garmin-connect

garmin-connect is a skill for Claude Code, Codex from Likenttt/garmin-connect-plugin-for-dsh. It costs 90 tokens per session (1,719 once invoked), scanned A, original, MIT.

A connection to Garmin Connect, Garmin's service for activity and health-device data, through a community-maintained package and tools.

In plain words
What is it for?
Use it to review activities, sleep, steps, heart rate, weight, workouts, running trends, and limited recovery information, or to create workouts and download FIT activity files when authorised.
Why use it?
It lets the agent retrieve selected Garmin data while requiring explicit approval for setup, software execution, configuration changes, and write actions.

Skill for Claude CodeCodex

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

Good fit Use it to review activities, sleep, steps, heart rate, weight, workouts, running trends, and limited recovery information, or to create workouts and download FIT activity files when authorised.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/likenttt/garmin-connect-plugin-for-dsh/garmin-connect
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 Likenttt/garmin-connect-plugin-for-dsh --skill garmin-connect
Clone the repo
git clone --depth 1 https://github.com/Likenttt/garmin-connect-plugin-for-dsh

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 garmin-connect

README.md
[![agentmods](https://agentmods.dev/badge/skills/likenttt/garmin-connect-plugin-for-dsh/garmin-connect/github.svg)](https://agentmods.dev/skills/likenttt/garmin-connect-plugin-for-dsh/garmin-connect)
Your own site
<a href="https://agentmods.dev/skills/likenttt/garmin-connect-plugin-for-dsh/garmin-connect"><img src="https://agentmods.dev/badge/skills/likenttt/garmin-connect-plugin-for-dsh/garmin-connect/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 garmin-connect

Your own site · 80×15
<a href="https://agentmods.dev/skills/likenttt/garmin-connect-plugin-for-dsh/garmin-connect"><img src="https://agentmods.dev/badge/skills/likenttt/garmin-connect-plugin-for-dsh/garmin-connect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,719 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 $0.00090 $0.01719
Opus 5 $0.00045 $0.00860
Sonnet 5 $0.00018 $0.00344
Haiku 4.5 $0.00009 $0.00172

Measured 2d ago against content hash 576ab96de42f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

garmin-connect 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 2d 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.

skills/garmin-connect/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Garmin Connect

Credit:李二牛

使用 npm 官方仓库中的社区维护、非 Garmin 官方软件包 dsh-plugin-garmin-connect。该包不指定版本,始终跟随 npm 当前的 latest 正式版本。不要抓取 Garmin 网页,也不要擅自替换成其他 Garmin 库。

连接工具

首先检查当前 WorkBuddy 会话能否使用下方列出的 Garmin MCP 工具。

  • 如果工具不可用,读取 references/workbuddy-setup.md。仅下载软件包 不会给正在运行的会话增加工具;必须在 WorkBuddy 中注册 stdio MCP 服务并 重新加载。
  • 如果 Garmin 工具提示凭据缺失、过期或需要浏览器认证,在展示或打开任何 内容前,先阅读同一参考文档中的认证部分。
  • 将配置视为两个阶段:先配置并重新加载 WorkBuddy,再请用户重新调用本技能 进行分析。不要承诺在原会话内同时完成配置和分析。
  • 在以下操作发生前分别获得用户授权:① 下载并执行 npm 软件包;② 修改 WorkBuddy 配置;③ 打开会写入会话文件的浏览器认证。不要把这些副作用 混入用户对数据分析的授权中。
  • 不要在对话中索取 Garmin 密码、MFA 验证码、OAuth 令牌、会话内容或 npm 令牌。回环页面由本社区插件提供;账号、密码和验证码只能输入其嵌入的 Garmin 表单。插件会以程序方式把 frame 服务地址限定为 https://sso.garmin.cn/sso/embedhttps://sso.garmin.com/sso/embed,并校验对应的 Web origin。浏览器地址栏 仍会显示 127.0.0.1,因此不要声称用户可仅凭地址栏独立验证 iframe 来源。 如果 Garmin 表单缺失或被拦截,立即停止输入。

用户没有指定账号时,使用已配置的默认 Garmin 服务。如果多个账号可能明显 影响答案且无法确定默认账号,询问账号别名;不要合并不同账号的数据。

获取最少必要数据

查询和分析数据时使用以下只读工具:

