claude-org-ja: Skill for Claude Code

.claude/skills/dispatcher-resume/SKILL.md

dispatcher-resume is a skill for Claude Code from suisya-systems/claude-org-ja. It costs 174 tokens per session (11,258 once invoked), scanned A, original, MIT.

A recovery skill for resuming a dispatcher—the coordinator that assigns work and monitors workers—after a session is cleared.

In plain words
What is it for?
It reads the handover, updates the saved session identifiers, and restarts three-minute worker monitoring when the previous workers are still running.
Why use it?
It restores the dispatcher’s working state from a handover file instead of starting the organization again.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is suisya-systems/claude-org-ja's own configuration. It tells Claude Code how to work on claude-org-ja itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-org-ja configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Bash(python3 ../tools/journal_append.py:*).

Reuse

Borrowing it

Nothing to install: this file belongs to suisya-systems/claude-org-ja. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/suisya-systems/claude-org-ja/main/.claude/skills/dispatcher-resume/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/suisya-systems/claude-org-ja

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 dispatcher-resume

README.md
[![agentmods](https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/dispatcher-resume/github.svg)](https://agentmods.dev/skills/suisya-systems/claude-org-ja/dispatcher-resume)
Your own site
<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/dispatcher-resume"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/dispatcher-resume/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.

agentmods 80×15 button for dispatcher-resume

Your own site · 80×15
<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/dispatcher-resume"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/dispatcher-resume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,258 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00174 $0.11258
Opus 5.5 $0.00070 $0.04503
Sonnet 5.5 $0.00035 $0.02252
Haiku 4.5 $0.00017 $0.01126

Measured 11d ago against content hash 70c671ec21dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dispatcher-resume 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 11d 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.

.claude/skills/dispatcher-resume/SKILL.md · 492 lines

How it starts

The opening of the file, as written. The whole thing — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dispatcher-resume: ディスパッチャーの復帰

/dispatcher-handover で書き出した .state/dispatcher-handover.md を読み込み、 ディスパッチャーとして最低限の自覚(組織員としての立ち位置・進行中の派遣・監視 対象ワーカー)を復元し、/loop 3m の worker monitoring を再開する。

前提:

  • ワーカー / 窓口のペインは前 session から生きたまま残っている。 新たに spawn しない(/org-start ではない)。キュレーターは常駐しない(起動中の curator が居れば Step 5 で追跡を引き継ぐ)。
  • 自ペイン(name=dispatcher)も生きている。secretary が send_keys で /clear → /dispatcher-resume を打鍵した直後の状態。pane_id / peer_id は 変わっていないはずだが、必ず観測し、観測で確定できた値だけを state.db に atomic 更新する(確定できなかった値は書かず既存値を保持する。Step 0 / Step 2)。
  • state DB (.state/state.db) はそのまま使う。
  • 監視 gap を埋める内部状態ファイル(.state/dispatcher-event-cursor.txt(backend session に束縛された poll_events cursor) / .state/dispatcher/worker-idle-state.json / .state/dispatcher/curate-inflight.json(存在時) / .state/pending_decisions.json)は 前 session から残っている。新規作成・初期化・削除しない(既存値からそのまま継続。 消すと前 session からの監視連続性が壊れる)。
  • handover ファイルが存在しないか古すぎる場合は、/org-start を案内して停止する。
  • /clear は /loop の予約を消さない。前 session の監視ループの予約は /clear の後も 残っており、同じ指示文で /loop をもう一度打つと予約が 2 本になる。監視ループを張る前に 必ず CronList で確かめる(Step 5。経緯は .claude/skills/dispatcher-resume/references/rationale.md §4)。

自動引き継ぎ(auto op=<OP> 付きで呼ばれたとき)

context-handover watcher(tools/context_handover_watch.py)が /dispatcher-handover auto op=<OP> → /clear → /dispatcher-resume auto op=<OP> を打鍵する。 手順は通常の resume と同じで、違いは次の 3 つだけ:

