agentmods.dev

rpgdev AGENTS.md

Repository instructions for RPGDev, a desktop overlay that turns coding-agent activity into a small role-playing game. They describe its platforms, architecture, commands, firewall setup, and project-specific checks.

In plain words
What is it for?
Use them when changing RPGDev, checking its desktop interface, working with hooks or the shared hub, testing platform-specific behavior, or preparing an npm release.
Why use it?
They help an agent follow RPGDev’s unusual desktop and Windows/WSL2 setup instead of treating it like an ordinary browser application.

Instructions file for CodexOpenCode

1 18d ago B scan 12,627 tokens original MIT
View the source file kitepon/rpgdev
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.

agentmods
npx agentmods add instructions/kitepon/rpgdev/agents-md
Clone the repo
git clone --depth 1 https://github.com/kitepon/rpgdev

Made for: Codex, OpenCode.

Per session 12,627 This file is loaded in full into every session.
When invoked 12,627 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
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 $0.12627 $0.12627
Opus 5 $0.06313 $0.06313
Sonnet 5 $0.02525 $0.02525
Haiku 4.5 $0.01263 $0.01263

Measured yesterday against content hash 71b77a8f66f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

rpgdev AGENTS.md 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 yesterday.

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.

`~/.claude/settings.json`（**ユーザー全体の `settings.local.json` は Claude Code に読まれない**＝v0.6.0 のバグ。v0.6.1 で修正）。
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex when working with code in this repository.

概要

RPGDev は Codex / Claude Code の Hook イベントを、小さな RPG 風デスクトップ ウィンドウの演出に変換するツール。モンスターはツール使用ごとに一定確率で出現する ランダムエンカウントで、ツール利用が攻撃になる。撃破条件は出現時に紐づいた TODO の 有無で変わる（攻撃5回／ターン終了で討伐、または紐づき TODO の完了で討伐）。TODO は クエスト一覧として表示しつつ、紐づきエンカウントの討伐トリガーにもなる。 macOS / Windows（WSL2 含む）対応、Node 20+、全体が ESM ("type": "module")。JS のビルド/バンドル工程はなく、TypeScript も使っていない。 デスクトップ窓だけがプラットフォーム依存（macOS=Swift+WKWebView / Windows=C# WinForms+WebView2 / WSL2=Windows ホスト側に interop で同窓を起動 / 素の Linux は窓なし＝npm run web）。Windows/WSL2 は サーバ（ハブ）も窓も Windows ホスト上の単一インスタンスに集約＝ハブ1つを Windows ローカルのファイルから起動して 0.0.0.0 で待ち受け（窓は localhost 接続、WSL2 フックはホストの WSL アダプタ IP 経由）、Windows でも WSL2 でも同じ1つの 共有冒険を動かす（セットアップ順非依存。要：WSL→ホスト inbound を許可する標準 Defender ＋ Hyper-V の両層の ファイアウォール許可規則＝rpgdev setup-firewall が適用。標準は RemoteAddress 172.16/12、Hyper-V は WSL vmCreator の既定 Block の例外）。詳細は docs/02_windows-wsl.md。 文書の入口は docs/00_overview.md。設計正典は docs/01_design-todo-rpg.md。

RPGDev 固有の検証ルール

RPGDev は macOS デスクトップアプリ / overlay アプリであり、ブラウザアプリではない。 ユーザーが明示的に依頼しない限り、Browser プラグイン、Playwright、ブラウザ表示確認、 npm run web を検証の主経路にしない。UI確認が必要な場合は npm start、 npm run build:desktop、npm run server + RPGDev overlay / デスクトップウィンドウ、 または reducer テストと demo Hook の流れで確認する。/ のフル Web ビューは補助ビューであり、 RPGDev の本体として勝手に扱わない。

コマンド

npm test                              # node:test の全テストを実行
node --test test/adventure-state.test.mjs   # 単一テストファイルを実行
node --test --test-name-pattern "spawns a monster"  # 名前で単一テストを実行

npm run server                        # HTTP サーバのみ起動（ウィンドウなし）
npm run web                           # サーバ起動 + ブラウザでフル Web ビューを開く
npm start                             # ビルド + macOS デスクトップウィンドウを起動
npm run build:desktop                 # Swift ウィンドウのコンパイルのみ（起動しない）
npm run render:bgm                    # BGM 7トラックを再生成（public/audio の BGM wav）
npm run render:sfx                    # 攻撃/帰還/被弾の効果音(SFX)を再生成
npm run demo                          # 起動中のサーバに対して擬似 Hook シーケンスを流す
npm run trace                         # 演出トレースを解析（二連続/欠落/取りこぼしの検出。docs §10）

Read the full file on GitHub · 391 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. yesterday First seen · 391 lines · 12,627 tokens per session scan B 71b77a8f66f5

Subscribe to this mod's changes

rpgdev AGENTS.md is an instructions file published in the GitHub repository kitepon/rpgdev (1 stars, last pushed 18d ago), licensed MIT. It adds 12,627 tokens to every session, about $0.0631 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.

Git and workflowPlanningTestingai-agentsclaude-codeclicodexcodex-clideveloper-tools
Related

Other instructions, from other repositories

apm python.instructions.md

Python development guidelines.

microsoft/apm · 78 tokens

copilot-proxy-api CLAUDE.md

Instructions for voidsteed/copilot-proxy-api, covering claude.md, project overview, common commands, architecture and entry points & cli structure.

voidsteed/copilot-proxy-api · 3,899 tokens

CodexPotter AGENTS.md

Instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.

breezewish/CodexPotter · 306 tokens

OpenMicro AGENTS.md

Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.

stephenleo/OpenMicro · 123 tokens

squarebox CLAUDE.md

Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.

SquareWaveSystems/squarebox · 1,772 tokens

SubFrame AGENTS.md

Instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.

Codename-11/SubFrame · 3,973 tokens