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/chendx404/cc-pet/claude-mdgit clone --depth 1 https://github.com/ChenDX404/CC-PetWrote 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/chendx404/cc-pet/claude-md)<a href="https://agentmods.dev/instructions/chendx404/cc-pet/claude-md"><img src="https://agentmods.dev/badge/instructions/chendx404/cc-pet/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 | $0.05403 | $0.05403 |
| Opus 5 | $0.02701 | $0.02701 |
| Sonnet 5 | $0.01081 | $0.01081 |
| Haiku 4.5 | $0.00540 | $0.00540 |
Grade A, and why
CC-Pet 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.
How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CC Pet — 项目约定与上下文（最终锁定版）
〇、最终总目标
CC Pet 是一个桌面浮窗桌宠（形态类似 Codex 自带桌宠）：
- 独立桌面进程（Tauri），不依赖 VS Code 可见 / 聚焦
- 透明背景、始终置顶、可拖到桌面任意位置
- 感知 VS Code、Claude Code、其他编码智能体的工作状态
- 以对应动画（idle / thinking / reading / editing / running / waiting / success / error）与方向帧反馈
长期架构（已锁定）
| 角色 | 技术栈 | 职责 |
|---|---|---|
| 桌面浮窗宿主 | Tauri（Rust + 系统 Webview） | 透明窗口、置顶、托盘、开机自启；承载 PetRenderer |
| VS Code Extension | 现有 TS + VS Code API | launcher + 状态桥：启动 / 停止 Tauri 进程、把 Claude Code 状态通过 IPC 推送给桌宠 |
| PetRenderer 共享核心 | 纯 TypeScript（不绑 vscode / tauri API） | 资产加载、帧计算、状态→动画映射；可被任意 Webview 宿主复用 |
⚠️ VS Code Webview 端已放弃（2026-07-21）
media/pet.js、src/petPreviewPanel.ts 以及 VS Code 内置浮窗（WebviewPanel）不再维护。
- 桌宠渲染唯一路径：Tauri 桌面浮窗（
dist-pet/pet.js） - VS Code Extension 仅作为 launcher + 状态桥 + GUI 绑定编辑器
- 动画架构：纯 JS setInterval（乒乓循环 / 正向播放），无 CSS animation，
dist-pet/pet.js中的startLoop()/playOnce()/stopAnimation()/frame()四个函数驱动全部动画
阶段路线（已修订）
| 阶段 | 目标 | 关键技术 | 状态 |
|---|---|---|---|
| 1 | 当前：VS Code WebviewPanel 预览原型 | VS Code Webview API | 规划完成，待实施 |
| 2 | 抽出 PetRenderer 共享核心（不绑 vscode） | TS 重构 | 延后 |
| 3 | 扩展 manifest schema + 11 行约定 + 16 方向 | PetRenderer + pet.json v3 | 延后 |
| 4 | Claude Code 状态检测（事件源） | VS Code ext + 文件监听 | 延后 |
| 5 | GUI 绑定编辑器（webviewView）+ 完整事件触发 + 动画状态机 | VS Code WebviewView | 延后 |
| 6 | Tauri 桌面浮窗原型 | Tauri (Rust + Webview) | 延后 |
| 7 | 透明 + 始终置顶 + 系统托盘 + 开机自启 | Tauri API | 延后 |
| 8 | VS Code Ext 改 launcher + IPC 整合 | IPC 协议 | 延后 |
| 9 | 打包发布（Marketplace + GitHub Release） | vsce + cargo bundle | 延后 |
业务模型 4 决策（已锁定）
| 决策点 | 终态默认行为 | 生效阶段 | 阶段 1 状态 |
|---|---|---|---|
| A 激活与生命周期 | VS Code Extension 激活时自动拉起 Tauri 桌宠；VS Code 关闭时桌宠退出 | 阶段 8 | ❌ 阶段 1 用手动命令 |
| B 多 VS Code 实例 | 全局单桌宠 + 用户手动选状态源 | 阶段 8 | ❌ 不适用 |
| C 离线行为（Claude Code 未运行 / 未安装） | 显示闲置动画（idle 帧），不报错、不隐藏 | 阶段 4 | ❌ 阶段 1 无状态检测 |
| D 交互模型 | 拖动（永远响应）+ 点击展示状态详情（CC 回复文本气泡） | 阶段 5+ | ❌ 阶段 1 仅拖动 |
阶段 1 严禁（即使想到也忍住）
- ❌ 不要加任何 Tauri 进程启动 / 关闭 / IPC 逻辑
- ❌ 不要加 Claude Code 状态检测的任何探针代码
- ❌ 不要让 WebviewPanel 自动随扩展激活打开
- ❌ 不要加点击 / 悬停 / 右键响应
- ❌ 不要加 idle / thinking / 任何动画状态切换逻辑
- ❌ 不要加多 VS Code 窗口协调代码
- ❌ 不要加 GUI 绑定编辑器（阶段 5 才做）
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 · 328 lines · 5,403 tokens per session scan A 1e0ae7640af0
CC-Pet CLAUDE.md is an instructions file published in the GitHub repository ChenDX404/CC-Pet (2 stars, last pushed 1mo ago), licensed MIT. It adds 5,403 tokens to every session, about $0.0270 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
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
my-claude-skills CLAUDE.md
Instructions for brody-0125/my-claude-skills, covering claude code skills repository, validation commands, sub-kopring-engineer: kotlin/java 코드 컨벤션 검증, numerical: 수치 연산 코드 검증 and sub-test-engineer: 문서 일관성 검증.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.