claude-org-ja: Skill for Claude Code

.claude/skills/runtime-release-with-paired-ja-sync/SKILL.md

runtime-release-with-paired-ja-sync is a skill for Claude Code from suisya-systems/claude-org-ja. It costs 142 tokens per session (7,429 once invoked), scanned B, original, MIT.

A release checklist for publishing the runtime package to PyPI, the Python package registry, and synchronising the related Japanese-side project.

In plain words
What is it for?
It helps plan delegation, prepare release guidance, and land the runtime release together with its required Japanese-side synchronisation.
Why use it?
It prevents a runtime release from leaving copied schemas, test expectations, permissions, or example settings out of date. It plans the paired update before release so the follow-up work is not discovered only after CI fails.

Skill for Claude Code

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

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(python tools/gen_delegate_payload.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/runtime-release-with-paired-ja-sync/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 runtime-release-with-paired-ja-sync

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/runtime-release-with-paired-ja-sync"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/runtime-release-with-paired-ja-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,429 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00142 $0.07429
Opus 5 $0.00071 $0.03714
Sonnet 5 $0.00028 $0.01486
Haiku 4.5 $0.00014 $0.00743

Measured 6d ago against content hash 45142ba12d5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

runtime-release-with-paired-ja-sync 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

settings(`~/.claude/settings.json` 等)は CI 対象外。CI green でも local は stale に
.claude/skills/runtime-release-with-paired-ja-sync/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

runtime-release-with-paired-ja-sync: runtime リリース+ja-side 同期ワークフロー

claude-org-runtime のリリースは PyPI 発行を経由して claude-org-ja の attention watcher integration test に必ず波及する。 本 skill はそのカスケードを「リリース起票時に予測し、paired ja-sync を同一 Secretary セッション内で land しきる」ためのチェックリスト。

本 SKILL のスコープ: 窓口が runtime release 系タスクを受領した際の 委譲設計と paired ja-sync 計画。実 commit / テスト修正はワーカー側であり本 skill ではない。

なぜこの skill が必要か

claude-org-runtime 側で DEFAULT_NOTIFY の値や classifier 語彙・role_configs_schema.json (runtime 同梱 schema。ja 側ミラーが tools/org_extension_schema.json)の項目を 更新してリリースすると、PyPI publish 後に claude-org-ja 側の以下が同時に古くなる:

  • tests/test_attention_runtime_integration.py の expectation
  • tools/org_extension_schema.json のバイト一致コピー
  • .claude/skills/org-setup/references/permissions.md の projection
  • tools/templates/attention.example.json の severity / TTL

過去のリリースサイクルでは「runtime release は無事だったが ja-side CI が翌日に red」になる カスケードが観測されており、これを毎回観測してから後追いで直すと、

  • Secretary セッションが切れて context を失う
  • ja-side worker に「なぜこの変更が必要か」の経路を再構築させる
  • 修正の paired-ness が暗黙的になり次回も同じカスケードを踏む

の 3 重コストが発生する。本 skill は paired-ness をリリース起票時に明示化し、 同一 Secretary セッション内で land しきる規律を提供する。

発動条件

以下のいずれかに該当する場合、Secretary は org-delegate より前にこの skill を確認する:

  • task_id に release を含む、または vX.Y.Z 形式のタグを発行するリリース系タスク
  • chore release 系のユーザー指示プロンプト(「runtime のリリース」「PyPI 上げ」等)
  • runtime 側の DEFAULT_NOTIFY / classifier mapping / role_configs_schema.json / attention テンプレのいずれかを触る変更が land 寸前
  • runtime 側の role_configs_schema.json にある required_allow / required_deny / required_hook_scripts / required_hooks への追加・変更を含むリリース。 これらは「settings ファイルに必ず存在すべき項目」を増やす変更であり、runtime 側 CI が full green・Codex 指摘ゼロでも ja 側の安全性は証明されない。ja は floating pin (>=X,<0.2)のため PyPI 公開の瞬間から ja 側の 2 系統のチェックが赤くなる: (a) tools/check_role_configs.py — permissions projection と tracked settings を schema との整合で検証する。CI 配線は --include-worker-settings.github/workflows/tests.yml)で、machine-local settings(~/.claude/settings.json 等)は CI 対象外。CI green でも local は stale に なり得るため、merge 後に /org-setup で反映する。なお --include-local は schema に settings_paths が宣言された role の settings.local.json しか見ず(user_commonsettings_paths: [])、参照 schema も checked-in の ja ミラーなので、home レベル (~/.claude/settings.json)の allowlist 検証ゲートにはならない — user_common の 現物反映は /org-setup 適用後に settings 現物を直接確認する。 (b) tools/check_runtime_schema_drift.py — ja の tools/org_extension_schema.json と runtime 同梱 role_configs_schema.json の、ja 固有節を strip した上でのバイト比較 (CI で実行。installed runtime が pin window 内なら skip されない)。 実例: renga capability probe server_inforequired_allow 追加 (2026-08-08, runtime Issue #161)で露見

Read the full file on GitHub · 373 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. 6d ago Changed · +17 lines 45142ba12d5c
  2. 11d ago First seen · 356 lines · 142 tokens per session scan B 512ec2796994

Subscribe to this mod's changes

runtime-release-with-paired-ja-sync is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 5d ago), licensed MIT. It adds 142 tokens to every session and 7,429 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.