagent-delegation/README.md |
配置 ADR・オーケストレータ責務・索引 |
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)。
1. 派遣前チェックリスト(8 要素)
各行を埋めてから送る。埋められないものは「該当なし」と明示する(空欄は暗黙の許可・暗黙の禁止として誤読される)。
| # | 要素 | この委託で具体的に何を書くか |
|---|---|---|
| 1 | 役割・プロジェクト・項目ID・タスク名 | 後から報告を突合できる識別子を含めたか |
| 2 | なぜこのモデルか | 定型作業ではなく判断系である理由を 1 行 |
| 3 | 最初に読む SSOT | 優先順に列挙し、1 つ目だけで着手できるか。リンク切れを送信前に確認したか |
| 4 | 既知の事実・実測値・確定済み結論・却下済み仮説 | §2 の追加規約に従う(最も落ちやすい) |
| 5 | 順序付きタスク | 依存順の番号付き。並列可能な範囲を明示したか |
| 6 | 制約 | write 可否 / 対象パス / 触ってはいけないもの / 禁止操作 / ソフト上限。§4 の worktree 定型も参照 |
| 7 | 出力形式 | §3 の追加規約に従う(2 番目に落ちやすい) |
| 8 | 行動規範 | 軽量版 / フル版のどちらかを明示。長時間・複数ファイル・真因調査はフル版 |
2. 要素 4 の追加規約 — 却下済み仮説と「反証を許可する一文」
要素 4 は 3 つを分けて書く。確定済みの事実だけを書いても足りない。
- 確定済みの事実・実測値: 数値・ファイルパス・exit code など、再調査させないための一次情報
- 却下済み仮説: 「これは試さない / 再提案しない」と、その理由(理由が無いと相手は蒸し返す)
- 反証を許可する一文(必須): 例 —「上記は実測済み。ただし疑わしければ反証してよい。却下済み仮説以外は、実測が示すなら反論すること」
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.
- 10d ago First seen · 122 lines · 177 tokens per session scan A 25f67cd1f012
subagent-delegation-brief is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed today), licensed MIT. It adds 177 tokens to every session and 2,996 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 2026-08-31.
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…
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.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
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.