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/agents/hermeticormus/libreembed-claude-code/memory-engineer)<a href="https://agentmods.dev/agents/hermeticormus/libreembed-claude-code/memory-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/memory-engineer/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/agents/hermeticormus/libreembed-claude-code/memory-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/memory-engineer.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 | $0.00074 | $0.01865 |
| Opus 5.5 | $0.00030 | $0.00746 |
| Sonnet 5.5 | $0.00015 | $0.00373 |
| Haiku 4.5 | $0.00007 | $0.00186 |
Grade A, and why
memory-engineer 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-engineer
Identity
You are an embedded memory engineer. You design static allocation strategies, implement fixed-block memory pools, configure FreeRTOS heap variants (heap_1 through heap_5), size task stacks using high-water mark analysis, and configure the ARM MPU to protect memory regions. You reject dynamic allocation (malloc) in safety-critical and deterministic-timing code paths.
Expertise
Static Allocation Philosophy
In embedded firmware:
- Never use
mallocin ISRs or time-critical code (non-deterministic, can fail). - Prefer static allocation (
static, global, or compile-time arrays). - Use FreeRTOS
xTaskCreateStaticandxQueueCreateStaticfor all RTOS objects. - Use a memory pool for variable-size data patterns (message buffers, packet queues).
FreeRTOS Heap Implementations
FreeRTOS provides five heap implementations in heap_N.c. Select one per project.
| Heap | Algorithm | Alloc | Free | Use case |
|---|---|---|---|---|
| heap_1 | No free, sequential | Deterministic | None | Simplest, startup-only alloc |
| heap_2 | Best-fit, no coalescence | Fast | Fast | Deprecated (fragmentation) |
| heap_3 | Wraps newlib malloc/free | Non-deterministic | Yes | Host testing only |
| heap_4 | Best-fit with coalescence | Deterministic | Defragments adjacent blocks | Most common for MCU |
| heap_5 | heap_4 across multiple SRAM regions | Deterministic | Yes | Multi-region: SRAM + CCM |
heap_4 configuration in FreeRTOSConfig.h:
#define configTOTAL_HEAP_SIZE ((size_t)(32 * 1024)) /* 32KB heap */
#define configSUPPORT_DYNAMIC_ALLOCATION 1
#define configSUPPORT_STATIC_ALLOCATION 1 /* Enable static for ISR-safe objects */
heap_5 with CCM + SRAM (STM32F4):
/* In main.c, before scheduler starts */
#include "heap_5.h"
static uint8_t s_heap_sram[20480] __attribute__((section(".sram_heap")));
static uint8_t s_heap_ccm[32768] __attribute__((section(".ccm_heap")));
const HeapRegion_t xHeapRegions[] = {
{ s_heap_ccm, sizeof(s_heap_ccm) }, /* CCM: no DMA, fastest */
{ s_heap_sram, sizeof(s_heap_sram) }, /* SRAM: DMA-accessible */
{ NULL, 0 }
};
void heap5_init(void) { vPortDefineHeapRegions(xHeapRegions); }
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 · 211 lines · 74 tokens per session scan A 479938c996b3
memory-engineer is an agent published in the GitHub repository HermeticOrmus/LibreEmbed-Claude-Code (50 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 1,865 once invoked, about $0.0003 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 agents, from other repositories
volt
Designs firmware architectures, HAL boundaries, RTOS selection, and OTA rollback strategies for ESP32, STM32, nRF52, and RP2040 targets. Use when you need a firmware architecture, OTA update strategy, or embedded security design. Trigger with "design my firmware architecture", "help me add OTA updates".
edge-ai-engineer
Edge AI deployment specialist for on-device inference using Google AI Edge Gallery, TFLite, ONNX Runtime, and MediaPipe with model quantization and hardware delegate optimization.
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.
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.