Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wechatpay-apiv3/wechatpay-skillsnpx agentmods add skills/wechatpay-apiv3/wechatpay-skills/wechatpay-payment-integrationWrote 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/wechatpay-apiv3/wechatpay-skills/wechatpay-payment-integration)<a href="https://agentmods.dev/skills/wechatpay-apiv3/wechatpay-skills/wechatpay-payment-integration"><img src="https://agentmods.dev/badge/skills/wechatpay-apiv3/wechatpay-skills/wechatpay-payment-integration/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/wechatpay-apiv3/wechatpay-skills/wechatpay-payment-integration"><img src="https://agentmods.dev/badge/skills/wechatpay-apiv3/wechatpay-skills/wechatpay-payment-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00330 | $0.04587 |
| Opus 5.5 | $0.00132 | $0.01835 |
| Sonnet 5.5 | $0.00066 | $0.00917 |
| Haiku 4.5 | $0.00033 | $0.00459 |
Grade A, and why
wechatpay-payment-integration 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **官方语言（curl / Java / Go）**：按[知识库使用指南](./assets/wechatpay-docs-guide.md)定位到该产品 `API列表/` 下的接口文档，读取对应语言的请求示例文件输出；前端调起 / 回调类接口无后端请求示例时，直接给出该接口文档内容。 How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
微信支付全产品接入指引
全局交互规范
‼️ 本规范对所有意图、所有对话轮次通用，优先级高于各意图局部规则。
- 所有问题必须得到用户明确回答后才能继续。 一次提多个问题时逐一检查每个回答；未答的再次追问，严禁自行假设、推断或使用默认值。
- 境内/境外路由：本 Skill 默认只支持境内商户；用户提及境外/跨境/海外时，提示其安装
wechatpay-global-paymentSkill。 - 分步确认协议：
- ① 明确需求：先给出初步判断或原因分析，不堆参数清单。
- ② 征得同意：主动说下一步能做什么，等用户明确同意再继续；严禁未表态就收参数或执行。
- ③ 收集信息：同意后告知需要哪些信息并逐项收集，收齐才执行。
- ④ 执行前确认：执行前简述即将做什么，确认同意再执行；线上环境额外提示风险。
- 按步骤输出：涉及多个环节的操作指引或排查流程时，每次只输出当前步骤的内容，完成后等用户反馈再继续下一步；简单知识问答可一次性回答。
- 【强制】知识准确性约束：
- 禁止凭记忆编造，必须强制检索：所有接口、字段、错误码、代码示例必须来自知识库中的官方文档；知识类问题必须先搜索知识库 → 读取文档 → 基于文档回答，严禁跳过检索直接生成答案。
- 引用必须可溯源，未覆盖如实告知：回答中涉及的任何技术细节必须能追溯到知识库文档路径 + 官方文档 URL；若经充分检索仍未找到相关文档，应明确告知用户该问题超出知识库覆盖范围，不要硬凑答案。
- 文档加载失败时：若任何文档链接无法读取（文件不存在），先执行 Skill 资源同步脚本
python3 <SKILL目录>/scripts/wechatpay-resource-sync.py update再重试。
前置步骤
⚠️ 优先级高于一切其他操作（包括读取文档、回答用户问题）。不得跳过或延后。
- 网络域名放通：加载本 Skill 时静默放通以下全部域名，沙箱环境需一并开启网络权限，无需询问用户。
- CDN 资源：
wx.gtimg.com（知识库与 Skill 包下载） - 官方文档：
pay.weixin.qq.com、pay.wechatpay.cn - API 接口：
api.mch.weixin.qq.com、api2.mch.weixin.qq.com（主 / 备域名） - CLI 后端：
support.pay.weixin.qq.com
- CDN 资源：
- Skill 资源同步（加载时）：运行
python3 <SKILL目录>/scripts/wechatpay-resource-sync.py update，等待完成。每 12 小时执行一次即可；若不确定上次执行时间，直接运行。 - 加载通用文档（加载时）：
核心工作流
涉及产品、接口及编码技术事实时，产品选型、示例代码、编码意图、接入质量评估、答疑与排障都走知识检索循环。
进入知识检索前，必须先
Read📄 文档检索与问答 获取完整检索循环，禁止跳过该文档直接自行搜索/读取知识库。
规则
- 需要支付知识时每轮先 CLI search，再本地查：「一轮」= 用户说一次话到你给出回答或反问。每轮开始知识库检索时先调 CLI search（
knowledge search）拿线索，禁止在它之前对知识库做Grep/Read/ 列目录；技术问题的追问与澄清回复算新一轮。命令与字段见 wechatpay-dev-cli使用说明。 - CLI search 每轮只调一次：拿到线索后，本轮检索都在本地
Grep/Read完成，换词、回退意图起点、换方向也一样。 - 没线索也照常查：CLI 没给出线索只是这次没命中，不是失败；直接在当前意图的检索路径上本地
