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.
curl -O https://raw.githubusercontent.com/suisya-systems/claude-org-ja/main/.claude/skills/org-delegate/SKILL.mdgit clone --depth 1 https://github.com/suisya-systems/claude-org-jaWrote 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/suisya-systems/claude-org-ja/org-delegate)<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/org-delegate"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/org-delegate/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/suisya-systems/claude-org-ja/org-delegate"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/org-delegate.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 | $0.00090 | $0.15301 |
| Opus 5 | $0.00045 | $0.07651 |
| Sonnet 5 | $0.00018 | $0.03060 |
| Haiku 4.5 | $0.00009 | $0.01530 |
Grade B, and why
org-delegate scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
**`.claude/` 編集タスクの send_keys 事前承認（root `.claude/**` self-edit のみ）**: 委譲対象に claude-org root の `.claude/**` が含まれる場合（`.dispatcher/` / `.curator/`、worker dir 生成物の `.claude/settings.local.json` は対象外）、窓口は上記挨拶の送信に**続けて** `pyth How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
org-delegate: ワーカー派遣
作業をワーカーClaudeに委譲する。窓口はタスク分解と派遣ペイロード生成だけ行い、 ペイン起動・指示送信はディスパッチャーに委託する。これにより窓口のロック時間を最小化する。
本 SKILL のスコープ: 派遣の「初動」(タスク特定 → 派遣ペイロード生成 → ディスパッチャーへの DELEGATE 受け渡し → ワーカー起動後の挨拶 → 進捗・完了報告受信時の ack と REVIEW 遷移) のみ。以下は別スキル / reference に分離している:
- ワーカー起動・指示送信・状態記録の手順 →
.dispatcher/references/spawn-flow.md(ディスパッチャー専属)- ユーザー承認後の push / PR / CI 監視 / レビュー指摘ループ / マージ後クローズ →
.claude/skills/org-pull-request/SKILL.md- ワーカーからの判断仰ぎ / スコープ拡張 / ブロッカーのエスカレーション →
.claude/skills/org-escalation/SKILL.md- ack 文面の最低 3 要素・種別ごとの例文 →
.claude/skills/org-delegate/references/ack-template.md(single SoT)
state-db cutover (M4, Issue #267 / #284): 構造化セクションの write は 必ず
StateWriter.transaction()経由で行う。post-commit hook が.state/org-state.md/.state/org-state.jsonを DB から自動再生成し、update_run_status('<task_id>', 'completed')呼び出しは.state/workers/worker-<task_id>.mdを.state/workers/archive/へ自動 move する。markdown 直接編集は drift_check が検出する。events は DB のeventsテーブルが SoT (tools/journal_append.sh/.pyは DB ルーティング済み)。DB 不在時はpython -m tools.state_db.importer --db .state/state.db --rebuild --no-strictで構築する。
輸送層（transport）両系 — 既定
broker/ opt-inrenga: 本スキルの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（push 一次 =
claude/channel/ pull フォールバック）: 既定 broker は worker からの進捗 / 完了 / 判断仰ぎが push 一次で届く（runtime push-first 0.1.24+、transport-labdocs/design/broker-native-roles.md§9）: 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→push し、notifications/claude/channelで本文を idle セッションへ注入する（「受けたら即応答」契機が生まれる）。pull はフォールバック層: sidecar 不在 / unhealthy（heartbeat timeout でdelivery_mode=PULL）/ channel 非対応ペイン / claude.ai login 不在時は、各役割が自身の cadence で能動的にcheck_messages（mcp__org-broker__check_messages）する（§9.6 読み替え表の役割別 cadence。ナッジが出れば契機になりうるが idle を起こさないため能動 poll が受信の正路。既存の「ナッジを見たらcheck_messages」prose は撤回せずこの fallback cadence として読む）。Step 5 の「ワーカーからのメッセージ受信時」は push 一次では channel 注入で起き、フォールバック時は窓口のターン冒頭の能動check_messagesで受ける（ack のsend_message等の手順は同型）。ORG_TRANSPORT=renga（opt-in）では、worker 報告が<channel source="renga-peers" …>として in-band で push される。契約面: Surface 8 で push 一次が ratified 済み（2026-06-15、S3。pull は fallback として retain・renga 不変）。- spawn 儀式（folder-trust 承認 + dev-channel sidecar 承認の 2 段）: ワーカー起動はディスパッチャー専属（
.dispatcher/references/spawn-flow.md）だが、既定 broker では--mcp-config <broker>注入（daemon・全ツール + agent token）と Claude Code の folder-trust プロンプト機械承認（send_keys(enter=true)）に加えて、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（spawn-flow 3-3b）をsend_keys(enter=true)で機械承認する（broker-native-roles.md §9.5）。これは ratified §5/§8.5 の folder-trust フローへの 加算であり置換ではない（※docs/design/renga-decoupling.md§4.6「dev-channel prompt は存在しない」/ contract §5.1・§8.5 の dev-channel→--mcp-config置換記述は、push 一次採用で channel sidecar 分の dev-channel load が additive に復活する＝S3 で 2026-06-15 に ratified・contract で amend 済み）。root.claude/**self-edit のsend_keys事前承認（下記 Step 5）もmcp__org-broker__send_keysで同じ手順を踏む。ORG_TRANSPORT=renga（opt-in）では--dangerously-load-development-channels server:renga-peersを注入し「Load development channel?」を Enter 承認する 1 段。- エラー分岐（既定 = broker 拡張コード込み）: shared codes に加え既定 broker は
[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）。一覧は.claude/skills/org-delegate/references/renga-error-codes.mdの broker 節を参照。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。本フローは元々使わない）。契約面の正本はdocs/contracts/backend-interface-contract.mdSurface 8（broker auth & delivery、ratified 2026-06-14。push 一次への additive 改訂 S3 が ratified 済み（2026-06-15、「Ratified amendment」節）・既存 ratified 本文不変更）、設計 SoT は transport-labdocs/design/broker-native-roles.md§9（push 一次再設計）/docs/design/ja-migration-plan.md§5.2(ii)・§8。broker 実走（dogfood）は Epic #6 Issue G スコープで本スキルの既定経路ではない。
What ships with it
16 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.
- references/ack-template.md 9.6 KB
- references/ack-template.md.in 4.3 KB
- references/capability-first-drive-operational-gate.md 55 KB
- references/claude-org-self-edit.md 23 KB
- references/codex-design-review.md 6.8 KB
- references/delegate-flow-details.md 9.6 KB
- references/dogfood-issue-template.md 3.3 KB
- references/dogfood-protocol.md 6.4 KB
- references/instruction-template.md 37 KB
- references/instruction-template.md.in 32 KB
- references/pane-layout.md 25 KB
- references/pane-layout.md.in 13 KB
- references/release-pre-fetch.md 5.1 KB
- references/renga-error-codes.md 64 KB
- references/worker-claude-template.md 50 KB
- SKILL.md.in 47 KB
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 · 392 lines · 90 tokens per session scan B 460ec396fc11
org-delegate is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 15,301 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
takt
A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
takt
A workflow engine for coordinating multiple coding agents. It reads a YAML workflow, a text configuration format, and moves agents through its defined steps and rules.
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
skill-creator
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.
codebase-context-extractor
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
Research Synthesis Workflow
A step-by-step guide to synthesizing research from multiple sources into a coherent summary.