Borrowing it
Nothing to install: this file belongs to jhoy1020/garmin-coach-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jhoy1020/garmin-coach-mcp/main/.claude/skills/garmin-azure-deploy/SKILL.mdgit clone --depth 1 https://github.com/jhoy1020/garmin-coach-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/skills/jhoy1020/garmin-coach-mcp/garmin-azure-deploy)<a href="https://agentmods.dev/skills/jhoy1020/garmin-coach-mcp/garmin-azure-deploy"><img src="https://agentmods.dev/badge/skills/jhoy1020/garmin-coach-mcp/garmin-azure-deploy/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/jhoy1020/garmin-coach-mcp/garmin-azure-deploy"><img src="https://agentmods.dev/badge/skills/jhoy1020/garmin-coach-mcp/garmin-azure-deploy.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00092 | $0.01119 |
| Opus 5 | $0.00046 | $0.00560 |
| Sonnet 5 | $0.00018 | $0.00224 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
garmin-azure-deploy 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hosted deployment
Runs the same code as a container in Azure so the Claude mobile app can reach it.
Say this before starting
The user should be able to decline once they know:
- Cost: about $5/month, almost entirely the container registry. The Container App itself scales to zero.
- Exposure: ingress is open to the internet. An IP allowlist was tried and broke
the connector, so
allowedClientCidrsis deliberately empty. What protects the data is authentication: Entra sign-in withAssignment required, plus an object-id allowlist checked on every request. - Time: ~20 minutes, and one interactive Microsoft sign-in.
- They need a working local setup first — the container cannot log in to Garmin itself.
One command
python scripts/deploy.py
--help shows --subscription, --location, --timezone, --env-name.
Why it runs in phases — do not reorder this
The Entra app needs a redirect URI containing the app's FQDN. That FQDN is generated by
uniqueString() during the first provision and cannot be known in advance.
An agent that does not know this will try to register the Entra app first and dead-end. The phases exist precisely for that:
| Phase | What happens |
|---|---|
| 1 | provision the infrastructure → learn the FQDN |
| 1.5 | create/patch the Entra app with <fqdn>/oauth/callback |
| 2 | provision again (now with sign-in) and deploy the image |
| 3 | seed the Garmin token, then verify |
Re-enter after a failure with --phase 2, etc. Details of what the app registration
must contain, and why, are in references/entra.md.
Two things that will bite
azd provisionalone takes the site down. It resets the Container App to a placeholder image that listens on the wrong port, so activation fails and every request hangs. Always follow it withazd deploy.deploy.pyandrotate_secrets.pyalways do both.- Deploying a half-configured Entra setup crash-loops the container. If
ENTRA_TENANT_IDis set butBROKER_SECRETis empty,config.pyrefuses to start and Container Apps restarts it forever.deploy.pychecks for this and refuses.
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.
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.
- 11d ago First seen · 104 lines · 92 tokens per session scan A d3f420c5ba23
garmin-azure-deploy is a skill published in the GitHub repository jhoy1020/garmin-coach-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,119 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 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…