regwatch

regwatch is a skill for Claude Code from muji-j/jp-power-tools. It costs 215 tokens per session (1,461 once invoked), scanned A, original, MIT.

A monitoring skill for official changes to Japan’s electricity-market rules and committee decisions.

In plain words
What is it for?
Use it to find new official publications, summarize their industry impact, detect outdated dates or numbers, and flag items needing manual confirmation.
Why use it?
It helps track regulatory updates in a market where prices, procedures, deadlines, and requirements can change frequently.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the jp-power plugin — 5 skills, 7 commands shipped together

Good fit Use it to find new official publications, summarize their industry impact, detect outdated dates or numbers, and flag items needing manual confirmation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/muji-j/jp-power-tools/regwatch
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add muji-j/jp-power-tools --skill regwatch
Clone the repo
git clone --depth 1 https://github.com/muji-j/jp-power-tools

Made for: Claude Code.

Or install jp-power, the plugin that ships this one along with the rest of its 5 skills, 7 commands.

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 regwatch

README.md
[![agentmods](https://agentmods.dev/badge/skills/muji-j/jp-power-tools/regwatch/github.svg)](https://agentmods.dev/skills/muji-j/jp-power-tools/regwatch)
Your own site
<a href="https://agentmods.dev/skills/muji-j/jp-power-tools/regwatch"><img src="https://agentmods.dev/badge/skills/muji-j/jp-power-tools/regwatch/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 regwatch

Your own site · 80×15
<a href="https://agentmods.dev/skills/muji-j/jp-power-tools/regwatch"><img src="https://agentmods.dev/badge/skills/muji-j/jp-power-tools/regwatch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,461 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.
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 $0.00215 $0.01461
Opus 5 $0.00108 $0.00731
Sonnet 5 $0.00043 $0.00292
Haiku 4.5 $0.00021 $0.00146

Measured 10d ago against content hash 17c780f1a1c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

regwatch 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.

jp-power/skills/regwatch/SKILL.md · 39 lines

What it actually says

電力市場ドメイン — 制度ウォッチ (regwatch)

官の公式公表物(METI 制度検討作業部会・電力安定供給ワーキンググループ・中長期取引市場検討ワーキンググループ・OCCTO 委員会・EGC 制度設計・監視専門会合)を定期取得し、新規分の業界影響を汎用サマリで提供する。制度改正が頻繁なこのドメインで「何が変わったか」を追う。

コマンド

  • /power-news — 新規公表物を取得し汎用の業界影響サマリを生成(scripts/power_watch.py)。
  • /power-verify — 変更検知+スキル内容(URL・数値・日程)の突合で更新候補を提示。

監視対象の審議体(2026-07時点。制度検討作業部会からの重心移動に注意)

容量市場の需要曲線、需給調整市場のΔkW上限価格など、実質的な決定の場が制度検討作業部会から電力安定供給ワーキンググループ(次世代電力・ガス事業基盤構築小委員会の下)へ移っている。監視対象として追加で押さえるべき審議体:

  • 電力安定供給ワーキンググループ: 第1回2026-05-13/第2回2026-06-05/第3回2026-06-23/第4回2026-07-14/第5回2026-07-29
  • 中長期取引市場検討ワーキンググループ: 第1回2026-06-02/第2回2026-06-25
  • 料金制度専門会合: 託送料金レベニューキャップ第2規制期間(2028年度開始)。一般送配電8社が「託送供給等に係る収入の見通しの変更承認申請」を提出し第76回で審査中(要確認)
  • 電力システム改革の検証を踏まえた制度設計ワーキンググループ

注意(実測事実): www.meti.go.jpwww.egc.meti.go.jp は AWS WAF の JS チャレンジ(HTTP 202・本文0バイト)で自動取得が通らないことがあり、これらの審議会は手動確認が必要になる場合がある。ΔkW上限価格については EPRX の上限価格ページhttps://www.eprx.or.jp/information/post.php)が1次公表元で自動取得可能。

要注意・直近の監視対象(2026-07時点)

markets.md に「募集要綱案・要確認」等で記載した未確定項目は、公表され次第 /power-verify で反映すること。特に:

  • 実需給2027年度追加オークションの約定結果(公表期日2026年7月末頃の予定、2026-07-30時点で未公表)
  • 実需給2030年度メインの約定結果(応札2026-10-13〜10-23、公表2026年12月頃予定)。募集要綱・Net CONE(20,911円/kW)・上限価格(31,366.5円/kW)は2026-07-30に確定公表済み
  • 長期脱炭素電源オークション第4回(応札年度2026年度)の募集要綱確定(2026年9月頃予定、意見募集は2026-07-21〜08-03)
  • 需給ひっ迫時補正インバランス料金改正(2026-10-01施行予定)の官報公布(2026-07-30時点で未掲載。詳細は ops/references/calc.md 参照)
  • 電気事業法改正(令和8年法律第68号、2026-07-24公布)の施行政令・省令。卸電力取引所が短期/中長期/需給調整の3節構成となり、いずれも経産大臣の指定制になる
  • 非化石価値取引の2027年度・2028年度の価格制限(第二十四次中間とりまとめ 2026-05-01、要確認)
  • 経過措置料金(電気)の指定解除。監視委が年1回判定し、2026-06-19時点で沖縄エリアのみ解除基準を満たす蓋然性あり

参照

用語は jp-power:core../core/references/terms.md)、市場ルールは jp-power:markets、情報源は jp-power:data(sites.md)。

鉄則

公開情報のみ。会社固有の解釈は含めない(汎用の業界影響のみ)。要約はLLMのため原文リンク併記・要確認。取得はブラウザUA、失敗ソースは取得不可と明示。

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 · 39 lines · 215 tokens per session scan A 17c780f1a1c8

Subscribe to this mod's changes

regwatch is a skill published in the GitHub repository muji-j/jp-power-tools (1 stars, last pushed 1mo ago), licensed MIT. It adds 215 tokens to every session and 1,461 once invoked, about $0.0011 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.