  • get_garmin_activities
  • get_garmin_sleep
  • get_garmin_steps
  • get_garmin_heart_rate
  • get_garmin_weight
  • get_garmin_workouts
  • get_garmin_profile
  • get_running_skill_advice

根据用户的问题选择工具,不要一次获取所有数据。按照用户 Garmin 账号或本地 日历时区,把相对日期换算成明确的 YYYY-MM-DD。确认是否需要包含尚未结束的 当天;否则优先使用完整日历日,并说明起止日期均包含在内。超过 30 天的范围 应拆成互不重叠、每批最多 30 天的数据,并标注合并后的总范围。

查询活动时默认使用 detail="compact",只有用户确实需要扩展字段时才提高 详细程度。full 可能暴露精确路线或位置;请求前说明其隐私影响。小表格或 摘要足以回答时,不要复述原始响应。

分析时避免过度推断

结果应明确区分:

  1. 数据范围以及缺失的日期或字段;
  2. 带日期和单位的直接观察;
  3. 明确标为推断的谨慎解释;
  4. 与用户目标匹配的可行下一步;
  5. 局限性,以及哪些补充数据可能改变结论。

至少比较多次测量后再称其为趋势。不要把相关性解释为因果关系,不要诊断疾病, 也不要把 Garmin 估算值当成医学结论。出现警示症状或异常测量时,应建议降低 训练强度,并在适当情况下寻求专业医疗帮助。

本插件未提供 HRV 状态、Body Battery、压力、训练准备度、恢复时间或训练负荷 工具。睡眠和静息心率趋势只能作为有限的恢复参考,不能称为完整恢复评分。

解释训练方法时,调用 get_running_skill_advice 并设置 mode="explain"。 提供个性化建议或计划时,使用 mode="personalized",收集工具返回的全部缺失 信息,并遵守其安全停止条件。Garmin 历史数据可以补充,但不能代替用户的目标、 当前成绩、训练背景、可用时间、健康与恢复情况以及训练负荷偏好。

写操作

用户明确要求创建 Garmin 训练或下载活动 FIT 时,可以使用下列工具。仅请求 分析、建议或生成计划时,不自动向 Garmin 训练库写入,也不自动下载文件。

Read the full file on GitHub · 122 lines

Files

What ships with it

1 file 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.

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. 2d ago First seen · 122 lines · 90 tokens per session scan A 576ab96de42f

Subscribe to this mod's changes

garmin-connect is a skill published in the GitHub repository Likenttt/garmin-connect-plugin-for-dsh (17 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 1,719 once invoked, about $0.0005 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 2026-09-10.

Related

Other skills, from other repositories

event-review

A weekly review process for event logs and leftover task records, turning repeated problems or useful lessons into proposed memory, knowledge, or skill entries.

reatcat/l123-harness · 92 tokens

web-artifact-designer

A design workflow for producing self-contained HTML or SVG files that open directly in a browser. It covers visual work such as posters, infographics, landing pages, charts, banners, cards, and interface mockups.

xulelenlp/dsh-web-artifact-designer · 115 tokens

voice

Text-to-Speech (TTS), voice cloning, voiceover, narration placement/sync, and custom sound effects (SFX) generator. Use when the user wants generated speech from text, wants to clone a consented voice from uploaded reference audio, wants to add/replace/align narration or voiceover for an existing video/timeline, wants…

nigedazhima/dsh-plugin-chatcut · 109 tokens

design-taste-frontend

A frontend-design skill for creating distinctive landing pages, portfolios, and redesigns. It first infers the desired visual character and then proposes a design direction and rules.

xiehuan123/coding-coach · 79 tokens

create-motion-graphics

Use whenever an ACP or local CLI agent in ChatCut Desktop needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a project. Covers direct inline JSX authoring, visual language, editable properties, asset binding, timeline placement, and local verification. Not for the built-in ChatCut Agent.

nigedazhima/dsh-plugin-chatcut · 70 tokens

talking-head-guide

A guide for editing videos where spoken delivery or conversation drives the structure, such as interviews, podcasts, lectures, tutorials, and courses.

nigedazhima/dsh-plugin-chatcut · 178 tokens