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 TencentCloudBase/awesome-miniprogram-skills --skill taxi-skillgit clone --depth 1 https://github.com/TencentCloudBase/awesome-miniprogram-skillsWrote 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/tencentcloudbase/awesome-miniprogram-skills/taxi-skill)<a href="https://agentmods.dev/skills/tencentcloudbase/awesome-miniprogram-skills/taxi-skill"><img src="https://agentmods.dev/badge/skills/tencentcloudbase/awesome-miniprogram-skills/taxi-skill/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/tencentcloudbase/awesome-miniprogram-skills/taxi-skill"><img src="https://agentmods.dev/badge/skills/tencentcloudbase/awesome-miniprogram-skills/taxi-skill.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 | $0.00024 | $0.00461 |
| Opus 5 | $0.00012 | $0.00230 |
| Sonnet 5 | $0.00005 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
taxi-skill 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.
What it actually says
出行打车
基于常用目的地完成行程预估、呼叫出租车、查看行程状态与历史行程的能力集合。
触发场景
用户原话举例（路由命中本技能）：
- "帮我叫个快车去首都机场"
- "从望京SOHO到北京南站多少钱"
- "我要打车去三里屯"
- "我的车到哪了"
- "帮我查一下现在的行程"
- "看看我之前的打车记录"
- "从这到机场打车要多久"
不适用范围
- 订机票、火车票 → 不在本技能范围，由票务技能处理
- 预约顺风车、代驾、租车等 → 不在本技能范围
- 查看公交地铁路线 → 不在本技能范围
- 外卖、跑腿、快递等物流服务 → 不在本技能范围
接口链路
estimateTrip：根据出发地和目的地预估各车型价格与时长。callTaxi：确认费用后发起叫车，返回叫车状态。getTripStatus：查询当前进行中行程的状态与司机信息。getTripHistory：查看历史行程记录。
使用顺序
- 叫车前需先确定出发地和目的地；没有明确地址时，展示常用目的地列表引导用户选择。
- 发起叫车前应先完成价格预估，让用户了解各车型费用后再确认。
- 查看行程状态时，优先返回当前活跃行程；用户明确要求查看历史记录时再调 getTripHistory。
- 所有已绑定组件的接口都应优先展示卡片，不要改成纯文本逐条展开。
What ships with it
29 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.
- apis/callTaxi.js 2.3 KB runs code
- apis/estimateTrip.js 2.8 KB runs code
- apis/getTripHistory.js 1.5 KB runs code
- apis/getTripStatus.js 2.8 KB runs code
- cloudbaserc.json 650 B
- cloudfunctions/taxi-skill-handler/index.js 4.3 KB runs code
- cloudfunctions/taxi-skill-handler/package.json 175 B
- components/calling-taxi-card/index.js 4.1 KB runs code
- components/calling-taxi-card/index.json 49 B
- components/calling-taxi-card/index.wxml 1.6 KB
- components/calling-taxi-card/index.wxss 3.8 KB
- components/trip-estimate-card/index.js 4.2 KB runs code
- components/trip-estimate-card/index.json 49 B
- components/trip-estimate-card/index.wxml 1.6 KB
- components/trip-estimate-card/index.wxss 6.0 KB
- components/trip-history-card/index.js 3.1 KB runs code
- components/trip-history-card/index.json 49 B
- components/trip-history-card/index.wxml 1.2 KB
- components/trip-history-card/index.wxss 2.4 KB
- components/trip-status-card/index.js 1.8 KB runs code
- components/trip-status-card/index.json 49 B
- components/trip-status-card/index.wxml 1.5 KB
- components/trip-status-card/index.wxss 5.2 KB
- data/seed.js 2.8 KB runs code
- index.js 1.0 KB runs code
- mcp.json 11 KB
- mp-skills.json 154 B
- README.md 2.2 KB
- utils/util.js 1.8 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.
- 9d ago First seen · 44 lines · 24 tokens per session scan A d98b25f11980
taxi-skill is a skill published in the GitHub repository TencentCloudBase/awesome-miniprogram-skills (36 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 461 once invoked, about $0.0001 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
gzh_article
A workflow for creating articles for WeChat Official Accounts, a Chinese publishing platform. It covers choosing a topic, researching sources, writing, adding images, checking the wording, and formatting the finished article.
weapp-vite-best-practices
An engineering guide for building small-program projects with weapp-vite, a Vite-based toolchain for compiling mini-apps for several platforms.
native-to-weapp-vite-wevu-migration
A step-by-step guide for gradually moving native WeChat, Alipay, or Douyin mini-programs to weapp-vite, with an optional later move to Vue single-file components.
docs-and-website-sync
A synchronization guide for keeping source code, website pages, READMEs, packaged documentation, and public coding-agent instructions consistent in a monorepo.
weapp-vite-vue-sfc-best-practices
A Chinese-language guide to writing Vue single-file components for weapp-vite mini-program projects. It covers templates, scripts, page metadata, component declarations, and platform differences.
release-and-changeset-best-practices
A release guide for a pnpm monorepo, a repository containing multiple related packages, templates, and tools.