Borrowing it
Nothing to install: this file belongs to sologuy/chatgpt-web-handoff. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sologuy/chatgpt-web-handoff/main/CLAUDE.mdgit clone --depth 1 https://github.com/sologuy/chatgpt-web-handoffWrote 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/sologuy/chatgpt-web-handoff/claude-md)<a href="https://agentmods.dev/instructions/sologuy/chatgpt-web-handoff/claude-md"><img src="https://agentmods.dev/badge/instructions/sologuy/chatgpt-web-handoff/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.
<a href="https://agentmods.dev/instructions/sologuy/chatgpt-web-handoff/claude-md"><img src="https://agentmods.dev/badge/instructions/sologuy/chatgpt-web-handoff/claude-md.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 | $0.00713 | $0.00713 |
| Opus 5 | $0.00357 | $0.00357 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
chatgpt-web-handoff 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 10d 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
@AGENTS.md
CLAUDE.md —— Claude Code 专用补充
项目规则统一在 AGENTS.md（Claude Code / Codex / DSH 共用），已由上面的 @AGENTS.md 导入。
本文件只放 Claude Code 专用内容；新增或修改项目规则请写进 AGENTS.md。
浏览器通道
正常 handoff 一律走 cgh submit / cgh poll，它们用自有 raw CDP 连 127.0.0.1:9222。
不要自己调 mcp__chrome-devtools__* 去做 handoff —— 那会绕过 host 白名单、档位回读、
模型校验、原话哈希、发送幂等这一整套门禁。MCP 只在 ChatGPT 改版后重新摸底 DOM 时用
（它的 a11y 快照会正确隐藏被 overflow:clip 裁掉的节点，裸 DOM 不会）。
⚠️ 不要用 Playwright（MCP 或 Python）连本机 9222 的 Chrome：旧版 connectOverCDP()
会替换 Chrome 的下载委托，下载文件变成无扩展名的 playwright-artifacts-*，
断开或杀进程都不恢复，只能重启 Chrome。跑 handoff 时也不要同时挂 claude-in-chrome，
两个自动化通道会互抢标签页和焦点。
上下文纪律
轮询 ChatGPT 生成状态用 evaluate_script 取最后一条 assistant 消息的尾部文本，
不要用 take_snapshot —— 长对话的完整 a11y 树会把上下文吃光。
快照只在定位控件和失败留证时用。
这个 Chrome 是用户日常在用的
任何交互前先校验目标页 host ∈ chatgpt.com；不要对无关标签页做快照、执行脚本或读网络请求。
开新标签页做实验，用完关掉，不要动用户已有的对话页。
不要替用户点「发送」以外的破坏性按钮：删除对话、清空记忆、修改账户设置一律不碰；
遇到会弹 confirm / alert 的元素先停下问。
Skill 真相源在仓库
skills/chatgpt-handoff/SKILL.md 是真相源，scripts/install.sh 已把它 symlink 到
~/.claude/skills/chatgpt-handoff。不要直接改 ~/.claude/skills/ 下的路径（那就是本仓库）。
MCP 注册（可选，仅用于改版摸底）
Skill 要在任意项目里可用，所以 scope 必须是 user：
claude mcp add chrome-devtools -s user -- \
npx -y [email protected] --browserUrl http://127.0.0.1:9222 \
--no-usage-statistics --no-performance-crux \
--no-category-performance --no-category-network --no-category-emulation \
--screenshotFormat webp --screenshotMaxWidth 1280
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.
- 10d ago First seen · 51 lines · 713 tokens per session scan A f9df8b03c8c9
chatgpt-web-handoff CLAUDE.md is an instructions file published in the GitHub repository sologuy/chatgpt-web-handoff (2 stars, last pushed 4d ago), licensed MIT. It adds 713 tokens to every session, about $0.0036 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.