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 instructions/eddmann/garmin-connect-cli/agents-mdgit clone --depth 1 https://github.com/eddmann/garmin-connect-cliWhat 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 | $0.00085 | $0.00085 |
| Opus 5 | $0.00043 | $0.00043 |
| Sonnet 5 | $0.00017 | $0.00017 |
| Haiku 4.5 | $0.00009 | $0.00009 |
Grade A, and why
garmin-connect-cli AGENTS.md 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.
What it actually says
Prefer make targets over direct commands. Run make help to see available targets.
Run make can-release before wrapping up substantial changes.
Detroit-style tests: assert on observable behaviour and mock only at the boundary.
Use garmin-connect as the public executable name in docs, examples, tests, and release assets. Keep garmin-connect-cli as the package name and uvx alias only.
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.
- 2d ago First seen · 8 lines · 85 tokens per session scan A 7f9f8bb335cd
garmin-connect-cli AGENTS.md is an instructions file published in the GitHub repository eddmann/garmin-connect-cli (11 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session, about $0.0004 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 instructions, from other repositories
gccli CLAUDE.md
Instructions for bpauli/gccli, covering claude.md, project overview, build & quality commands, architecture and key packages.
garmin-connect-mcp AGENTS.md
Instructions for eddmann/garmin-connect-mcp: Prefer make targets over direct commands. Run make help to see available targets.
garmin_ai AGENTS.md
AGENTS.md instructions for TolmachevKirill/garmin_ai, covering agents.md — garmin health pipeline, setup / running commands, testing, ad hoc analytical questions (no exact report matches) and creating/scheduling a workout in garmin.
go-garmin CLAUDE.md
Claude Code instructions for llehouerou/go-garmin, covering claude code instructions, verification, adding new endpoints, quick start and step-by-step guide.
garmin-connect-mcp CLAUDE.md
Instructions for eddmann/garmin-connect-mcp, a project described as: MCP server enabling LLMs to interact with Garmin Connect - activities, health metrics, sleep data, and training analysis.
garmin-health-data CLAUDE.md
Instructions for diegoscarabelli/garmin-health-data, covering claude.md, readme.md, database schema architecture, schema documentation and formatting ddl files.