  • 完了の event(末尾「イベント記録」)に op=<OP> を付ける。watcher はこの行で復帰の完了を判定する。 Step 0 の前の already_consumed に落ちた場合(watcher の再送など)も、(i) と unknown の 分岐の終わりに同じ形の行を note=already_consumed で 1 行書く。初期化はやり直さない。
  • Step 6 の後に、/clear の前後に届いて会話から消えた入力を処理する(Step 6.5)。
  • 窓口への DISPATCHER_RESUMED / DISPATCHER_RESUMED_IDLE は通常どおり送る。

輸送層(transport)両系 — 既定 broker / opt-in renga: 本ファイル(および各スキル)の mcp__org-broker__* 呼び出しは 既定 broker(ORG_TRANSPORT 無設定)で書いてあり、そのまま従えばよい(既定挙動)。ORG_TRANSPORT=renga(opt-in・切戻し可)では MCP サーバー名が renga-peers になり、ツールの 完全修飾名が mcp__org-broker__* → mcp__renga-peers__* に機械置換される(引数形・セマンティクスは同一なので手順の論理は変わらない)。輸送依存で手順が変わる点だけ renga 併記する:

  • 受信モデル: 既定 broker は push 一次(各ペイン同居の channel sidecar server:org-broker-channel が broker キューを ~1 秒間隔で claim→notifications/claude/channel で idle セッションへ本文注入。pull = ナッジ + check_messages は sidecar 不在 / unhealthy / channel 非対応ペイン(codex pull-peer)/ claude.ai login 不在時のフォールバック層)。ORG_TRANSPORT=renga 時は dispatcher / worker メッセージが <channel source="renga-peers" …> として in-band で push される。
  • spawn 儀式: 既定 broker は --mcp-config <broker> 注入による Claude Code folder-trust プロンプトの画面判定による機械承認に加え、push 一次のため channel sidecar を --dangerously-load-development-channels server:org-broker-channel で load し dev-channel 承認プロンプトを画面判定で機械承認する(2 段承認)。ORG_TRANSPORT=renga 時は --dangerously-load-development-channels server:renga-peers の「Load development channel?」を画面判定で承認する 1 段。 画面判定 = inspect_pane → claude-org-runtime dispatcher spawn-prompt-step が返した 1 手だけを send_keys する反復(runtime 0.1.43+)。盲目 Enter は禁止(folder-trust の初期カーソルは「No, exit」で、Enter 一発はワーカーを終了させる)。手順は spawn-flow 3-3b。
  • エラー分岐: 既定 broker は shared codes(pane_not_found / last_pane / invalid-params)に加え broker 固有 [token_invalid] / [session_invalid] / [tool_not_authorized] / [no_backend](= adapter_unavailable)/ [nudge_failed] / [peer_not_found] / [name_taken] を返しうる(未知コードは default-branch で escalate)。ORG_TRANSPORT=renga 時は broker 固有コードは発生しない。

new_tab / focus_pane は broker surface に無い(意図的除外)。契約面の正本は docs/contracts/backend-interface-contract.md Surface 8 + push-primary amendment(broker push 一次が 既定の契約、pull は fallback として retain)。opt-in renga は削除せず常時有効な切戻しの安全装置として維持する。broker 実走(dogfood)は Epic #6 Issue G スコープで本ファイルの既定運用経路ではない(二フレーム注記(Refs #604): ここの「既定 broker」はコード既定(tools/transport.py: DEFAULT_TRANSPORT、生成面はこれで render)。運用既定は broker dogfood が Epic #6 Issue G まで未活性のため renga で、両者は指す対象が異なり矛盾しない。総説は root CLAUDE.md。)

Read the full file on GitHub · 492 lines

Files

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.

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. 11d ago Changed · +6 lines 70c671ec21dd
  2. 12d ago Changed · +49 lines · +28 tokens per session 3697ddd173bc
  3. 1mo ago Changed 8d15975ca9b5
  4. 2mo ago First seen · 437 lines · 146 tokens per session scan A 9c609ba01158

Subscribe to this mod's changes

dispatcher-resume is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 5d ago), licensed MIT. It adds 174 tokens to every session and 11,258 once invoked, about $0.0007 per session on Opus 5.5. 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.