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.
npx skills add ishida-supsys/oretachi --skill app-startergit clone --depth 1 https://github.com/ishida-supsys/oretachiWrote 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/skills/ishida-supsys/oretachi/app-starter)<a href="https://agentmods.dev/skills/ishida-supsys/oretachi/app-starter"><img src="https://agentmods.dev/badge/skills/ishida-supsys/oretachi/app-starter/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.
<a href="https://agentmods.dev/skills/ishida-supsys/oretachi/app-starter"><img src="https://agentmods.dev/badge/skills/ishida-supsys/oretachi/app-starter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00109 | $0.12182 |
| Opus 5.5 | $0.00044 | $0.04873 |
| Sonnet 5.5 | $0.00022 | $0.02436 |
| Haiku 4.5 | $0.00011 | $0.01218 |
Grade B, and why
app-starter 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 2d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const res = await net.fetch('https://api.example.com/v1/items?limit=10', { method: 'POST', // GET / HEAD / POST / PUT / PATCH / DELETE / OPTIONS(既定 GET) How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
app-starter スキル
React アーティファクトに manifest(app) を付けると、権限を申請して動く「アプリ」になる。
このスキルは同梱の最小アプリ(通知の一覧と、テスト通知の送信)を生成する雛形で、生成物は
そのまま自分のアプリへ書き換えて使う。
アプリの性質(先に知っておくこと)
- manifest だけでは何も動かない。 AI が書いた manifest は信頼されない。ユーザーがアーティファクトウィンドウの起動画面で起動し、承認ダイアログで許可して初めて権限が有効になる。承認の前に、あなたが API を呼べるようにする手段は無い。
- 宣言したものだけが使える。 manifest に無い権限(ツール・越境先・メモリー)は、承認済みでも常に拒否される。
- 通常のビューアでは動かない。
app付きのアーティファクトは起動画面を出す。実行は承認後の常駐ウィンドウの中(sandboxiframe)。Web ビューアでは起動できない。 - 今の版で書ける権限は
mcp(toolsとtargets)、memory(maxBytes必須)、fs、db(下記)、aiTerminal(agentsとmaxConcurrent必須)、network(allowに URL プレフィックス。下記)、subWindow(専用サブウィンドウ。下記)、audio(マイクの音声入力。下記)、media(動画・音声の再生。下記)だけ。wasmは未対応で、書くとエラーになる。 - コード(content / modules)を更新しても再承認は要らず、起動中なら承認を保ったまま iframe がリロードされる(フルリロード。メモリー以外の JS の状態は失われる)。権限(manifest の
permissions)を変えたときだけ、起動中なら直ちに再承認のダイアログが出る。承認までは旧権限のまま動き(リロードもされない)、新しい権限が要る呼び出しは拒否される。承認でリロード、拒否で停止。
manifest
<SKILL_DIR>/app.json が雛形。
{
"name": "表示名",
"description": "説明",
"version": "1.0.0",
"permissions": {
"mcp": {
"tools": ["oretachi_list_worktree_notifications", "notify_worktree"],
"targets": []
},
"memory": { "maxBytes": 65536 },
"fs": {
"read": ["worktree://docs/", "artifact://"],
"write": ["worktree://out/", "artifact://data/"]
}
}
}
mcp.tools: 呼びたいツールだけを書く。呼べるのはartifactツールの説明にある一覧の部分集合。oretachi_write_terminal/oretachi_send_keys/oretachi_answer_prompt/oretachi_add_taskは**ユーザーと同等の権限(任意コマンド実行)**として、承認ダイアログで強調される。本当に必要なときだけ宣言する。mcp.targets: 他のワークツリーへ届かせたいときだけ書く(省略 = 自ワークツリーのみ)。ワークツリー名 / ID、*、workgroup:<ID か名前>、repo:<リポジトリ名>。ワイルドカードは最も強い警告になる(今後作られるワークツリーも含み、メインのクローンの端末にも届く)。名前で書いたワークツリーは承認時に ID へ固定される。越境には、これに加えて既存の購読(oretachi_subscribe_worktree)も必要。memory.maxBytes: メモリーを使うなら必須(1〜1048576 バイト。書き込み後の JSON のバイト数で数える)。宣言が無い・0 以下・上限超過の manifest は拒否される。承認ダイアログに最大サイズが出る。上限を下げる変更も再承認になり、既存データが新しい上限を超えていても消えない(収まらない書き込みだけ拒否、読み取りは可)。
What ships with it
2 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.
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.
- 2d ago Changed · +23 lines 9136571942f5
- 4d ago First seen · 279 lines · 109 tokens per session scan B c2f35f8fe46f
app-starter is a skill published in the GitHub repository ishida-supsys/oretachi (2 stars, last pushed 3d ago), licensed MIT. It adds 109 tokens to every session and 12,182 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-17.
Other skills, from other repositories
add-new-agent-support
Add a new agent (tool) support to agent-command-sync following the registry pattern.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.
moai-domain-frontend
Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture. Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management.
neo4j-snowflake-graph-analytics-skill
Run Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra, KNN, Node2Vec, FastRP, GraphSAGE) directly inside Snowflake without moving data. Use when running graph algorithms against Snowflake tables via the Neo4j Snowflake Native App ("GDS Snowflake", "graph algorithms in Snowflake", "Neo4j Graph…
neo4j-aura-graph-analytics-skill
Serverless Aura Graph Analytics (AGA) GDS Sessions — covers GdsSessions, AuraGraphDataScience, AuraAPICredentials, DbmsConnectionInfo, SessionMemory, getorcreate, remote graph projection with gds.graph.project.cypher and gds.graph.project.remote, gds.graph.project.native, gds.graph.construct, graphdatascience client…