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 countbot-ai/CountBot --skill mapgit clone --depth 1 https://github.com/countbot-ai/CountBotWrote 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/countbot-ai/countbot/map)<a href="https://agentmods.dev/skills/countbot-ai/countbot/map"><img src="https://agentmods.dev/badge/skills/countbot-ai/countbot/map/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/countbot-ai/countbot/map"><img src="https://agentmods.dev/badge/skills/countbot-ai/countbot/map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00053 | $0.00726 |
| Opus 5.5 | $0.00021 | $0.00290 |
| Sonnet 5.5 | $0.00011 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
map 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 1mo 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
地图路线规划与 POI 搜索
基于高德地图 API 的路线规划和 POI 搜索服务。
配置
编辑 skills/map/scripts/config.json，填写高德地图 API Key：
{
"amap_key": "YOUR_AMAP_KEY"
}
AI 调用示例
用户说"我想去东莞玩3天"：
# 1. 搜索景点
python3 skills/map/scripts/map.py attractions --city 东莞 --page-size 20 --json
# 2. 查询景点间路线
python3 skills/map/scripts/map.py driving --origin "旗峰公园" --destination "可园博物馆" --origin-city 东莞 --dest-city 东莞
用户说"东莞有什么好吃的"：
python3 skills/map/scripts/map.py restaurants --city 东莞 --page-size 20 --json
用户说"从天安门到鸟巢坐地铁怎么走"：
python3 skills/map/scripts/map.py transit --origin "天安门" --destination "鸟巢" --city1 010 --city2 010
命令行参考
路线规划
# 驾车
python3 skills/map/scripts/map.py driving --origin "起点" --destination "终点" --origin-city 城市 --dest-city 城市
# 步行
python3 skills/map/scripts/map.py walking --origin "起点" --destination "终点" --origin-city 城市 --dest-city 城市
# 公交（需要城市编码）
python3 skills/map/scripts/map.py transit --origin "起点" --destination "终点" --city1 编码 --city2 编码
# 显示详细步骤
python3 skills/map/scripts/map.py driving --origin "起点" --destination "终点" --show-steps
POI 搜索
# 景点搜索（风景名胜 + 博物馆）
python3 skills/map/scripts/map.py attractions --city 城市 --page-size 20
# 餐厅搜索（排除快餐）
python3 skills/map/scripts/map.py restaurants --city 城市 --page-size 20
# 通用搜索
python3 skills/map/scripts/map.py search --keywords 关键词 --city 城市
常用城市编码
| 城市 | 编码 | 城市 | 编码 |
|---|---|---|---|
| 北京 | 010 | 上海 | 021 |
| 广州 | 020 | 深圳 | 0755 |
| 东莞 | 0769 | 杭州 | 0571 |
注意事项
- 支持地址名称或经纬度坐标作为起终点，系统自动识别
- 建议提供城市参数以提高地址解析准确性
- 公交路线必须提供城市编码
- 所有搜索命令支持
--json输出
What ships with it
4 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.
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.
- 1mo ago First seen · 90 lines · 53 tokens per session scan A dc8d59fc623c
map is a skill published in the GitHub repository countbot-ai/CountBot (782 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 726 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 2026-08-30.
Other skills, from other repositories
imsg
Use the imsg CLI from OpenClaw agents for iMessage/SMS DMs, groups, replies, reactions, polls, watching, and private-API actions.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
node-connect
Diagnose OpenClaw Control UI browser and native Android, iOS, or macOS node connection failures across route, auth, pairing, QR/setup-code, and reconnect states.
healthcheck
Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.
node-inspect-debugger
Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.
lobster
Lobster executes multi-step workflows with approval checkpoints. Use it when.