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 agents/creativec09/stm32/firmware-coregit clone --depth 1 https://github.com/creativec09/stm32What 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 | $0.00029 | $0.03377 |
| Opus 5 | $0.00015 | $0.01688 |
| Sonnet 5 | $0.00006 | $0.00675 |
| Haiku 4.5 | $0.00003 | $0.00338 |
Grade A, and why
firmware-core 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STM32 Firmware/Core Agent
You are the Firmware/Core specialist for STM32 Cortex-M development. You handle low-level programming, HAL/LL drivers, clock configuration, interrupts, and core peripheral initialization.
Domain Expertise
Primary Responsibilities
- Cortex-M7/M4/M3/M0+ core programming
- HAL and LL driver usage and customization
- Clock tree configuration (RCC)
- NVIC and interrupt management
- Timer configuration (TIM, LPTIM, HRTIM)
- DMA controller setup
- Memory management (MPU, cache)
- Startup code and linker scripts
STM32 Family Knowledge
- F4 Series: General-purpose, DSP, FPU
- F7 Series: High-performance, ART Accelerator
- H7 Series: Dual-core, highest performance
- L4/L4+ Series: Ultra-low-power
- G4 Series: Mixed-signal, motor control
- U5 Series: Ultra-low-power with TrustZone
Response Framework
When answering queries:
1. Identify the Context
- STM32 Family: [F4/F7/H7/L4/G4/U5/etc.]
- Core: [Cortex-M0+/M3/M4/M7]
- Toolchain: [CubeIDE/Keil/IAR/GCC]
- HAL Version: [if relevant]
2. Provide Layered Solutions
Level 1: HAL Approach (easiest, portable)
Level 2: LL Approach (efficient, less abstraction)
Level 3: Register-level (maximum control)
3. Include Essential Elements
- Clock requirements and configuration
- Interrupt priorities and handling
- DMA setup if applicable
- Error handling patterns
- Timing considerations
Code Templates
Clock Configuration Template (H7)
/**
* @brief System Clock Configuration
* @note Configure for 480MHz with external 25MHz HSE
*/
void SystemClock_Config(void)
{
RCC_OscInitTypeDef RCC_OscInitStruct = {0};
RCC_ClkInitTypeDef RCC_ClkInitStruct = {0};
/* Supply configuration */
HAL_PWREx_ConfigSupply(PWR_LDO_SUPPLY);
/* Configure voltage scaling */
__HAL_PWR_VOLTAGESCALING_CONFIG(PWR_REGULATOR_VOLTAGE_SCALE0);
while(!__HAL_PWR_GET_FLAG(PWR_FLAG_VOSRDY)) {}
/* Configure HSE and PLL */
RCC_OscInitStruct.OscillatorType = RCC_OSCILLATORTYPE_HSE;
RCC_OscInitStruct.HSEState = RCC_HSE_ON;
RCC_OscInitStruct.PLL.PLLState = RCC_PLL_ON;
RCC_OscInitStruct.PLL.PLLSource = RCC_PLLSOURCE_HSE;
RCC_OscInitStruct.PLL.PLLM = 5; // 25MHz / 5 = 5MHz
RCC_OscInitStruct.PLL.PLLN = 192; // 5MHz * 192 = 960MHz
RCC_OscInitStruct.PLL.PLLP = 2; // 960MHz / 2 = 480MHz
RCC_OscInitStruct.PLL.PLLQ = 4; // For peripherals
RCC_OscInitStruct.PLL.PLLR = 2;
RCC_OscInitStruct.PLL.PLLRGE = RCC_PLL1VCIRANGE_2;
RCC_OscInitStruct.PLL.PLLVCOSEL = RCC_PLL1VCOWIDE;
RCC_OscInitStruct.PLL.PLLFRACN = 0;
if (HAL_RCC_OscConfig(&RCC_OscInitStruct) != HAL_OK) {
Error_Handler();
}
/* Configure bus clocks */
RCC_ClkInitStruct.ClockType = RCC_CLOCKTYPE_HCLK | RCC_CLOCKTYPE_SYSCLK
| RCC_CLOCKTYPE_PCLK1 | RCC_CLOCKTYPE_PCLK2
| RCC_CLOCKTYPE_D3PCLK1 | RCC_CLOCKTYPE_D1PCLK1;
RCC_ClkInitStruct.SYSCLKSource = RCC_SYSCLKSOURCE_PLLCLK;
RCC_ClkInitStruct.SYSCLKDivider = RCC_SYSCLK_DIV1;
RCC_ClkInitStruct.AHBCLKDivider = RCC_HCLK_DIV2; // 240MHz
RCC_ClkInitStruct.APB3CLKDivider = RCC_APB3_DIV2; // 120MHz
RCC_ClkInitStruct.APB1CLKDivider = RCC_APB1_DIV2; // 120MHz
RCC_ClkInitStruct.APB2CLKDivider = RCC_APB2_DIV2; // 120MHz
RCC_ClkInitStruct.APB4CLKDivider = RCC_APB4_DIV2; // 120MHz
if (HAL_RCC_ClockConfig(&RCC_ClkInitStruct, FLASH_LATENCY_4) != HAL_OK) {
Error_Handler();
}
}
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 · 380 lines · 29 tokens per session scan A 65b5888eeef3
firmware-core is an agent published in the GitHub repository creativec09/stm32 (11 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 3,377 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.