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 JakubMikolajek/codex-skills-collection --skill stm32-halgit clone --depth 1 https://github.com/JakubMikolajek/codex-skills-collectionWrote 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/jakubmikolajek/codex-skills-collection/stm32-hal)<a href="https://agentmods.dev/skills/jakubmikolajek/codex-skills-collection/stm32-hal"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/stm32-hal/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/jakubmikolajek/codex-skills-collection/stm32-hal"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/stm32-hal.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 | $0.00093 | $0.03441 |
| Opus 5 | $0.00046 | $0.01721 |
| Sonnet 5 | $0.00019 | $0.00688 |
| Haiku 4.5 | $0.00009 | $0.00344 |
Grade A, and why
stm32-hal 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 11d 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STM32 with HAL
STM32 is the dominant microcontroller family in commercial embedded. This skill covers HAL-based development — the recommended starting point for most projects — with notes on where LL (Low-Layer) drivers are preferable for performance.
When to Use
- Writing firmware for any STM32 microcontroller (F0/F1/F4/F7/H7/G4/L4/WB)
- Reviewing STM32 HAL driver usage for correctness
- Adding peripherals to a CubeMX-generated project
- Debugging HAL timeout, DMA transfer, or interrupt issues
When NOT to Use
- ESP32 — use
esp32-idf - RP2040 — different SDK (Pico SDK), different patterns
- AVR — different toolchain, avr-libc
Project Setup
CubeMX Workflow
CubeMX generates the peripheral initialization code. Your application code goes in the USER CODE BEGIN/END sections — this survives code re-generation.
project/
├── Core/
│ ├── Inc/
│ │ ├── main.h # CubeMX generated
│ │ └── stm32f4xx_hal_conf.h
│ └── Src/
│ ├── main.c # Add app code in USER CODE sections
│ ├── stm32f4xx_it.c # ISR handlers — add your code here
│ └── stm32f4xx_hal_msp.c
├── Drivers/
│ ├── STM32F4xx_HAL_Driver/
│ └── CMSIS/
├── Middlewares/
│ └── Third_Party/FreeRTOS/ # if RTOS enabled in CubeMX
├── CMakeLists.txt # or .ioc + CubeIDE project
└── STM32F407VGTx_FLASH.ld # linker script (CubeMX generated)
CMake with arm-none-eabi
# CMakeLists.txt for STM32F4 project
cmake_minimum_required(VERSION 3.22)
project(my_firmware C CXX ASM)
set(CMAKE_C_STANDARD 11)
set(CMAKE_CXX_STANDARD 17)
# MCU-specific flags — adjust for your part
set(CPU_FLAGS
-mcpu=cortex-m4
-mthumb
-mfpu=fpv4-sp-d16
-mfloat-abi=hard
)
add_compile_options(
${CPU_FLAGS}
-ffunction-sections
-fdata-sections
-fno-exceptions # C++ only
-fno-rtti # C++ only
-Wall
-Wextra
-Os
)
add_link_options(
${CPU_FLAGS}
-T${CMAKE_SOURCE_DIR}/STM32F407VGTx_FLASH.ld
-Wl,--gc-sections
-Wl,--print-memory-usage
-specs=nano.specs # newlib-nano: reduced printf/malloc
-specs=nosys.specs # no system calls (bare metal)
)
# Collect sources
file(GLOB_RECURSE SOURCES
Core/Src/*.c
Drivers/STM32F4xx_HAL_Driver/Src/*.c
)
# Exclude template files
list(FILTER SOURCES EXCLUDE REGEX ".*_template\\.c")
add_executable(${PROJECT_NAME}.elf ${SOURCES} startup_stm32f407vgtx.s)
target_include_directories(${PROJECT_NAME} PRIVATE
Core/Inc
Drivers/STM32F4xx_HAL_Driver/Inc
Drivers/CMSIS/Device/ST/STM32F4xx/Include
Drivers/CMSIS/Include
)
target_compile_definitions(${PROJECT_NAME} PRIVATE
USE_HAL_DRIVER
STM32F407xx
)
# Generate .bin and .hex
add_custom_command(TARGET ${PROJECT_NAME}.elf POST_BUILD
COMMAND ${CMAKE_OBJCOPY} -O ihex $<TARGET_FILE:${PROJECT_NAME}.elf> ${PROJECT_NAME}.hex
COMMAND ${CMAKE_OBJCOPY} -O binary $<TARGET_FILE:${PROJECT_NAME}.elf> ${PROJECT_NAME}.bin
COMMAND ${CMAKE_SIZE} $<TARGET_FILE:${PROJECT_NAME}.elf>
)
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.
- 11d ago First seen · 362 lines · 93 tokens per session scan A 23c024d3d176
stm32-hal is a skill published in the GitHub repository JakubMikolajek/codex-skills-collection (5 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 3,441 once invoked, about $0.0005 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
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…
embedded-stm32
Best practices for embedded C/C++ development on STM32 microcontrollers using the HAL, covering peripherals, DMA, interrupts, memory constraints, and hardware-focused testing. Use when writing STM32 HAL code, configuring peripherals generated by STM32CubeMX, working with interrupts or DMA, debugging with SWD/JTAG…
hip-kernel-optimization
This skill should be used when writing or tuning HIP kernels on AMD/NVIDIA GPUs, covering memory coalescing, shared-memory tiling, bank conflict avoidance, warp primitives, occupancy, vectorization, async ops, loop unrolling, and profiling.
cuda
Use when writing CUDA kernels, managing the thread, block, and grid hierarchy, tiling shared memory, using streams, setting nvcc flags, or using Thrust. Not for kernel debugging: use cuda-debugging.
acad-arx-wizard
Agentic ObjectARX project scaffolding for AutoCAD 2027 / Visual Studio 2026. Replaces the broken .vsz VsWizardEngine wizard with a PowerShell script that generates identical C++ project files. Works for new ARX/DBX/CRX projects and add-on class wizards (Jig, Reactors, Custom Object, MFC, .NET Wrapper, COM Wrapper…
hls-c2rtl
Translate C / C++ / SystemC algorithmic descriptions into synthesizable RTL via High-Level Synthesis. Use when the user says "HLS", "C to RTL", "C++ to Verilog", "Vitis HLS", "Catapult", "XLS", "algorithmic design", or provides a reference implementation in software and asks for hardware.