Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/athitupakan/garmin-dev-skillsnpx agentmods add commands/athitupakan/garmin-dev-skills/runWrote 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/commands/athitupakan/garmin-dev-skills/run)<a href="https://agentmods.dev/commands/athitupakan/garmin-dev-skills/run"><img src="https://agentmods.dev/badge/commands/athitupakan/garmin-dev-skills/run.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 | $0.00000 | $0.00360 |
| Opus 5 | $0.00000 | $0.00180 |
| Sonnet 5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
run 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 7d 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
Run (full cycle: simulator + compile + push)
For the first run of a session or after closing the simulator.
Run
# Windows
.\.claude\skills\garmin-dev\scripts\windows\run.ps1
# macOS / Linux
./.claude/skills/garmin-dev/scripts/posix/run.sh
The script is idempotent — re-running mid-session just skips the simulator launch if it's already up.
What it does
- Ensures
bin\exists - Launches simulator if not already running (2-sec boot buffer)
- Compiles →
bin\<project>.prg - Pushes via
monkeydo— blocks while streaming device logs
Caveats
- Step 4 blocks the terminal.
monkeydois streamingSystem.printlnoutput. Not a hang — Ctrl+C to stop. - If
monkeydoerrors immediately with a connection issue → simulator hasn't fully booted. Wait for the simulator window to render, then re-run. - Simulator window title should read:
CIQ Simulator - <your device> (<firmware version>)— the device name comes from yourmanifest.xml<iq:product>entry
Claude Code invocation
Long-lived — pass run_in_background: true in the PowerShell tool call. Do not wait for exit.
Re-pushing after edits
- Manual: Ctrl+C → re-run
run.ps1(or justbuild.ps1+monkeydoyourself) - Auto: stop
run.ps1, switch to watch.md
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.
- 7d ago First seen · 40 lines · 0 tokens per session scan A 61a581953eac
run is a command published in the GitHub repository athitupakan/garmin-dev-skills (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 360 tokens. 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 commands, from other repositories
capacitor-plan
Capacitor native-layer security audit — plan only, no config edits until approved.
mobile-plan
App Store / Play submission-readiness audit — plan only, no manifest edits until approved.
swift-feature
Implement a new Swift feature end-to-end: analysis, confirmation, implementation, and build validation.
audit-accessibility
Audit iOS app for accessibility compliance.
audit-security
Run security audit against OWASP Mobile Top 10 2024.
validate-appstore
Validate iOS app against App Store Review Guidelines.