Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/s977043/PlanGatenpx agentmods add commands/s977043/plangate/ai-dev-workflowWrote 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.
[](https://agentmods.dev/commands/s977043/plangate/ai-dev-workflow)<a href="https://agentmods.dev/commands/s977043/plangate/ai-dev-workflow"><img src="https://agentmods.dev/badge/commands/s977043/plangate/ai-dev-workflow.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.06761 |
| Opus 5 | $0.00000 | $0.03381 |
| Sonnet 5 | $0.00000 | $0.01352 |
| Haiku 4.5 | $0.00000 | $0.00676 |
Grade A, and why
ai-dev-workflow 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ai-dev-workflow
PlanGate ワークフロー v5 の各フェーズを実行する。
PlanGateガイド: docs/plangate.md
ワークフロー詳細: docs/ai-driven-development.md
ルール: .claude/rules/working-context.md
パス表記の規約(重要): 本コマンド中のパス参照は、Markdown リンクのリンク先 を除き 上流リポジトリのルート基準であり、導入先でそのまま解決できるとは限らない。
リンク先(
](...)の中身)は解決に使わないこと。本文中の[docs/ai/core-contract.md](../../docs/ai/core-contract.md)のような../記法は 上流リポジトリで GitHub 上の相対リンクを成立させるためだけのもので、コマンド ファイルのディレクトリ基準で解決される。導入先(特に plugin)でこれを辿ると plugin root の外へ抜ける。解決には必ず表示テキスト側のパス(上記例ではdocs/ai/core-contract.md)を使い、下表の規則に従うこと。参照の種類ごとに解決先が異なる:
参照の種類 上流リポジトリ 導入先での解決 ルール .claude/rules/**配布される。plugin 導入先は <plugin_root>/rules/**、install.sh --claude導入先は.claude/rules/**ガイド / 契約 doc docs/**3 経路とも配布対象外。導入先の同名パスを探す working context テンプレート docs/working/templates/**3 経路とも配布対象外。導入先の同名パスを探す 作業ディレクトリ( docs/working/TASK-XXXX/**)— 導入先リポジトリ内に本コマンドが生成する(配布物ではない) 参照解決順: (1) 導入先リポジトリの同名パスを探す → (2) 見つからなければ 「正本
<path>を参照できなかった」と明示し、本コマンド内の記述を代替正本 として扱い、推測で内容を補わない。テンプレートが解決できない場合、テンプレート由来の 章立て・スキーマを推測で捏造せず、不足を明示したうえで最小構成で生成する。 plugin root 直下にdocs/を探しに行かないこと: plugin が配布するのはagents/commands/skills/rules等の定義ディレクトリのみでdocs/を 配布対象として認識しないため必ず空振りする(rules/が plugin root 配下で 解決できるのは実際に配布されるからであり、この非対称をdocs/**に持ち込まない)。
引数
$ARGUMENTS に以下の形式で渡される:
TASK-XXXX brainstorm— フェーズ0: Brainstorming(アイデア→設計書の対話的生成)TASK-XXXX plan— フェーズB〜C-2: Plan + ToDo + Test Cases生成 → セルフレビュー → 外部AIレビュー → 指摘反映(一括自動実行)TASK-XXXX exec— フェーズD〜C-4: Agent実行 → 多層防御検証 → PR作成TASK-XXXX status— 現在のフェーズと進捗を表示
Iron Law(不可侵ルール)
違反したら即停止する 7 項目の Iron Law(docs/ai/core-contract.md の Hard constraints が正本)。
| ルール | 意味 |
|---|---|
NO EXECUTION WITHOUT REVIEWED PLAN FIRST |
承認なしにコードを書くな |
NO SCOPE CHANGE WITHOUT USER APPROVAL |
勝手にスコープを変えるな |
NO CODE WITHOUT APPROVED DESIGN FIRST |
設計なしにコードを書くな |
NO MERGE WITHOUT TWO-STAGE REVIEW |
2段階レビューなしにマージするな |
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE |
証拠なしに完了と言うな |
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST |
原因調査なしに修正するな |
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.
- 3d ago First seen · 400 lines · 0 tokens per session scan A 4e4e81498a96
ai-dev-workflow is a command published in the GitHub repository s977043/PlanGate (2 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,761 tokens. 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 2026-09-03.
Other commands, from other repositories
compatibility-audit
Audit all agents for Trinity compatibility by requesting self-diagnostics from each agent.
dispatch-worker
Run one in-session-agent Worker tick (RFC-0041 §4.3.1).
wardley
Create strategic Wardley Maps for architecture decisions and build vs buy analysis.
risk
Create comprehensive risk register following HM Treasury Orange Book principles.
at-dsgvo
You are helping an enterprise architect generate an Austrian Data Protection Assessment — the Austrian-specific GDPR layer applied by the Datenschutzbehörde (DSB) under the Datenschutzgesetz (DSG 2018, BGBl. I Nr. 165/1999 as amended). Run this after /arckit:eu-rgpd to add Austrian obligations that go beyond the EU…
gov-reuse
Discover reusable UK government code before building from scratch.