chatgpt-bridge

chatgpt-bridge is a skill for Claude Code, Codex from renky1025/agent-skills. It costs 182 tokens per session (2,574 once invoked), scanned A, original, MIT.

A bridge that lets an agent ask questions through a user's already signed-in ChatGPT browser session and retrieve the answers. It can also find an earlier ChatGPT conversation and continue it.

In plain words
What is it for?
It is for checking uncertain technical details, asking ChatGPT for a second opinion, and continuing relevant past conversations.
Why use it?
It provides a way to consult ChatGPT without handling the user's password or requiring an OpenAI API key.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for checking uncertain technical details, asking ChatGPT for a second opinion, and continuing relevant past conversations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/renky1025/agent-skills/chatgpt-bridge
Install

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.

Any agent
npx skills add renky1025/agent-skills --skill chatgpt-bridge
Clone the repo
git clone --depth 1 https://github.com/renky1025/agent-skills

Made for: Claude Code, Codex.

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 chatgpt-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/renky1025/agent-skills/chatgpt-bridge/github.svg)](https://agentmods.dev/skills/renky1025/agent-skills/chatgpt-bridge)
Your own site
<a href="https://agentmods.dev/skills/renky1025/agent-skills/chatgpt-bridge"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/chatgpt-bridge/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 chatgpt-bridge

Your own site · 80×15
<a href="https://agentmods.dev/skills/renky1025/agent-skills/chatgpt-bridge"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/chatgpt-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 182 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,574 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00182 $0.02574
Opus 5.5 $0.00073 $0.01030
Sonnet 5.5 $0.00036 $0.00515
Haiku 4.5 $0.00018 $0.00257

Measured 22d ago against content hash 97786874171a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chatgpt-bridge scanned grade A 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 22d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/bridge.py, scripts/cdp.mjs, scripts/chatgpt.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `--proxy` 指定的代理 curl 实测不通 -> 停止,先让用户修代理,不要反复重试。
chatgpt-bridge/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

chatgpt-bridge

Purpose

把 ChatGPT 当成一个可脚本调用的外部专家:发送你不确定的问题,取回准确答案;或按关键字 定位历史对话并在其中继续追问。三条设计约束:

  • 发送走页面 UI(官方发送接口需要页面计算的 proof-of-work / sentinel token,绕过会被拒)。
  • 读取走 backend-api(markdown 完整、含代码块,不受对话 DOM 虚拟化影响)。
  • 凭证复用用户本机 Chrome 的登录态副本,全程不接触密码,也不需要 OpenAI API key。

When to Use

  • 遇到不确定的技术细节(某个 API 的确切签名、某个标准里的编号、某段代码是否成立),需要 外部权威答案而不是自己猜。
  • 用户说"帮我问一下 GPT""复查这个结论""找回之前聊过的那个话题再问一句"。
  • 需要在已登录站点上做操作,而 AppleScript 路径不可用。
  • 触发词:问一下 ChatGPT、帮我问 GPT、用我的 ChatGPT 问、复查这个结论、找回之前和 GPT 聊过的 X、 继续问那个对话、ask ChatGPT in my browser、"我不确定这个 API 怎么用 去问一下"。

When NOT to Use

  • 答案能靠本地代码 / 文档 / 搜索确定 -> 没必要消耗用户配额。
  • 只想抓公开网页 -> 用 WebFetch。
  • 本机 Chrome 中未登录 chatgpt.com -> 无法复用登录态,停下来让用户手动登录后重试。

Workflow

快速开始:

SK="$HOME/.workbuddy/skills/chatgpt-bridge/scripts"
NODE=<node 绝对路径>          # 需要 Node 18+
# 关键:清掉沙箱注入的代理环境变量,否则连不上本地 CDP
AB() { env -u http_proxy -u https_proxy -u HTTP_PROXY -u HTTPS_PROXY \
        NO_PROXY="127.0.0.1,localhost" no_proxy="127.0.0.1,localhost" "$@"; }

python3 "$SK/bridge.py" up --proxy http://127.0.0.1:7890   # 1. 起桥(无代理需求则 --proxy none)
AB $NODE "$SK/chatgpt.mjs" status                            # 2. 确认已登录、输入框就绪
...                                                          # 3. 干活(见下)
python3 "$SK/bridge.py" down                                 # 4. 必须收尾(会删掉含 cookie 的副本)

bridge.py up 返回 JSON:{"status":"up","port":9222,"browser":"Chrome/152..."}。

工作流 1:新建对话提问,取回答案

AB $NODE "$SK/chatgpt.mjs" ask "<你的问题>" --new --out /tmp/ans.json --timeout 240000

--new 先跳到 chatgpt.com/ 开新对话再提问。回答较长时务必用 --out:stdout 只打印摘要, 全文写进 JSON 文件,再用读文件工具取,避免命令行输出被截断。

工作流 2:按关键字找回历史对话 / 继续提问

AB $NODE "$SK/chatgpt.mjs" search "网格生成算法 语言选择" --limit 5 --out /tmp/s.json
AB $NODE "$SK/chatgpt.mjs" read <conversationId> --out /tmp/c.json    # 另生成 /tmp/c.md
AB $NODE "$SK/chatgpt.mjs" ask "<追问>" --in <conversationId> --out /tmp/followup.json

Decision Rules

命令 作用 关键参数
status 当前页 URL / 标题 / 会话 id / 是否登录 / 输入框是否就绪 -
new 跳到新对话 -
open <id|url> 打开指定对话 -
ask "<文本>" 发送并等待回复,取回答案 --new --in <id> --out --timeout
read [<id>] 导出完整会话(API,markdown 保真) --out(另生成同名 .md)
list 最近会话列表 --limit --out
search "<词>" 关键字/语义检索历史会话 --limit --out
api <path> 直接打 authed GET,调试用 -

Read the full file on GitHub · 146 lines

Files

What ships with it

6 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.

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. 22d ago First seen · 146 lines · 182 tokens per session scan A 97786874171a

Subscribe to this mod's changes

chatgpt-bridge is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed 7d ago), licensed MIT. It adds 182 tokens to every session and 2,574 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.

Related

Other skills, from other repositories

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…

jihe520/social-push · 108 tokens

cursor-skill

A computer-use skill for controlling a desktop through Magic Mouse, a desktop pet that provides screen interaction. It can inspect screenshots, plan actions, click, type, switch applications, and verify results.

WangYuecheng1106/Magic-Mouse · 0 tokens

dingtalk_channel_connect

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.

agentscope-ai/QwenPaw · 69 tokens

browser_cdp

Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.

agentscope-ai/QwenPaw · 85 tokens

browser_visible

Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…

agentscope-ai/QwenPaw · 75 tokens

edgeone skill scanner

A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.

Tencent/AI-Infra-Guard · 148 tokens