weixinpay-pay

weixinpay-pay is a skill for Claude Code, Codex from rojim666/SztuCode. It costs 151 tokens per session (3,462 once invoked), scanned A, original, MIT.

A payment helper for retrying a cancelled or closed WeChat Pay order in the current AI conversation. It uses the original payment details so the same order can be paid again without creating a new order.

In plain words
What is it for?
Use it when a user wants to pay the same WeChat order again after cancelling or closing the payment screen. It is for payment execution, not for opening or linking an AI payment account.
Why use it?
It avoids making the user start a new order when they only cancelled the previous payment attempt. The user confirms the order before payment is triggered again.

Skill for Claude CodeCodex

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

Good fit Use it when a user wants to pay the same WeChat order again after cancelling or closing the payment screen. It is for payment execution, not for opening or linking an AI payment account.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rojim666/sztucode/weixinpay-pay
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 rojim666/SztuCode --skill weixinpay-pay
Clone the repo
git clone --depth 1 https://github.com/rojim666/SztuCode

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 weixinpay-pay

README.md
[![agentmods](https://agentmods.dev/badge/skills/rojim666/sztucode/weixinpay-pay/github.svg)](https://agentmods.dev/skills/rojim666/sztucode/weixinpay-pay)
Your own site
<a href="https://agentmods.dev/skills/rojim666/sztucode/weixinpay-pay"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/weixinpay-pay/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 weixinpay-pay

Your own site · 80×15
<a href="https://agentmods.dev/skills/rojim666/sztucode/weixinpay-pay"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/weixinpay-pay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,462 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00151 $0.03462
Opus 5 $0.00076 $0.01731
Sonnet 5 $0.00030 $0.00692
Haiku 4.5 $0.00015 $0.00346

Measured today against content hash cf681d066733, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

weixinpay-pay 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 today.

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.

packages/runtime-ts/prompts/workbuddy/skills/_builtin-plugins/weixinpay/skills/weixinpay-pay/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

微信支付AI专属卡 — 支付能力

功能描述

帮助用户在当前 AI 对话中完成微信支付AI专属卡的支付。本技能阐述微信支付的完整支付能力,让智能体据此正确处理用户的各类支付请求。

微信支付AI专属卡是用户微信支付账号下的一个子账户,专供智能体场景使用,由用户在支付卡片上确认后扣款。

微信支付通过**「工程化支付」**完成:系统通过确定性代码接管支付指令(weixin://wxpay/bizpayurl?pr=... 形式的支付 URL,或 WeixinPay-Required 字段),呈现为可交互的支付卡片 UI,由用户在卡片上确认后扣款,而非把原始支付指令文本直接暴露给用户。

触发工程化支付的途径依场景分两种:

  • 自动触发(发起支付的正常路径):商户下单后会在工具或服务返回中产生支付凭据(weixin://wxpay/bizpayurl?pr=...WeixinPay-Required),系统自动检测并触发工程化支付、弹出支付卡片。这是对一笔订单正常发起支付的默认路径,无需智能体手动调用工具或转述支付指令。
  • 重新触发(取消后重新支付):当用户在上一次支付中取消、关闭支付,想对同一笔订单再付一次时,商户不会再自动返回凭据,于是改由智能体先与用户确认要重新支付哪一笔订单,再把该订单上次相同的支付凭据(payUrlsWeixinPay-Required 的值)传给 mcp__weixinpay__weixinpay_retry_pay。该工具把凭据原样回显给系统,系统据此重新检测并再次触发工程化支付,用户会再次看到支付卡片,全程无需商户重新下单。

两种途径的区别在于触发方与适用场景:自动触发由商户下单凭据驱动、是默认路径;重新触发由智能体在取消后经 mcp__weixinpay__weixinpay_retry_pay 发起。

适用场景

  • 用户需要在当前对话中对商户订单完成微信支付(正常路径由系统在商户下单后自动触发工程化支付,见「触发途径一」)
  • 用户上一次支付时取消 / 关闭了支付,或对同一笔订单想再付一次(由智能体经 mcp__weixinpay__weixinpay_retry_pay 重新触发工程化支付,见「触发途径二」)

不适用场景

本技能仅面向终端用户在与智能体对话过程中完成微信支付的场景。下列场景不触发本技能:

  • 开通 / 绑定 / 激活 AI专属卡:应使用 weixinpay-register 技能
  • 支付失败、扣款异常、反复报错需要反馈:应使用 weixinpay-feedback 技能
  • 用户想换一个商品 / 换一笔订单支付:这属于新的下单支付(由商户下单后走自动触发),不是"重新支付"
  • 开发者 / 商户侧集成咨询:请改走微信支付官方文档,包括:
    • 询问微信支付 API、SDK、统一下单、签名算法、回调验签
    • 询问 JSAPI / Native / H5 / 小程序 / 付款码 / 刷脸支付的实现
    • 申请微信支付商户号、配置授权目录、回调地址、API 证书
    • 询问 prepay_id、code_url、out_trade_no 等微信支付商户接口字段
    • "如何在我的网站 / App / 小程序集成微信支付"
    • 任何带"商户"、"接入"、"对接"、"集成"、"开发"语境的咨询

如有歧义(用户身份不明),先询问用户:

您是想在当前对话里直接用微信支付付款,还是询问如何在自己的应用中集成微信支付?

触发途径一:商户下单后自动触发(发起支付的正常路径)

商户下单产生支付凭据后,系统自动检测并工程化地接管本次支付指令,触发工程化支付、弹出支付卡片。这是对一笔订单正常发起支付的默认路径。

智能体在该链路中的定位:

  • 该路径由系统自动触发,智能体无需也不应手动调用工具去重复发起支付
  • 智能体不得向用户展示 WeixinPay-Required: 的原始值——它是一次性支付凭证,由系统接管呈现,不得写入持久化日志或转发到其他渠道
  • 支付结果(成功 / 失败)由系统支付卡片回传,智能体不主动轮询、不臆测、不编造支付状态

仅当用户在该工程化支付之后取消 / 关闭了支付、并希望对同一笔订单再付一次时,才进入「触发途径二」,由智能体主动经工具重新触发工程化支付。

触发途径二:取消后重新支付(智能体经 mcpweixinpayweixinpay_retry_pay 重新触发工程化支付)

进入条件

满足以下任一意图且属于"对同一笔订单再次支付"时进入此触发途径:

Read the full file on GitHub · 198 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. today First seen · 198 lines · 151 tokens per session scan A cf681d066733

Subscribe to this mod's changes

weixinpay-pay is a skill published in the GitHub repository rojim666/SztuCode (64 stars, last pushed today), licensed MIT. It adds 151 tokens to every session and 3,462 once invoked, about $0.0008 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 2026-09-12.