A skill for creating, publishing, and running Copilot Studio workflows through Microsoft's management APIs. Copilot Studio is Microsoft's tool for building conversational agents and workflows, while Dataverse stores related business data.

Use it to create a new workflow from a trusted template, configure its connections, perform an approved dry run, and verify the result.

It turns a repeatable workflow definition into a controlled process with environment checks, approval gates, and execution verification instead of making untracked changes.

How geekfujiwara/CodeAppsDevelopmentStandard configures Claude Code an

Reuse

Borrowing it

Nothing to install: this file belongs to geekfujiwara/CodeAppsDevelopmentStandard. 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/geekfujiwara/CodeAppsDevelopmentStandard/main/.github/skills/agent-flows/SKILL.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/agent-flows/github.svg)](https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/agent-flows)

Your own site

<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/agent-flows"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/agent-flows/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/agent-flows"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/agent-flows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,797 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.

Model	Per session	Once invoked
Fable 5.1	$0.00096	$0.02797
Opus 5.5	$0.00038	$0.01119
Sonnet 5.5	$0.00019	$0.00559
Haiku 4.5	$0.00010	$0.00280

Measured 17d ago against content hash 8508f9fac45f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-flows 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 17d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/agent_flow.py, scripts/conversation_contract.py, scripts/inspect_agent_node.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/agent-flows/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Flows: 新 UI Workflow の API 構築

標準対象は、Copilot Studio Workflow の Dataverse レコード作成/更新トリガー + 既存 Agent ノードで発行済み v2 エージェントを起動する経路。Code Apps を介さないバックグラウンド処理にも使う。手動 Start + 外部ツールなし inline Agent の CLI は、new UI Workflow の作成・公開・実行契約を検証する補助経路であり、既存 v2 の呼び出し成功を代用しない。一般クラウドフローは power-automate、既存 bot の構築は copilot-studio-v2 を使う。

標準経路: Dataverse トリガー + 既存 v2 Agent ノード

対象 v2 を公開し、対象環境、bot schema、利用スキル/MCP、実行主体を確定する。
Copilot Studio の Workflows で Dataverse の行追加・変更トリガーを選び、テーブル、scope、filter columns、filter expression を最小化する。
Agent ノードで 既存の発行済み v2 を明示選択し、固定された業務指示とトリガー行の必要項目だけを入力へ割り当てる。
構造化出力を検証してから Dataverse へ書き戻す。元行の再更新で自己再帰しない終了状態と条件を設ける。
Review 後に公開し、専用テスト行を 1 件作成または更新して、trigger / Agent / write-back の run と業務出力を照合する。

製品 UI の Agent ノードが標準の authoring 経路。観測した shared_agentnode API Hub 契約を使って定義を推測生成しない。接続所有者の権限を要求者本人の権限と表現せず、ACP/DLP、クレジット、重複起動、タイムアウト後の再照合を受入項目に含める。API 側の検証境界は Agent ノードの診断を参照する。

補助経路: 手動 Start + inline Agent の API ライフサイクル

既存の最小フローを信頼済みテンプレートとして読み、同一ソリューション内へ別名作成する。モデルと接続参照はテンプレートから継承する。既存フローの更新・削除は行わない。

Step 1: 対象と実行ゲートを確認する

standard の共通認証と .env を使い、通常は環境・DLP / ACP の事前診断を挟まず作成へ進む。使用コネクタは shared_agentnode。明示依頼時・障害時だけ admin の権限確認付き復旧で必要範囲を診断する。権限不足なら管理 API を繰り返さず管理者へ依頼する。ポリシー変更は別の明示承認で行う。設定の読み戻しと実行基盤の判定は別ゲートとして記録する。

作成名、テンプレート、ソリューション、モデル、固定応答、実行回数をユーザーに提示する。テナント固有値は references/.env.example に従い .env へ置く。既存テンプレートに Start / Agent / edge / nodeActionMapping / 接続参照が揃っていることを CLI で検証する。

Step 2: API で別名作成する

python .github/skills/agent-flows/scripts/agent_flow.py create --report-file .local/agent-flow/create-plan.json
python .github/skills/agent-flows/scripts/agent_flow.py create --apply --expected-hash <approved-hash> --report-file .local/agent-flow/create-result.json

create-plan.json の定義と影響を確認してから適用する。計画ハッシュは環境、ソリューション、テンプレート定義、接続参照、作成名に結び付く。書き込み直前に再読み取りする。 created-verified の flowId を .env の AGENT_FLOW_ID に設定する。新規名の重複を拒否し、category=5 / type=1 / modernflowtype=1 と Draft を読み戻し検証する。

Read the full file on GitHub · 143 lines

Files

What ships with it

16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

17d ago Changed · -3 lines 8508f9fac45f
1mo ago Changed · +30 lines · +8 tokens per session a6d3515f5b10
1mo ago First seen · 116 lines · 88 tokens per session scan A 0497f0230ede

Subscribe to this mod's changes

agent-flows is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 2,797 once invoked, about $0.0004 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 2026-09-10.

Building agents automation

agent-flows next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-flowsgeekfujiwara/CodeAppsDevelopmentStandard	Skill	78	yesterday	MIT	A	96	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

CodeAppsDevelopmentStandard: Skill for Claude Code