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/secretary-handover/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/secretary-handover)<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/secretary-handover"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/secretary-handover/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/secretary-handover"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/secretary-handover.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 | $0.00138 | $0.01871 |
| Opus 5 | $0.00069 | $0.00936 |
| Sonnet 5 | $0.00028 | $0.00374 |
| Haiku 4.5 | $0.00014 | $0.00187 |
Grade A, and why
secretary-handover 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 12d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
secretary-handover: 窓口の引き継ぎ
窓口セッションを長期化させずに、組織員としての自覚と直近やり取りを次セッションへ
受け渡すための引き継ぎファイルを作る。書き出した後にユーザーへ /clear →
/secretary-resume の流れを案内する。
重要な前提:
- ディスパッチャー / キュレーター / ワーカーのペインは生かしたまま残す。
/clearは窓口の Claude コンテキストだけをリセットするので、state.db と handover ファイルから復帰できれば組織は途切れない。- state DB (
.state/state.db) は唯一の SoT。ペイン identity やワーク状態は そちらから引ける。handover はあくまで「会話の温度感」「人間との合意」「進行中の判断」など、 構造化データに収まらない部分を残すために使う。
Step 1: handover 対象を整理する
書き出す前に、窓口(自分)の context から以下を抽出する:
- 直近の人間との合意・判断
- 採用した方針、却下した選択肢、保留中の検討事項
- 進行中のワーク
- 派遣中のワーカー、その task_id、最新の進捗ステータス
- Pending Decisions(人間に投げて未回答)
.state/pending_decisions.jsonがあれば併読し、register と context の差分を残す
- 次のアクション(窓口視点)
- 次に自分が何をすべきか、誰の返答を待っているか
- 直近の重要なやり取り抜粋
- ユーザーが言った決定的な一言、自分が提案して合意された案など、3〜6 項目程度
Step 2: state.db から構造化情報を取得する
handover に参考情報として埋め込む。書き出し先は sandbox で write 可能な $TMPDIR
(未設定なら /tmp フォールバック)に置く:
python3 -c "
from tools.state_db import connect
from tools.state_db.queries import get_org_state_summary
import json, os
conn = connect('.state/state.db')
out_path = os.path.join(os.environ.get('TMPDIR', '/tmp'), 'secretary-handover-state.json')
with open(out_path, 'w') as f:
json.dump(get_org_state_summary(conn), f, ensure_ascii=False, indent=2, default=str)
print(out_path)
"
シェルリダイレクトで > /tmp/... を使うと、sandbox 環境では /tmp が read-only で
書き込み失敗する。Python 側で TMPDIR を解決してから open(..., 'w') する形が安全。
ここから以下を取り出す:
session.status/session.objectivesession.dispatcher_pane_id/session.dispatcher_peer_idsession.curator_pane_id/session.curator_peer_id(null が正常系。curator はオンデマンド化済みで常駐せず、org-start がStateWriter.CLEARで明示クリアする。null を「欠損」扱いしない)active_runs[](進行中タスク)active_worker_dirs[](生きているワーカーディレクトリ)- 直近の
recent_events上位 3〜5 件
Step 3: handover ファイルを書き出す
書き出し先: .state/secretary-handover.md
既存ファイルがあれば .state/secretary-handover.prev.md にバックアップしてから上書きする:
[ -f .state/secretary-handover.md ] && cp .state/secretary-handover.md .state/secretary-handover.prev.md
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.
- 12d ago First seen · 158 lines · 138 tokens per session scan A bfb5a8a2520a
secretary-handover is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 1,871 once invoked, about $0.0007 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
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
compact-now
Operator-triggered proactive compaction — Chrono externalizes load-bearing state (active decisions, open tasks, next action) to a snapshot + a durable Vault learning note before invoking Claude Code's native /compact, then resumes from the snapshot. Use when the operator says "/compact-now" / "compact now" or when…
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
ai-interview-preparation-coaching
When user asks for interview prep, mock interview, practice questions, behavioral questions, technical interview, HR round, salary negotiation, STAR method, common interview questions, company research, interview tips, confidence building, answer feedback, body language tips, fo…
alephnet-node-operator
A complete social/economic network for AI agents. Provides semantic computing, distributed memory, social networking, coherence verification, autonomous learning, and token economics through an agent-centric API.
agent-lessons-learned-capture
Capture durable lessons from debugging, user corrections, missing capabilities, and repeated workflow friction so future sessions avoid the same mistakes. Use this skill when a non-obvious failure is diagnosed, the user corrects or updates the agent, a workaround or project conv…