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 skills add aiguicai/MCP-Gateway --skill chat-plus-adapter-debuggergit clone --depth 1 https://github.com/aiguicai/MCP-GatewayWrote 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/skills/aiguicai/mcp-gateway/chat-plus-adapter-debugger)<a href="https://agentmods.dev/skills/aiguicai/mcp-gateway/chat-plus-adapter-debugger"><img src="https://agentmods.dev/badge/skills/aiguicai/mcp-gateway/chat-plus-adapter-debugger/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/skills/aiguicai/mcp-gateway/chat-plus-adapter-debugger"><img src="https://agentmods.dev/badge/skills/aiguicai/mcp-gateway/chat-plus-adapter-debugger.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 | $0.00098 | $0.06487 |
| Opus 5 | $0.00049 | $0.03243 |
| Sonnet 5 | $0.00020 | $0.01297 |
| Haiku 4.5 | $0.00010 | $0.00649 |
Grade A, and why
chat-plus-adapter-debugger 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 9d 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 — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chat Plus Adapter Debugger
目标
产出或修复一段可直接粘贴到 Chat Plus 的站点适配脚本,并满足新框架硬规则:
- 最外层必须
return { ... } - 必须包含
meta - 必须包含四个 hook:
transformRequestextractResponsedecorateBubblescontinueConversation
decorateBubbles必须使用ctx.helpers.ui.decorateProtocolBubbles(...)continueConversation必须使用ctx.helpers.plans.dom(...)continueConversation必须使用ctx.continuationTextextractResponse必须返回responseContentPreviewtransformRequest要么使用ctx.helpers.buildInjectedText(...)改写请求,要么明确return null- 输出抓取必须基于真实协议 / 真实响应,不接受用消息 DOM 反向抄正文代替
extractResponse - 输入实现允许两条路:
- 优先请求层协议注入
- 协议层因加密、签名、opaque body 或其他原因无法稳定改写时,退回 DOM 发送
- 生成脚本时必须使用平台 helpers:JSON 解析、文本转换、协议注入、气泡装饰、续写 DOM plan 都不要手写替代实现
使用 chrome-cdp
准备页面调试前,先确认工具列表存在 chrome-cdp,并读取 builtin://chrome-cdp/SKILL.md。本 skill 的执行入口可直接代理常用 CDP 调试命令,也可用更贴近 Chat Plus 工作流的别名。
只有用户明确允许启动浏览器调试会话后,才使用浏览器调试命令。MCP Gateway 内置 chrome-cdp 默认通过原生 Chrome DevTools Protocol 启动或复用独立的持久 profile Chrome,不连接用户已经打开的 Chrome 调试端口。
常用别名:
capture start
capture clear
network search <filter>
network get <request-id>
network perf
等价 CDP 命令:
netclear
net <filter>
netget <request-id>
perfnet
html [target] [selector]
snap [target]
evalraw <target> <method> [json]
如果 chrome-cdp 启动或浏览器连接失败:
- 运行
stop - 再运行
open <url>或launch <url> - 不要要求用户关闭已有 Chrome 或已有 DevTools 调试端口,除非用户明确要求连接既有浏览器
抓样本流程
按这个顺序抓样本。不要把 URL、Performance index 或页面 DOM 文本当作稳定 request id。
- 打开 / 选中目标页面,并确认处于用户真实登录态和真实使用模式
- 执行
capture start或netclear,让 CDP Network 从用户操作前开始记录 - 告诉用户现在只需要在页面里手动发送一条唯一探针文本,例如
CHATPLUS_ADAPTER_PROBE_YYYYMMDD_001 - 用户回页面手动发送这条探针文本
- 等用户明确回复:
发好了 - 执行
network search <关键词>或net <关键词>搜索 CDP Network 记录 - 按 URL / method / status / MIME / timing / body 线索找真实发送请求
- 复制
net输出里的 CDP request id - 执行
network get <request-id>查看请求体、响应体、状态码、content-type 和传输类型 - 根据
network get输出总结协议结构,不复述敏感 headers - 只有当 body 太长、输出被截断、需要离线解码二进制/长流式内容时,才追加
--request-file/--response-file保存到临时文件后再读取 - 如果首条消息创建了新会话或跳转,必须在新会话页重新执行
capture start,让用户发第二条 follow-up 样本
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.
- 9d ago First seen · 527 lines · 98 tokens per session scan A e54c3e903ffe
chat-plus-adapter-debugger is a skill published in the GitHub repository aiguicai/MCP-Gateway (154 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 6,487 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.