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/bpauli/gccli/claude-mdgit clone --depth 1 https://github.com/bpauli/gccliWrote 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/instructions/bpauli/gccli/claude-md)<a href="https://agentmods.dev/instructions/bpauli/gccli/claude-md"><img src="https://agentmods.dev/badge/instructions/bpauli/gccli/claude-md.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 5.1 | $0.01727 | $0.01727 |
| Opus 5 | $0.00864 | $0.00864 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
gccli CLAUDE.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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
gccli is a Go CLI (gccli) for interacting with the Garmin Connect API. It covers authentication, activities, workouts, health data, body composition, devices, gear, goals, badges, challenges, profile, hydration, training, and wellness data. Module: github.com/bpauli/gccli.
Build & Quality Commands
make build # Build binary to ./bin/gccli
make run -- <args> # Build and run with arguments
make fmt # Format code (goimports + gofumpt)
make lint # Run golangci-lint
make test # Unit tests with race detector
make test-e2e # E2E tests (requires .env with GARMIN_EMAIL/GARMIN_PASSWORD)
make ci # Full CI gate: fmt-check + lint + test
make tools # Install dev tools to .tools/
Run a single test:
go test -run TestFuncName ./internal/pkg/...
Run E2E tests selectively:
go test -tags=e2e -run TestName -v -count=1 ./internal/e2e/...
All three checks (make fmt, make lint, make test) must pass before committing.
Architecture
Layered structure: cmd/gccli/main.go → internal/cmd/ (CLI commands) → internal/garminapi/ (API client) → internal/garminauth/ (authentication).
Key packages
internal/cmd/— Kong-based CLI commands. Each command is a struct withRun(g *Globals) error.Globalsholds context, UI, and account info.resolveClient()loads tokens from the OS keyring and creates an API client.internal/garminapi/— HTTP client for Garmin Connect. Returnsjson.RawMessagefrom API calls (no Go structs for every endpoint). IncludesRetryTransport(429/5xx retry with backoff) andCircuitBreakerfor resilience. Auto-refreshes OAuth2 tokens on 401.internal/garminauth/— Garmin SSO authentication. Supports browser-based SSO (local callback server) and headless email/password login with MFA. OAuth1 → OAuth2 exchange flow.internal/secrets/— OS keyring storage (macOS Keychain, Linux Secret Service, file fallback). Tokens keyed bygccli:token:{email}.internal/config/— Config file paths and env var overrides.internal/outfmt/— Output formatting (JSON/Table/Plain). Mode passed via context.internal/ui/— Terminal UI (colors, prompts) via termenv. Passed via context.internal/errfmt/— Maps typed errors to user-friendly messages.internal/fit/— FIT file binary encoding for weight data uploads.internal/testutil/— Test helpers: mock HTTP servers, test token fixtures.internal/e2e/— End-to-end tests (build tage2e) against real Garmin Connect API.
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.
- 5d ago First seen · 113 lines · 1,727 tokens per session scan A 49b370878d6a
gccli CLAUDE.md is an instructions file published in the GitHub repository bpauli/gccli (27 stars, last pushed 5d ago), licensed MIT. It adds 1,727 tokens to every session, about $0.0086 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
garmin-connect-mcp AGENTS.md
Instructions for eddmann/garmin-connect-mcp: Prefer make targets over direct commands. Run make help to see available targets.
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-connect-cli AGENTS.md
Instructions for eddmann/garmin-connect-cli: 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.
garmin-connect-cli CLAUDE.md
Instructions for eddmann/garmin-connect-cli, a project described as: Garmin Connect from your terminal. Pipe it, script it, automate it.