meituan-coupon-assistant

meituan-coupon-assistant is a skill for Claude Code, Codex from uvwt/agentdock-skills. It costs 48 tokens per session (1,101 once invoked), scanned A, original, Apache-2.0.

A Meituan coupon assistant for one user-requested sign-in and coupon-claiming session. Meituan is a Chinese services platform; the assistant uses its Passport login and coupon interfaces for the current request only.

In plain words
What is it for?
Use it to log in through Meituan and claim a requested coupon or red packet once, including handling the authorization flow and saving the session state needed for that request.
Why use it?
It keeps login and device session data in its managed data area and avoids background tasks, recommendations, and reuse of credentials from other applications. It also requires confirmation before clearing a device identifier.

Skill for Claude CodeCodex

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

Good fit Use it to log in through Meituan and claim a requested coupon or red packet once, including handling the authorization flow and saving the session state needed for that request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uvwt/agentdock-skills/meituan-coupon-assistant
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 uvwt/agentdock-skills --skill meituan-coupon-assistant
Clone the repo
git clone --depth 1 https://github.com/uvwt/agentdock-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 meituan-coupon-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/uvwt/agentdock-skills/meituan-coupon-assistant/github.svg)](https://agentmods.dev/skills/uvwt/agentdock-skills/meituan-coupon-assistant)
Your own site
<a href="https://agentmods.dev/skills/uvwt/agentdock-skills/meituan-coupon-assistant"><img src="https://agentmods.dev/badge/skills/uvwt/agentdock-skills/meituan-coupon-assistant/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 meituan-coupon-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/uvwt/agentdock-skills/meituan-coupon-assistant"><img src="https://agentmods.dev/badge/skills/uvwt/agentdock-skills/meituan-coupon-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,101 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 $0.00048 $0.01101
Opus 5.5 $0.00019 $0.00440
Sonnet 5.5 $0.00010 $0.00220
Haiku 4.5 $0.00005 $0.00110

Measured 29d ago against content hash 0497c5b04523, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meituan-coupon-assistant 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 29d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (run.py, scripts/auth.py, scripts/run.js, …), 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.

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.

skills/meituan-coupon-assistant/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

美团领券助手(AgentDock 适配版)

本 Skill 根据用户提供的 meituan-coupon-assistant 包适配。保留上游 Passport 登录、二维码生成和领券业务流程,移除上游宿主专属运行时绑定、包外状态符号链接、运行时依赖安装和用户 Home 目录中的动态更新加载。

安全边界

  • 仅在用户明确发起当前一次美团领券请求时执行;不做消费推荐,也不创建定时、后台或自动任务。
  • 登录 Token、device token 和 Passport 会话只保存在本 Skill 独立数据目录;不得展示、复制或迁移其他应用的凭据。
  • 对外统一通过根目录 run.py,stdin 传 JSON,顶层字段为 skill_action。不要直接调用包内 pt-passport 或让 Token 出现在命令行和回复中。
  • 网络用于美团 Passport 授权、https://click.meituan.com 二维码接口和 https://media.meituan.com 领券接口。不得覆盖 client id、aiScene 或接口地址。
  • 包内 Passport 与 CLIGuard 代码来自用户提供的上游包;AgentDock 适配版只加载包内固定版本,不读取用户 Home 目录中的更新代码,也不启动 CLIGuard wrapper 的后台更新或上报逻辑。
  • 请求失败、超时或结果未知时不使用同一 Token 自动重试。401 仅按上游流程清除旧登录并进入一次新授权。
  • clear_device_token 会清除设备标识并影响登录状态,必须由用户明确确认后执行。

数据目录

在 AgentDock managed Skill 中,不需要用户配置数据目录。宿主执行 exec_command(skill_ref=...) 时会自动注入保留变量 SKILL_DATA_DIR;根目录 run.py 优先使用它保存设备标识、Passport 登录状态、临时授权状态、当日领券缓存和诊断日志。