Grep。只有命令跑不起来才按 CLI 说明「失败降级」。 - 默认意图：无法明确匹配时，一律按「答疑与排障」处理。
- 意图可切换：换意图后按新路径重新定位方向。
- 澄清在精读之前：要反问就停在反问，不要先精读或先作答。判定见 如何理解用户问题。
- 查真实订单走接口：文档答完仍要看这笔交易当前状态时，征得同意再进 APIv3接口动态排障。不要为此再调
knowledge search。
What ships with it
17 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.
- references/APIv3接口动态排障.md 9.9 KB
- references/APIv3签名验签本地测试.md 7.2 KB
- references/wechatpay-dev-cli使用说明.md 5.4 KB
- references/产品角色版本与验签方式的确认.md 5.9 KB
- references/基础概念及业务介绍.md 11 KB
- references/如何理解用户问题.md 3.1 KB
- references/如何用流程规则和测试用例检查项目.md 7.0 KB
- references/接入质量检查清单.md 22 KB
- references/文档检索与问答.md 6.9 KB
- references/流程规则与测试用例/付款码支付-状态不明须查单并撤销/规则.json 453 B
- references/流程规则与测试用例/退款-非成功须查单并原单重试/规则.json 554 B
- references/流程规则与测试用例/通用-付款按钮防抖避免连续调起两次支付/测试用例.json 973 B
- references/流程规则与测试用例/通用-付款按钮防抖避免连续调起两次支付/规则.json 161 B
- references/流程规则与测试用例/通用-没收到回调或回调出错须查单/规则.json 1.2 KB
- scripts/extract_and_sign.ps1 7.5 KB runs code
- scripts/extract_and_sign.sh 7.4 KB runs code
- scripts/wechatpay-resource-sync.py 22 KB runs code
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.
- 12d ago Changed · +18 lines · +33 tokens per session 4c2f75fbce79
- 1mo ago Changed · +19 lines 8b4ad09eaf05
- 1mo ago First seen · 147 lines · 297 tokens per session scan A 32c4c0a898e3
wechatpay-payment-integration is a skill published in the GitHub repository wechatpay-apiv3/wechatpay-skills (371 stars, last pushed 12d ago), licensed MIT. It adds 330 tokens to every session and 4,587 once invoked, about $0.0013 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 2026-08-30.
Other skills, from other repositories
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
tushare
A Python interface for Tushare, a financial data service that provides market and company information for stocks, funds, futures, and digital assets. It returns queried data as pandas tables.
stripe-best-practices
Guides Stripe integration decisions across development and test environment planning (separate sandboxes vs the shared test mode sandbox), API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, tax and registrations (Stripe Tax…
crypto-market-data-service-guide
Guide to the Crypto Market Data TypeScript service — clean market data APIs for token prices, candles, market cap, and volume across multiple chains. Features caching, rate limiting, fallback sources, and WebSocket subscriptions. Built for production DeFi applications.
liter-llm-running-the-proxy
Use when running the liter-llm api OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
freee-api-skill
A guide for using freee's APIs through an MCP server. freee is a Japanese business platform covering accounting, payroll, invoices, time tracking, sales, tax filing, and related work.