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 mohitmishra786/low-level-dev-skills --skill stm32-baremetalgit clone --depth 1 https://github.com/mohitmishra786/low-level-dev-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/mohitmishra786/low-level-dev-skills/stm32-baremetal)<a href="https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/stm32-baremetal"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/stm32-baremetal/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/mohitmishra786/low-level-dev-skills/stm32-baremetal"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/stm32-baremetal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.01316 |
| Opus 5 | $0.00041 | $0.00658 |
| Sonnet 5 | $0.00016 | $0.00263 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
stm32-baremetal 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STM32 Bare-Metal (CMSIS, No HAL)
Purpose
Guide agents through a minimal STM32 bare-metal project using CMSIS device headers and startup code only — no STM32 HAL — covering clock setup, linker script integration, peripheral register access, and a reproducible build layout for STM32F/G/H/L families.
When to Use
- Starting STM32 firmware without Cube HAL dependency
- Porting vendor examples to register-level drivers
- Integrating with
skills/baremetal/baremetal-startupandskills/embedded/linker-scripts - Debugging clock or flash placement issues on STM32
- Teaching register-level STM32 before RTOS or Zephyr
Workflow
1. Minimal project layout
stm32-bare/
├── startup_stm32f407xx.s # vector table + Reset_Handler
├── system_stm32f4xx.c # SystemInit(), SystemCoreClockUpdate()
├── stm32f407xx.h # CMSIS (from ST pack or copy)
├── linker.ld # FLASH/RAM regions
├── main.c
└── Makefile
Use CMSIS-Core (core_cm4.h) and device header from ST CMSIS pack or open-source packs (e.g. stm32-cmsis-device-f4).
2. Clock configuration (RCC)
STM32 requires explicit HSE/HSI and PLL setup before high-speed peripherals:
/* system_stm32f4xx.c — simplified PLL from 8 MHz HSE */
void SystemInit(void)
{
RCC->CR |= RCC_CR_HSEON;
while (!(RCC->CR & RCC_CR_HSERDY)) {}
RCC->PLLCFGR = RCC_PLLCFGR_PLLSRC_HSE | (8 << 0) | (336 << 6) | (0 << 16) | (7 << 24);
RCC->CFGR |= RCC_CFGR_PPRE1_DIV2 | RCC_CFGR_PPRE2_DIV1 | RCC_CFGR_HPRE_DIV1;
RCC->CR |= RCC_CR_PLLON;
while (!(RCC->CR & RCC_CR_PLLRDY)) {}
FLASH->ACR = FLASH_ACR_LATENCY_5WS;
RCC->CFGR |= RCC_CFGR_SW_PLL;
while ((RCC->CFGR & RCC_CFGR_SWS) != RCC_CFGR_SWS_PLL) {}
SystemCoreClockUpdate();
}
Always match FLASH_ACR wait states to voltage scale and SYSCLK per reference manual table.
3. Enable peripheral clock before MMIO
#define RCC_AHB1ENR_GPIOAEN (1U << 0)
static inline void gpioa_clock_enable(void)
{
RCC->AHB1ENR |= RCC_AHB1ENR_GPIOAEN;
(void)RCC->AHB1ENR; /* AHB read-after-write — required on STM32 */
}
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 · 118 lines · 82 tokens per session scan A 3125a5d569d0
stm32-baremetal is a skill published in the GitHub repository mohitmishra786/low-level-dev-skills (202 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,316 once invoked, about $0.0004 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 2026-08-30.
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.