  • 不要通过 skill_manage env_set 或请求级 env 配置、覆盖 SKILL_DATA_DIR。
  • shared/workspace 同名候选不会获得 managed Skill 的 SKILL_DATA_DIR。
  • 在不提供 SKILL_DATA_DIR 的其他宿主中,可以显式设置 MEITUAN_COUPON_DATA_DIR 作为兼容 fallback;两者同时存在时始终以 SKILL_DATA_DIR 为准。
  • 持久状态只写数据目录,不写回 Skill 包。

运行需要 Node.js >= 18 和 Python 3;其他 JavaScript 依赖均已固化在包内,不在运行时安装依赖。

执行接口

只读状态

{"skill_action":"status"}

只检查独立数据目录中是否存在设备状态和登录状态,不访问网络,也不返回凭据内容。

当前一次领券

{"skill_action":"execute"}

返回两类状态:

  • AUTH_REQUIRED:读取 references/auth-flow.md,向用户展示本次返回的 url 和可选 imageUrl。用户完成登录后再执行 auth_complete。
  • TERMINAL:直接把 response_text 作为本次结果;不要改写成功/失败语义,也不要自动重试。

完成登录并领券

用户明确表示已完成刚才的美团登录后执行:

{"skill_action":"auth_complete"}

该动作会等待本次 Passport 授权并立即执行一次领券。执行完成后使用真实 response_text 返回结果,不创建新的授权会话。

退出登录

{"skill_action":"logout"}

只在用户明确要求退出时执行。保留设备标识。

清除设备标识

只有用户明确二次确认后执行:

{"skill_action":"clear_device_token","confirmed":true}

通用运行方式

从 Skill 根目录执行入口脚本,业务请求通过 stdin 传入:

printf '%s' '{"skill_action":"status"}' | python3 run.py

非 AgentDock 宿主在需要持久状态的动作前设置 MEITUAN_COUPON_DATA_DIR;入口脚本不会把 Token、Cookie 或授权状态写回 Skill 包。

Read the full file on GitHub · 91 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. 29d ago First seen · 91 lines · 48 tokens per session scan A 0497c5b04523

Subscribe to this mod's changes

meituan-coupon-assistant is a skill published in the GitHub repository uvwt/agentdock-skills (6 stars, last pushed 8d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,101 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-23.

Related

Other skills, from other repositories

renewal-playbook

Crea un playbook de renovación estructurado para una cuenta de cliente. Úsalo cuando necesites planificar una renovación, estructurar una negociación de renovación, prepararte para una conversación de expansión, o construir una estrategia de renovación para cuentas en riesgo o saludables. Produce un brief de…

mohitagw15856/pm-claude-skills · 88 tokens

product-page-seo

Optimize AEM Edge Delivery Services commerce product pages for search engine crawling and indexing. Audits client-side rendered product content for crawlability, validates meta tags, Product schema.org structured data, canonical URLs, and image optimization. Addresses the core challenge that EDS product pages render…

adobe/skills · 90 tokens

commerce-app-business-config

Manage custom business configuration in an Adobe Commerce app. Use when the user wants to add, modify, or remove merchant-configurable settings (config fields, admin config, store configuration) exposed through Commerce Admin. Creates typed config fields (text, password, email, url, tel, boolean, list) in…

adobe/skills · 80 tokens

acp

This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.

majiayu000/claude-skill-registry · 0 tokens

doku-payment-gateway

Expert guide for integrating DOKU Payment Gateway: DOKU Checkout (Hosted & Modal Popup with HMAC-SHA256), Direct API SNAP BI Standard (VA, QRIS, Direct Debit with HMAC-SHA512), and Direct API Non-SNAP (Card Payment Page, OVO Push). Covers single-integration checkout, direct host-to-host APIs, webhook verification, and…

roedyrustam/vibes-plug · 107 tokens

marketplace-purchase-vetting

Use this when the user asks whether a local listing is a scam, "too good to be true," worth looking at, or a good deal. Also use this when he asks you to find options — search/discover candidates, then vet the best ones. The goal is not a generic buying guide; it is a practical risk read with clear next steps.

AtlasOmnia/donna-starter · 72 tokens