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 agentmods add skills/lhbsaa/embedded-dev-skill/embedded-verificationnpx skills add lhbsaa/embedded-dev-skill --skill embedded-verificationgit clone --depth 1 https://github.com/lhbsaa/embedded-dev-skillWhat 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 | $0.00026 | $0.01085 |
| Opus 5 | $0.00013 | $0.00543 |
| Sonnet 5 | $0.00005 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
embedded-verification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Embedded Verification
Overview
The Iron Law enforcement phase. No completion claims without fresh verification evidence.
Core principle: Evidence before claims, always.
Context: Run after embedded-implementation completes all tasks.
The Iron Law
NO COMPLETION CLAIMS WITHOUT BUILD-FLASH-MONITOR VERIFICATION
Verification Gate
BEFORE claiming ANY status:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute FULL command (fresh, complete)
3. READ: Full output, check exit code, errors
4. VERIFY: Does output confirm?
5. ONLY THEN: Make the claim
Verification Types
| Type | Command | Expected |
|---|---|---|
| Build | idf.py build |
Exit 0, no errors |
| Flash | idf.py -p COM3 flash |
Exit 0, flash success |
| Monitor | idf.py monitor |
No crash, correct output |
| Full Loop | idf.py build flash monitor |
All pass |
Platform Commands
Windows PowerShell
# Build
idf.py build
if($LASTEXITCODE -eq 0) { echo "Build PASS" } else { echo "Build FAIL" }
# Flash + Monitor
idf.py -p COM3 flash; if($?) { idf.py monitor }
Linux/macOS Bash
# Build
idf.py build && echo "Build PASS"
# Flash + Monitor
idf.py -p /dev/ttyUSB0 flash monitor
Process
1. Build Verification
Run: idf.py build
Check:
- Exit code = 0
- No errors in output
- No unexpected warnings
If FAIL:
- Analyze error
- Fix
- Re-build
2. Flash Verification
Run: idf.py -p [PORT] flash
Check:
- Flash successful message
- No timeout errors
If FAIL:
- Check port (COMx / /dev/ttyUSBx)
- Check connection
- Re-flash
3. Monitor Verification
Run: idf.py monitor
Duration: 30-60 seconds minimum
Check:
- No Guru Meditation Error
- No assertion failures
- Expected log output present
- Initialization sequence logged
Use: scripts/serial_monitor.py for structured output
4. Runtime Behavior Check
Based on design spec:
| Feature | Verification |
|---|---|
| Display driver | Monitor shows init success |
| Sensor | Correct readings in log |
| Wi-Fi | Connected to AP |
| Protocol | Data transmission logged |
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.
- 2d ago First seen · 211 lines · 26 tokens per session scan A 31b355d5de96
embedded-verification is a skill published in the GitHub repository lhbsaa/embedded-dev-skill (9 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,085 once invoked, about $0.0001 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
driver-review
Review and implement hardware driver code — DMA safety, interrupt correctness, timing constraints, peripheral register usage, channel drivers, and peripheral mock implementations. Use when writing, modifying, or reviewing LED drivers, SPI/I2S/RMT/UART/PARLIO/LCDCAM peripherals, GPIO configuration, or peripheral mock…
esp32-arch-review
Review ESP32 FastLED firmware architecture for RTOS safety, DMA correctness, LED driver patterns, memory management, and peripheral safety. Use before merging significant driver changes, new platform ports, or when auditing existing ESP32 FastLED code.
esp32-log-triage
Parse and classify ESP32 serial log output to identify FastLED-related errors, RMT/I2S/SPI driver faults, timing violations, RTOS issues, and crash signatures. Use when debugging unexpected device behavior, boot failures, or LED output problems on ESP32.
embedded-debug
Firmware crash analysis, stack trace decoder, and register dump interpreter for ESP32/ARM/AVR platforms. Use when debugging device crashes, panics, guru meditation errors, hard faults, or analyzing core dumps.
platform-port
Guide porting FastLED to new MCU platforms, including int.h types, clockless drivers, SPI implementations, and platform detection. Use when adding support for a new microcontroller family or board.
memory-audit
Audit embedded code for stack overflow risks, heap fragmentation, static allocation patterns, and memory leaks. Use when investigating OOM crashes, optimizing memory usage, or reviewing memory-critical code on constrained devices.