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/watchWrote 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/watch)<a href="https://agentmods.dev/commands/athitupakan/garmin-dev-skills/watch"><img src="https://agentmods.dev/badge/commands/athitupakan/garmin-dev-skills/watch.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 | $0.00438 |
| Opus 5 | $0.00000 | $0.00219 |
| Sonnet 5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
watch 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 8d 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
Watch (auto-rebuild + re-push on file change)
Polls source\ + resources\ every 2s. On change → kill old monkeydo → rebuild → push fresh.
Status: experimental. Connect IQ has no official hot reload — this script approximates it.
Run
# Windows
.\.claude\skills\garmin-dev\scripts\windows\watch.ps1
# macOS / Linux
./.claude/skills/garmin-dev/scripts/posix/watch.sh
Prerequisites
- Simulator already running (run.ps1 once first, or manually open it)
bin\exists (script creates it if missing)
What it does
- Initial build + push as a background
Start-Job - Loops every 2s checking file mtimes in
source\+resources\ - On change: stop old monkeydo job → re-compile → start new monkeydo job
- On Ctrl+C:
try/finallycleans up the background job
Caveats
- 2-second poll latency — rebuild starts up to 2s after Ctrl+S. Acceptable for watch face dev.
- Device logs hidden —
monkeydoruns as a background job, soSystem.printlndoesn't appear in this terminal. To see logs:Receive-Job <job-id> -Keep, or userun.ps1instead. - Rapid saves — if you save twice within one build cycle, the second change may be missed. Save once, wait for
PUSHED, save again. - Simulator must stay open — closing it kills monkeydo's socket; the next push fails silently. Re-run
run.ps1to recover.
When to prefer run.ps1 instead
- You want to see device logs (debugging with
System.println) - You're doing fewer than ~3 builds in a sitting (re-running run.ps1 manually is fine)
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.
- 8d ago First seen · 42 lines · 0 tokens per session scan A 52e562bacaec
watch 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 438 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
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
design-form
Design a form with the fewest fields that works, clear labels, and errors that help.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.
review
Submit a story for verification (In Progress → In Review, no PR yet).
standup
Alias of /board — the async sprint snapshot.
diagram
Generate an Excalidraw architecture or flow diagram using the ExcaliClaude skill.