teamwork-parent

teamwork-parent is a skill for Claude Code from ishida-supsys/oretachi. It costs 182 tokens per session (3,988 once invoked), scanned A, original, MIT.

A workflow for splitting a large issue into smaller sub-issues and coordinating their separate worktrees. A worktree is an isolated copy of a Git project where one task can be developed independently.

In plain words
What is it for?
Use it to plan sub-issues, get approval, create child worktrees, monitor them, and report when all child tasks are closed.
Why use it?
It organizes dependencies, progress updates, and completion across several contributors or agent sessions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to plan sub-issues, get approval, create child worktrees, monitor them…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ishida-supsys/oretachi/teamwork-parent
Install

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.

Any agent
npx skills add ishida-supsys/oretachi --skill teamwork-parent
Clone the repo
git clone --depth 1 https://github.com/ishida-supsys/oretachi

Made for: Claude Code.

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 teamwork-parent

README.md
[![agentmods](https://agentmods.dev/badge/skills/ishida-supsys/oretachi/teamwork-parent.svg)](https://agentmods.dev/skills/ishida-supsys/oretachi/teamwork-parent)
Your own site
<a href="https://agentmods.dev/skills/ishida-supsys/oretachi/teamwork-parent"><img src="https://agentmods.dev/badge/skills/ishida-supsys/oretachi/teamwork-parent.svg" alt="Measured on agentmods" height="20"></a>
Per session 182 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,988 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 $0.00182 $0.03988
Opus 5 $0.00091 $0.01994
Sonnet 5 $0.00036 $0.00798
Haiku 4.5 $0.00018 $0.00399

Measured 2d ago against content hash a089fad378c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

teamwork-parent 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 2d 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.

src-tauri/skills/teamwork-parent/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

teamwork-parent スキル

このセッションは以後「チームワークセッション」として、sub-issueの分担・進行管理に徹する。実際のコード実装は各sub-issue用の子ワークツリーに委ね、このセッション自身はコードを書かない。

Step 1: 計画とユーザー承認

  1. まず自分自身のワークツリーのトレイ通知をオフにする(承認を待つ必要はない。自分のノイズを止めるだけで他ワークツリーの通知には影響しないため):
    oretachi_set_tray_notification(project_dir: <自分の作業ディレクトリ絶対パス>, enabled: false)
    
  2. 対象issueの本文・既存コメント・既存sub-issue(あればgh issue list等で確認)から、タスク分担と依存関係を洗い出す。sub-issueがまだ存在しない場合は、分割案を作成し「sub-issueを新規作成するか」を後続の承認要求に含める(この時点では作成しない)。
  3. 各sub-issueに決定的なブランチ名を採番する(例: issue-<番号>)。検証sub-issue等、完了前にユーザー確認が必要なものを識別する。
  4. 3章の手順で計画フロー図をartifactとして作成する(状態はすべてnot_startedでよい)。この計画フローartifactが以後の唯一の進捗管理データになる(別途マークダウン等は作らない)。
  5. ユーザーに承認を求める。承認内容には次を含める:
    • sub-issue新規作成の要否(対象がある場合)
    • 計画フロー(依存関係・検証ポイント・ユーザーが介入するタイミング) 承認が得られるまでStep2(oretachi_add_taskの呼び出し)を行わない。

Step 2: 子ワークツリー作成(承認不要、開始・完了トリガーで自動)

依存が無い、または既に解消済みのnot_startedのsub-issueについて、承認後は都度ユーザーに確認せず以下を実行する:

  1. oretachi_add_taskを呼ぶ。promptの冒頭に必ずteamwork-childスキルの読み込み指示を入れ、本文はsub-issueのURL参照のみに留める(issue本文を転記しない):
    oretachi_add_task(prompt: "teamwork-child スキルを読み込んでから対応してください。\nSub-issue: <URL>")
    
  2. oretachi_add_taskは非同期発火のため、ターン境界を挟んでoretachi_get_worktree_status(query: <採番したブランチ名>)をポーリングし、実際に作成されたワークツリー名を確認する。
  3. oretachi_subscribe_worktree(target: <確認したワークツリー名>, event_kinds: ["worktree.closed", "worktree.created", "worktree.message"])で購読する。
  4. 4章の手順で計画フローartifactのdata/flowモジュールを更新し、対象タスクのstatusin_progressにし、branchが実際の値と一致していることを確認する。

Step 3: 子ワークツリーイベントへの対応

  • worktree.closed: 対応するsub-issueのstatusdata/flow更新でdoneにする。依存が解消されて着手可能になったnot_startedのsub-issueがあれば、Step2の手順で次の子ワークツリーを承認を求めず自動作成する。
  • worktree.message: oretachi_poll_inboxで内容を確認し、oretachi_ack_messageで既読化する。
    • issueコメントのURLのみの場合は必要に応じて参照し、ユーザーの判断が必要な内容かどうかを見極める。
    • ユーザー判断が必要な内容だけを提示し、それ以外は自動で流れを継続する。
  • ユーザーの判断・操作が必要になったときは必ずnotify_worktreeを呼ぶ。 Step 1 でトレイ通知をオフにしているため、テキストを出力するだけではユーザーは気付けない。notify_worktreeはトレイ通知オフでも常に通る唯一の呼び戻し経路。
  • すべてのイベントを4章の手順でdata/flowMESSAGESに追記する(新しい順に先頭へ追加)。
  • 状態に迷ったらoretachi_list_subscriptionsで購読状態を確認してよい。

Read the full file on GitHub · 178 lines

Files

What ships with it

4 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.

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. 2d ago Changed · +23 lines a089fad378c3
  2. 6d ago First seen · 155 lines · 182 tokens per session scan A 3f3618c451de

Subscribe to this mod's changes

teamwork-parent is a skill published in the GitHub repository ishida-supsys/oretachi (2 stars, last pushed 2d ago), licensed MIT. It adds 182 tokens to every session and 3,988 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.