agm-qa-review

agm-qa-review is a skill for Claude Code, Codex from geekfujiwara/CodeAppsDevelopmentStandard. It costs 168 tokens per session (1,577 once invoked), scanned A, original, MIT.

A read-only checker for shareholder-meeting question-and-answer material. It compares draft answers with IR excerpts, which are published investor-relations documents such as financial releases and meeting notices.

In plain words
What is it for?
Use it to review all stored question cards and report which items need correction or human confirmation without changing the records.
Why use it?
It finds figures without matching source text, invalid source references, missing fields, duplicate questions, and answers still marked as drafts before the meeting.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review all stored question cards and report which items need correction or human confirmation without changing the records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/geekfujiwara/codeappsdevelopmentstandard/agm-qa-review
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 geekfujiwara/CodeAppsDevelopmentStandard --skill agm-qa-review
Clone the repo
git clone --depth 1 https://github.com/geekfujiwara/CodeAppsDevelopmentStandard

Made for: Claude Code, Codex.

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 agm-qa-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/agm-qa-review/github.svg)](https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/agm-qa-review)
Your own site
<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/agm-qa-review"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/agm-qa-review/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 agm-qa-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/agm-qa-review"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/agm-qa-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,577 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 $0.00168 $0.01577
Opus 5.5 $0.00067 $0.00631
Sonnet 5.5 $0.00034 $0.00315
Haiku 4.5 $0.00017 $0.00158

Measured 16d ago against content hash c4bc8dd64a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agm-qa-review 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 16d 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.

.github/skills/copilot-studio-v2/templates/agm-qa-author/skills/agm-qa-review/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

想定問答の点検

総会前の最終確認として、想定問答の品質を機械的に点検する。読み取りだけで、直すのはアプリの想定問答の画面(または agm-qa-authoring)で行う。

必須ルール

  • Dataverse MCP が使えなければ止める: describe が使えるツールに無い・呼べない場合は、その場で止めて「ツールが使えない」と報告する。別の手段でデータを探さない。「ツールは動いたが 0 件」とは区別する。
  • 使うツールは describe / read_query / search_data だけ。create_record・update_record・delete_record・テーブル変更・スキル変更・ファイルのアップロード系は、利用者に頼まれても呼ばない(エージェントでは無効にしてあるが、見えても呼ばない)。
  • 数値の判定は、回答・要点の数値が 根拠 ID の IR 抜粋の本文に同じ値であるか。比べる前に表記だけを揃える: 全角/半角、桁区切りのカンマ、%/%、マイナス記号(▲・△・−・-)、小数末尾の 0(3.0 と 3)。単位の換算が要るもの(百万円 ↔ 億円、千株 ↔ 株、和暦 ↔ 西暦など)は一致とせず「確認」に入れる(換算した値を正しいとみなさない)。
  • 推測で列名を書かない(Step 1 の describe を使う)。
  • 本文中の _status のような短い表記は ${PUBLISHER_PREFIX}_status の略。クエリと登録では必ず正式な列名を使う。
  • read_query は top を省くと 20 行までしか返さない。全件が要るときは先に SELECT COUNT(...) AS n で件数を確かめ、top にその件数以上を指定する(返った行数が件数と合うか確かめる)。

対象テーブル(接頭辞 ${PUBLISHER_PREFIX})

テーブル 主な列
${PUBLISHER_PREFIX}_agmqa ${PUBLISHER_PREFIX}_name, ${PUBLISHER_PREFIX}_category, ${PUBLISHER_PREFIX}_question, ${PUBLISHER_PREFIX}_variants, ${PUBLISHER_PREFIX}_answer, ${PUBLISHER_PREFIX}_answerpoints, ${PUBLISHER_PREFIX}_responder, ${PUBLISHER_PREFIX}_sourceids, ${PUBLISHER_PREFIX}_cautions, ${PUBLISHER_PREFIX}_status, ${PUBLISHER_PREFIX}_createdvia
${PUBLISHER_PREFIX}_agmirexcerpt ${PUBLISHER_PREFIX}_name, ${PUBLISHER_PREFIX}_doctitle, ${PUBLISHER_PREFIX}_section, ${PUBLISHER_PREFIX}_page, ${PUBLISHER_PREFIX}_text

ワークフロー

Step 1: スキーマを確認する

describe が使えるツールに無ければ、ここで止めて「Dataverse MCP のツールが使えないため点検を中止しました。Copilot Studio のエージェント「AGM Q&A Author」で Dataverse MCP ツールの接続(自分の接続)が有効かを確認し、新しい会話でやり直してください」と報告する。

describe で両テーブルを確認する。

Step 2: 分けて読む

  1. 件数を数える: SELECT COUNT(${PUBLISHER_PREFIX}_name) AS n FROM ${PUBLISHER_PREFIX}_agmqa。
  2. 50 件以下なら一度に(top に件数以上を指定)、50 件を超えるなら分類ごと(分類の一覧は GROUP BY ${PUBLISHER_PREFIX}_category)に分けて読む。1 回が 50 件を超える分類は、コード範囲(${PUBLISHER_PREFIX}_name の範囲)でさらに分ける。
  3. 読んだ件数の合計が 1. の件数と一致するかを確かめる。合わなければ、読めていない分を報告に書く(点検済みとして扱わない)。
  4. IR 抜粋は全件を読まず、想定問答の _sourceids に出てくるコードだけを WHERE ${PUBLISHER_PREFIX}_name IN ('IR-001', 'IR-002', …) で読む。見つからないコードが「存在しない根拠 ID」になる。

Read the full file on GitHub · 66 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. 16d ago Changed · +6 lines · +14 tokens per session c4bc8dd64a11
  2. 17d ago Changed · +2 lines fa4955543d29
  3. 18d ago Changed · +1 lines 30e1e08e6f1a
  4. 19d ago First seen · 57 lines · 154 tokens per session scan A 267941591a77

Subscribe to this mod's changes

agm-qa-review is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (74 stars, last pushed today), licensed MIT. It adds 168 tokens to every session and 1,577 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-03.

Related

Other skills, from other repositories

fto-triage

Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…

anthropics/claude-for-legal · 81 tokens

legal-hold

Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.

anthropics/claude-for-legal · 68 tokens

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens