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/releaseWrote 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/release)<a href="https://agentmods.dev/commands/athitupakan/garmin-dev-skills/release"><img src="https://agentmods.dev/badge/commands/athitupakan/garmin-dev-skills/release.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 | $0.00531 |
| Opus 5 | $0.00000 | $0.00266 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
release 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 6d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
release — release.ps1
Compile a release-stripped build for the active device → bin\<project>-release.prg.
Single device, single .prg. Does not push.
Use to verify the optimized binary still runs in the simulator before packaging for the store.
Run
# Windows
.\.claude\skills\garmin-dev\scripts\windows\release.ps1
# macOS / Linux
./.claude/skills/garmin-dev/scripts/posix/release.sh
Why test release before packaging
The -r / --release flag strips debug info AND lets the compiler optimize more aggressively. This is exactly the build the store ships. Release builds can break in ways debug builds never see:
- Type pruning — code reachable only from debug paths gets eliminated. If anything was relying on side effects in those paths, it disappears.
- Latent null/type errors — debug builds tolerate some sloppy types via runtime checks; release strips those.
- Aggressive inlining — exposes ordering assumptions that the debug build's slower dispatch hid.
So: always release.ps1 + push + verify in sim FIRST. Only then package.ps1.
Output naming
Output is intentionally distinct from bin\<project>.prg (the debug build) so push.ps1 / run.ps1 — which target the debug $Prg — don't accidentally push the release binary on the next dev-loop iteration.
Pushing the release build to the simulator
push targets $Prg (the debug name). To push the release binary, invoke monkeydo directly:
# Windows
. .\.claude\skills\garmin-dev\scripts\windows\_env.ps1
& "$Sdk\bin\monkeydo.bat" "bin\$Project-release.prg" $Device
# macOS / Linux
. ./.claude/skills/garmin-dev/scripts/posix/_env.sh
"$Sdk/bin/monkeydo" "bin/${Project}-release.prg" "$Device"
(Long-lived — pass run_in_background: true in PowerShell / Bash tool calls.)
On failure
- Type errors that pass in debug → almost always a missing null guard. Fix in source.
- Other unexpected errors → ../troubleshooting.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.
- 6d ago First seen · 56 lines · 0 tokens per session scan A ce42fdb1099d
release 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 531 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
scope
Command "scope" from jzl-maker/EA-SKILL, covering 命令: /ea scope (示波器), 功能, 调用方式, ✅ 确认 pyvisa 栈 / visa 资源 / 设备 and 抓波形：chan1，存 csv + 出图.
debug
自主调试四件套，用于「代码跑哪了 / 变量值对不对 / 根因是什么」。双后端：--backend jlink（默认）或 --backend openocd（ST-Link/DAP 用，无停机监控）。.
la
Saleae 逻辑分析仪（Logic 8 / Logic 16 / Pro 8 / Pro 16）抓取 + 协议解码，用于排查 UART/SPI/I2C 等总线时序。.
svd
解析芯片 SVD 寄存器描述文件（CMSIS-SVD，Keil Pack 自带），把「门牌号（外设基地址）+ 住户名单（寄存器/位域）」查出来，还能免查手册读寄存器当前值并解码位域含义。.
map
解析 Keil 编译生成的 .map 文件，输出 对象内存排行 / 内存分段分布 / 符号地址映射 / 栈堆详情，用于定位内存大户、核对链接布局、查符号地址。.
size
解析 Keil 编译生成的 .map 文件，统计固件 Flash / RAM / 栈 / 堆 使用情况，并支持超限预警（使用率 ≥ warn 警告，≥ err 超限）。.