agentmods.dev

Project-Pilot: Instructions file for Claude Code

CLAUDE.md

Project-Pilot CLAUDE.md is an instructions file for Claude Code from Kaine665/Project-Pilot. It costs 1,667 tokens per session, scanned A, original, MIT.

A development guide for ProjectPilot’s architecture-migration branch. It describes a desktop application moving from Next.js to React and Vite in the front end, Hono in the back end, and Electron for the desktop shell.

In plain words
What is it for?
Use it when changing ProjectPilot’s agents workspace, front end, back end, desktop app, translations, or other documented capability areas.
Why use it?
It requires reading the relevant design and current-behaviour documents before making substantial changes, which keeps implementation aligned with the project’s intended architecture.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Codex.

This is Kaine665/Project-Pilot's own configuration. It tells Claude Code how to work on Project-Pilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Project-Pilot configures →

not rated 5repo 6mo ago A scan 1,667 tokens original MIT
View source ↗ Kaine665/Project-Pilot
Reuse

Borrowing it

Nothing to install: this file belongs to Kaine665/Project-Pilot. 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/Kaine665/Project-Pilot/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Kaine665/Project-Pilot

Made for: Claude Code.

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.

agentmods badge for Project-Pilot CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kaine665/project-pilot/claude-md/github.svg)](https://agentmods.dev/instructions/kaine665/project-pilot/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kaine665/project-pilot/claude-md"><img src="https://agentmods.dev/badge/instructions/kaine665/project-pilot/claude-md/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.

agentmods 80×15 button for Project-Pilot CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kaine665/project-pilot/claude-md"><img src="https://agentmods.dev/badge/instructions/kaine665/project-pilot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,667 This file is loaded in full into every session.
When invoked 1,667 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01667 $0.01667
Opus 5.5 $0.00667 $0.00667
Sonnet 5.5 $0.00333 $0.00333
Haiku 4.5 $0.00167 $0.00167

Measured 2mo ago against content hash b2ec62140d0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Project-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 2mo 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.

CLAUDE.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ProjectPilot — Architecture Migration Branch

这是什么

这是 ProjectPilot 的架构迁移分支 (arch/vite-hono-migration-260325)。

从 Next.js 全栈架构迁移到：

  • 前端：React + Vite (SPA) + React Router v7 + react-i18next
  • 后端：Hono (Node.js/Bun) — 统一后端，吸收了原 Sidecar 进程
  • 桌面：Electron (简化为 2 进程：Main + Hono Backend)

技术栈

  • 前端: React 19 + Vite 8 + TypeScript (strict) + Tailwind CSS 4 + shadcn/ui (Radix)
  • 后端: Hono 4 + @hono/node-server
  • 国际化: react-i18next (中/英)
  • 状态管理: Zustand
  • 路由: React Router v7 (SPA)
  • AI: Claude Agent SDK, OpenAI Codex SDK, MCP SDK
  • 桌面: Electron 40
  • 包管理: Bun (运行时 + 包管理器)
  • 开发端口: 前端 4000, 后端 4500

文档驱动开发（必须遵循）

本项目采用文档优先工作方式。对任何非琐碎改动（不仅仅是修错字、调间距），必须按以下顺序操作：

改动前

  1. 确定涉及的能力域（见下方域索引表）。
  2. 先读该域的 as-is（docs/as-is/）了解当前行为与入口，再读 design（docs/design/）了解原则与目标态。
  3. 若存在 active 状态的 contract（docs/contracts/），以契约为准确定范围与验收标准。
  4. 之后再酌情读代码。

改动后

  1. 若行为发生变化，必须更新对应 as-is 文档（刷新 last_reviewed 日期）。
  2. 若改变了长期方向或做了重大技术取舍，补充 design 或新建 ADR（docs/design/decisions/）。

域索引

能力域 as-is design
Agents 工作区（布局/侧栏/会话） docs/as-is/agents-workspace.md docs/design/agents-workspace.md

随项目演进补充更多行。未覆盖的域：先检查 docs/as-is/ 和 docs/design/ 是否已有对应页面；若无，改动后创建。

协作与分支

参考

开发命令

bun run dev            # 同时启动 Vite (4000) + Hono (4500)
bun run dev:client     # 仅 Vite 前端
bun run dev:server     # 仅 Hono 后端
bun run build          # 生产构建（Vite + Bun bundle）
bun run electron:dev   # Electron 开发模式

Read the full file on GitHub · 126 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. 2mo ago First seen · 126 lines · 1,667 tokens per session scan A b2ec62140d0f

Subscribe to this mod's changes

Project-Pilot CLAUDE.md is an instructions file published in the GitHub repository Kaine665/Project-Pilot (5 stars, last pushed 6mo ago), licensed MIT. It adds 1,667 tokens to every session, about $0.0067 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 2026-08-31.

Related

Project-Pilot CLAUDE.md compared with instructions from other repositories

Project-Pilot CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Project-Pilot CLAUDE.mdKaine665/Project-PilotInstructions file56mo agoMITA1,667Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode