claude-org-ja: Skill for Claude Code

.claude/skills/org-down/SKILL.md

org-down is a skill for Claude Code from suisya-systems/claude-org-ja. It costs 114 tokens per session (3,807 once invoked), scanned A, original, MIT.

A full shutdown procedure for an organization of coding-agent processes, including its broker daemon, which coordinates them.

In plain words
What is it for?
Use it when asked to completely stop the organization, including its daemon. It first saves state and stops managed helper processes and panes, then stops the broker when that transport is in use.
Why use it?
It prevents the coordinator from being stopped before work is saved and queued messages are handled. It also distinguishes a full shutdown from a temporary pause that leaves the daemon running.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; 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 runs a file that does not travel with it, so clone the repository first. The line is Bash(bash tools/journal_append.sh:*).

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/org-down/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 org-down

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/org-down"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/org-down.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,807 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 warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 20
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Excessive Agency · line 161
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • medium Agent Snooping · line 72
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00114 $0.03807
Opus 5 $0.00057 $0.01903
Sonnet 5 $0.00023 $0.00761
Haiku 4.5 $0.00011 $0.00381

Measured 10d ago against content hash 05ee8672d9a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

org-down 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.

.claude/skills/org-down/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

org-down: 組織の完全停止(broker daemon まで)

/org-down/org-suspend を完走してから claude-org-runtime org down を呼び、broker daemon まで含めて組織を完全に停止する統合終了スキルである。

責務境界(最重要): claude-org-runtime org down(broker daemon 停止)を呼ぶのは 本スキルだけである。/org-suspend は「状態保存 + ja 管理下の補助 プロセス(dashboard / secretary_queue_watcher / attention watcher)とペインの停止」までで 止まり、daemon は走らせたまま(/org-start で再開する前提の中断)にする。/org-down は suspend の成功を確認できたときにのみ daemon 停止へ進む。順序を守るのは、未保存の状態を 残したまま daemon を落とすと復旧経路(check_messages での drain 等)ごと失われるため。

runtime 側の pre-flight 検出(org down 前に生存ワーカー / 未 drain キューを警告する機能)は runtime#142 の担当で、本スキルは 触れない。本スキルは runtime の org down呼ぶだけ

輸送層の前提: claude-org-runtime org down は broker daemon を落とすコマンドで、broker transport(ORG_TRANSPORT 無設定=コード既定 broker、または明示 broker)でのみ意味を持つ。 renga フォールバック(ORG_TRANSPORT=rengarenga --layout ops 起動)では daemon の概念が 無いので、Step 3 は skip して「renga では daemon 停止は不要」と案内する。jud断は Step 3 の transport 確認で行う。

Step 1: /org-suspend を完走する

/org-suspend の全 Phase を順に実行する(Phase 1 状態収集 → Phase 2 未応答スクレイプ → Phase 3 状態書き込み → Phase 3.6 secretary_queue_watcher 停止Phase 3.7 attention watcher 停止(ペイン teardown 前)→ Phase 4 全ペイン停止)。

ただし Phase 3.5 の dashboard blind kill は本スキル Step 2 の stale-pid-safe 停止に差し替える (org down 直前の完全停止では、pid recycle された stale な dashboard.pid を無検証 kill すると 無関係プロセスを撃つため。誤 kill 防止)。他の Phase はそのまま実行する。

suspend 成功の確認(gate) — 次を満たしたときのみ Step 2 / Step 3 へ進む:

  • .state/state.dbsession.statusSUSPENDED になっている(Phase 3 の DB write が成立)
  • Phase 4 が全対象ペイン(ワーカー / ディスパッチャー / 存在した場合のキュレーター)について停止を 「消滅済み」として確定している。ここで確定と読んでよいのは .claude/skills/org-suspend/SKILL.md Phase 4 が F-1(同 Phase 1 手順 1 の「フォーカス前提(F)」)に従って自ら出した結論だけで、 本 gate のために org-down 側で list_panes を引き直して判定をやり直さない — 生存判定の正本は org-suspend 側にあるので、その条件文をここに再掲せず確定結果を読むだけにする(list_panes に 居ないことを単独で停止の根拠にする単段の読み替えを本スキルに置かない)。Phase 4 が自らの停止確認の ために行う再列挙(同 Phase 4 停止手順 1 の台帳最新化 / Pass 2 の残存確認)は org-suspend 側の手順 なので、Step 1 の「全 Phase を順に実行する」どおりそのまま実行する
  • Phase 4 が「停止できなかった / 判定できなかったピア」を 1 件も残していない。生死を判定できなかった ピアは、Phase 4 の停止手順が「残存または判定不能なら、閉鎖扱いにせず journal に記録して人間に報告 する」に従って pending に残すので、gate の入口は同 Phase 4 手順 7 の最終報告になる — pendingunresolved が両方空で「組織を中断しました」と言い切れた形だけが gate 成立である。 「組織を部分的に中断しました(停止しきれていないペインがあります)」の形(停止できなかったワーカー / role が判定できず対象外にしたピア / 他タブに見えたが自組織と確認できず対象外にしたピアのいずれかが 残る)は gate 不成立として扱う
  • 最後の窓口ペインが残っているのは gate の妨げにならない(窓口は自分自身を close できない。同 Phase 4 「最後のペイン (窓口) の扱い」)

Read the full file on GitHub · 197 lines

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. 10d ago First seen · 197 lines · 114 tokens per session scan A 05ee8672d9a7

Subscribe to this mod's changes

org-down is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 4d ago), licensed MIT. It adds 114 tokens to every session and 3,807 once invoked, about $0.0006 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.