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 skills add gandarez/agent-skills --skill tinygogit clone --depth 1 https://github.com/gandarez/agent-skillsWrote 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/gandarez/agent-skills/tinygo)<a href="https://agentmods.dev/skills/gandarez/agent-skills/tinygo"><img src="https://agentmods.dev/badge/skills/gandarez/agent-skills/tinygo/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/gandarez/agent-skills/tinygo"><img src="https://agentmods.dev/badge/skills/gandarez/agent-skills/tinygo.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 | $0.00056 | $0.03956 |
| Opus 5.5 | $0.00022 | $0.01582 |
| Sonnet 5.5 | $0.00011 | $0.00791 |
| Haiku 4.5 | $0.00006 | $0.00396 |
Grade A, and why
tinygo 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 2mo 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 — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TinyGo Development
Expert guidance for developing with TinyGo — the Go compiler for microcontrollers, WebAssembly, and other small targets. Covers project setup, peripheral programming, driver integration, WASM builds, and optimization for constrained environments.
When to Use
- User is writing Go code for microcontrollers or embedded systems
- User wants to compile Go to WebAssembly using TinyGo
- User is working with
machinepackage, GPIO, I2C, SPI, UART, ADC, PWM, or DAC - User is integrating
tinygo.org/x/driversfor sensors, displays, or other hardware - User asks about flashing firmware to a board
- User needs help reducing binary size for constrained devices
- User references TinyGo, any supported board (Arduino, Raspberry Pi Pico, ESP32, etc.), or embedded Go
Core Principles
- Minimize allocations — Heap is scarce on microcontrollers. Prefer stack variables, fixed-size arrays in structs, and avoid string concatenation in loops.
- Avoid
fmton constrained targets — Use the builtinprintln()instead.fmt.Printlnpulls in reflection and adds significant binary size. - Design drivers against interfaces, not
machine— Never importmachinein reusable driver code. Acceptdrivers.I2C,drivers.SPI, etc. - Always debounce physical inputs — Buttons and switches generate electrical noise. Guard interrupt handlers with a minimum interval (typically 100ms).
- Use volatile for shared state — Variables shared between interrupt handlers and main code must use
runtime/volatileoperations.
Project Scaffolding
Step 1 — Initialize the module
mkdir myproject && cd myproject
go mod init myproject
Step 2 — Create main.go
Use the appropriate template based on target type.
Microcontroller (e.g., Arduino, Pico, ESP32)
package main
import (
"machine"
"time"
)
func main() {
led := machine.LED
led.Configure(machine.PinConfig{Mode: machine.PinOutput})
for {
led.High()
time.Sleep(500 * time.Millisecond)
led.Low()
time.Sleep(500 * time.Millisecond)
}
}
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.
- 2mo ago First seen · 580 lines · 56 tokens per session scan A b56ea11399e9
tinygo is a skill published in the GitHub repository gandarez/agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 56 tokens to every session and 3,956 once invoked, about $0.0002 per session on Opus 5.5. 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.
tinygo compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tinygogandarez/agent-skills | Skill | 2 | 7mo ago | MIT | A | 56 | Claude Code, Codex |
| wasmTheBeardedBearSAS/claude-craft | Skill | 107 | 3d ago | MIT | A | 43 | Claude Code |
| analyzing-golang-malware-internalsmeltedinhex/analyst-ai-pack | Skill | 24 | 4mo ago | Apache-2.0 | A | 65 | Claude Code, Codex |
| ikuai-cliikuaios/ikuai-cli | Skill | 15 | 4mo ago | MIT | C | 112 | Claude Code, Codex |
| viam-go-platformviam-devrel/agent-skills | Skill | 2 | 3mo ago | none | A | 216 | Claude Code |
| viam-go-motion-visionviam-devrel/agent-skills | Skill | 2 | 3mo ago | none | A | 204 | Claude Code |
| analyzing-golang-malware-with-ghidraYoungmaidainon/Agent-Level-Up | Skill | 4 | 2mo ago | MIT | A | 95 | Claude Code, Codex |