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 agentmods add instructions/tsunamayo7/helix-pilot/claude-mdgit clone --depth 1 https://github.com/tsunamayo7/helix-pilotWrote 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/instructions/tsunamayo7/helix-pilot/claude-md)<a href="https://agentmods.dev/instructions/tsunamayo7/helix-pilot/claude-md"><img src="https://agentmods.dev/badge/instructions/tsunamayo7/helix-pilot/claude-md.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 | $0.00471 | $0.00471 |
| Opus 5 | $0.00235 | $0.00235 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
helix-pilot CLAUDE.md 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 5d 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.
What it actually says
CLAUDE.md — helix-pilot
プロジェクト概要
helix-pilot は、ローカル Vision LLM (Ollama) でホスト OS 上のウィンドウを直接操作する GUI 自動操作 MCP サーバーです。GitHub 公開してスター獲得を目指します。
技術スタック
- Python 3.12 + uv（パッケージ管理）
- FastMCP（MCP サーバー実装）
- Ollama Vision LLM（画面解析: mistral-small3.2 等）
- PyAutoGUI / Windows SendInput（操作実行）
共有記憶（Mem0）
Mem0 MCP サーバーが接続されています。
Qdrant コレクション名は mem0_shared で全ツール統一（詳細は AGENTS.md 参照）。
- 過去の決定や方針を確認したい時は
search_memoryで検索すること - ユーザーが「覚えておいて」と言ったら
add_memoryで保存すること
開発ルール
- 日本語で応答すること
- コード・コミットメッセージ・README は英語
- UTF-8 エンコーディング必須
- テストは pytest で作成
uv run pytestでテスト実行uv run python -m py_compile <file>で構文チェック
競合情報
- UI-TARS Desktop (ByteDance): GUI アプリ。MCP 対応済み。ただし CLI ではない
- Peekaboo: CLI + MCP + Ollama だが macOS 専用
- Cua: VM 内操作。ホスト OS 直接操作ではない → Windows + CLI + MCP + Ollama Vision の組み合わせは helix-pilot のみ
ゴール
- FastMCP でMCPサーバーとして実装
- GitHub に公開（英語 README）
- Stars 獲得 → 転職活動に活用
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.
- 5d ago First seen · 44 lines · 471 tokens per session scan A f1f847ed28fc
helix-pilot CLAUDE.md is an instructions file published in the GitHub repository tsunamayo7/helix-pilot (4 stars, last pushed 4mo ago), licensed MIT. It adds 471 tokens to every session, about $0.0024 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
Shinken CLAUDE.md
Instructions for Meirtz/Shinken, covering claude.md — guide for ai coding sessions in this repo, ⛔ the one hard rule: this is a public open-source project, layout, development commands and architecture (how the pieces connect).
trope-cua AGENTS.md
Instructions for tropeai/trope-cua, covering repository guidelines, collaboration & git safety, repository layout, quick commands and engineering guidelines.
gui_agent AGENTS.md
Instructions for leandre755/gui_agent, covering git-context-controller (gcc) protocol, 3.1. .gcc/main.md template, current project context, 🏆 major milestones (archived epics) and 🎯 objective.
glovebox-mcp AGENTS.md
Instructions for segentic-lab/glovebox-mcp, covering glovebox-mcp — instructions for the agent, responses: read ok and fix, mental model, the core loop and grounding: how to know where to click.
agent-computer-use-mcp AGENTS.md
AGENTS.md instructions for astraclawteam/agent-computer-use-mcp, covering agent worker rules, read order, repository purpose, project structure and branch and pr rules.
oculos AGENTS.md
Instructions for huseyinstif/oculos, covering oculos — ai agent instructions, core workflow, discovery, list all windows and search for elements (preferred — fast).