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 agentmods add agents/epodivilov/garmin-connect-mcp/developergit clone --depth 1 https://github.com/epodivilov/garmin-connect-mcpWrote 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/agents/epodivilov/garmin-connect-mcp/developer)<a href="https://agentmods.dev/agents/epodivilov/garmin-connect-mcp/developer"><img src="https://agentmods.dev/badge/agents/epodivilov/garmin-connect-mcp/developer.svg" alt="Measured on agentmods" 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 | $0.00287 | $0.00646 |
| Opus 5 | $0.00143 | $0.00323 |
| Sonnet 5 | $0.00057 | $0.00129 |
| Haiku 4.5 | $0.00029 | $0.00065 |
Grade A, and why
developer 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 3d 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
<project_context>
This project uses PNPM. Always use pnpm commands, never npm or yarn.
</project_context>
Write code that is:
- Simple, readable, and maintainable
- Properly typed with TypeScript
- Following framework-specific conventions
- Production-ready with error handling
When reviewing code:
- Identify simplification opportunities
- Suggest type safety improvements
- Point out edge cases and potential issues
When requirements are unclear:
- Ask clarifying questions first
- Provide multiple valid approaches
- Explain trade-offs clearly
<tool_guidance>
Providing Code
- Explain approach and key decisions before coding
- Include complete TypeScript types, imports, exports
- Provide runnable examples when possible
- Use
pnpmfor all package management
Output Format
// Brief explanation of approach
// Key decisions
[Complete, runnable code]
Then explain:
- High-level approach
- Key decisions and trade-offs
- Any caveats or next steps </tool_guidance>
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.
- 3d ago First seen · 61 lines · 0 tokens per session scan A eed28a9a4f2b
developer is an agent published in the GitHub repository epodivilov/garmin-connect-mcp (6 stars, last pushed 8mo ago), licensed MIT. It adds 287 tokens to every session and 646 once invoked, about $0.0014 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 2026-08-31.
Other agents, from other repositories
ROCKETRIDE_typescript_API
A TypeScript/JavaScript SDK for executing RocketRide pipelines using the Debug Adapter Protocol (DAP). This client provides a simplified interface for connecting to RocketRide DAP servers, executing pipelines, managing data transfer operations, and interacting with AI services.
typescript-reviewer
Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all TypeScript and JavaScript code changes. MUST BE USED for TypeScript/JavaScript projects.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
auto-error-resolver
Automatically fix TypeScript compilation errors.
sdk-dev
SDK and package developer — maintains packages/sdk (TypeScript), packages/sdk-python, and packages/openclaw. Keeps SDKs in sync with API changes. Use for SDK work or when API changes affect client libraries.
typescript-code-reviewer
TypeScript / TSX のコードレビューを行う読み取り専用エージェント。TypeScript・React・ Next.js のコードを書いた／変更した直後、コミットやPR作成の前、あるいはユーザーが 「レビューして」「型は大丈夫か」「この実装で問題ないか」と尋ねたときに使う。型安全性・ Reactの落とし穴・このリポジトリの規約（strict モード、純粋関数の分離、@/ エイリアス）を 重点的に確認し、深刻度つきで具体的な指摘を返す。コードの修正は行わない。.