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.
git clone --depth 1 https://github.com/HermeticOrmus/LibreEmbed-Claude-CodeWrote 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/commands/hermeticormus/libreembed-claude-code/cortex-m)<a href="https://agentmods.dev/commands/hermeticormus/libreembed-claude-code/cortex-m"><img src="https://agentmods.dev/badge/commands/hermeticormus/libreembed-claude-code/cortex-m/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/commands/hermeticormus/libreembed-claude-code/cortex-m"><img src="https://agentmods.dev/badge/commands/hermeticormus/libreembed-claude-code/cortex-m.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 | $0.00025 | $0.01195 |
| Opus 5.5 | $0.00010 | $0.00478 |
| Sonnet 5.5 | $0.00005 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
cortex-m 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 15d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cortex-m
ARM Cortex-M development command: startup code, linker scripts, peripheral configuration, and debug.
Trigger
/cortex-m <action> [options]
Actions
init
Generate startup code and linker script for a target MCU.
/cortex-m init --mcu stm32f407 --flash 1024K --sram 192K --ccm 64K
/cortex-m init --mcu nrf52840 --flash 1024K --sram 256K
Generates:
startup_stm32f407xx.sor.c(Reset_Handler, vector table, .data copy, .bss zeroing)stm32f407.ld(MEMORY regions, SECTIONS with LMA/VMA separation)system_init.c(clock tree, FPU enable, SysTick)
configure
Configure a specific Cortex-M subsystem.
/cortex-m configure --subsystem nvic --groups 4
/cortex-m configure --subsystem fpu --core m4
/cortex-m configure --subsystem mpu --guard-stack 0x20000000 --size 32
/cortex-m configure --subsystem systick --freq-hz 168000000 --tick-ms 1
debug
Analyze fault conditions and decode exception frames.
/cortex-m debug --fault hardfault
/cortex-m debug --fault memmanage
/cortex-m debug --decode-cfsr 0x00000082
/cortex-m debug --stack-frame 0x20001F00
Outputs: decoded CFSR/HFSR/BFAR/MMFAR, stacked register dump, fault cause in plain English.
benchmark
Generate DWT-based timing instrumentation.
/cortex-m benchmark --function my_dsp_filter --core m4
/cortex-m benchmark --isr uart_rx_handler --cycles
Process
- Confirm target core variant (determines available features: FPU, DSP, MPU regions, DWT).
- Read existing linker script and startup if present.
- Generate or modify requested artifact.
- Include barrier instructions (
__DSB,__ISB) wherever system register writes occur. - Verify generated ISR names against device header
IRQn_Typeenum.
Output Examples
Minimal linker script fragment (STM32F407, Cortex-M4)
MEMORY
{
FLASH (rx) : ORIGIN = 0x08000000, LENGTH = 1024K
SRAM (rwx) : ORIGIN = 0x20000000, LENGTH = 128K
SRAM2 (rwx) : ORIGIN = 0x2001C000, LENGTH = 16K
CCM (rwx) : ORIGIN = 0x10000000, LENGTH = 64K
}
_estack = ORIGIN(SRAM) + LENGTH(SRAM);
SECTIONS
{
.isr_vector :
{
. = ALIGN(4);
KEEP(*(.isr_vector))
. = ALIGN(4);
} > FLASH
.text :
{
. = ALIGN(4);
*(.text)
*(.text*)
*(.rodata)
*(.rodata*)
. = ALIGN(4);
_etext = .;
} > FLASH
.data :
{
. = ALIGN(4);
_sdata = .;
*(.data)
*(.data*)
. = ALIGN(4);
_edata = .;
} > SRAM AT > FLASH
_sidata = LOADADDR(.data);
.bss :
{
. = ALIGN(4);
_sbss = .;
*(.bss)
*(.bss*)
*(COMMON)
. = ALIGN(4);
_ebss = .;
} > SRAM
}
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.
- 15d ago First seen · 164 lines · 25 tokens per session scan A 289b2d7b82b5
cortex-m is a command published in the GitHub repository HermeticOrmus/LibreEmbed-Claude-Code (50 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 1,195 once invoked, about $0.0001 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 2026-10-01.
Other commands, from other repositories
debug
A command-line debugging toolkit for embedded programs using J-Link or OpenOCD, tools that connect a computer to a microcontroller for inspection.
la
A command for capturing and decoding signals with a Saleae logic analyzer, a device that records electrical digital signals over time. It supports buses such as UART, SPI, and I2C, which are common ways chips communicate with peripherals.
map
A parser for Keil compiler map files, which are build reports describing where program code and data are placed in memory. It reports object sizes, memory regions, symbols, and stack or heap details.
verify
An embedded-device verification workflow that checks a development step through building, flashing firmware, debugging with J-Link, and reading serial logs. Firmware is software that runs directly on a microcontroller or other device.
debug
Start GDB debug session with OpenOCD or probe-rs.
t32
TRACE32 setup, container lifecycle, GUI reopen flow, RCL/GDB interfaces, PRACTICE scripts, and probe troubleshooting.