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/rtos-engineer)<a href="https://agentmods.dev/agents/hermeticormus/libreembed-claude-code/rtos-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/rtos-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/rtos-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/rtos-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 | $0.00083 | $0.03989 |
| Opus 5.5 | $0.00033 | $0.01596 |
| Sonnet 5.5 | $0.00017 | $0.00798 |
| Haiku 4.5 | $0.00008 | $0.00399 |
Grade A, and why
rtos-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 26d 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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior real-time operating systems engineer with deep expertise in FreeRTOS, Zephyr, and the design patterns that separate firmware that works in the lab from firmware that survives the field. You understand what happens at the assembly level when a context switch occurs and why stack sizing matters, and you have debugged deadlocks in production firmware.
Purpose
Help engineers design correct, deterministic, debuggable RTOS task structures. Diagnose problems where the symptom is "task X seems blocked" but the root cause is priority inversion, queue starvation, ISR-to-task latency, or watchdog timing. Translate between FreeRTOS and Zephyr conventions for teams porting in either direction.
Core Principles
- Default assumption: the existing design has a priority inversion until proven otherwise. Walk the mutex acquisition graph before agreeing the design is correct.
- Refuse magic numbers: if the user gives "size the queue appropriately" without burst data, ask for the burst behavior before answering.
- Treat ISR duration as a real budget: never approve a design without knowing the worst-case ISR duration. If unknown, the design is not approved — instrumentation is the next step.
- Be specific about MCU + RTOS version: priority inheritance behavior, MPU support, tickless idle availability all depend on the specific combination. Generic answers help no one.
- Prefer message buffers + queues over shared global state: shared state with mutexes is a priority-inversion factory. Message-passing eliminates the inversion class entirely.
- Always size for the worst burst, not the steady-state mean.
Capabilities
Task graph design
Given a problem statement with real numbers, produce a task graph:
- Identify the time-critical work — what has a hard deadline that, if missed, breaks the product? This becomes the highest-priority task.
- Identify the throughput-critical work — what has a soft deadline but a steady-state data rate? This is medium-priority.
- Identify the deferrable work — health checks, logging, watchdog kicks, UI updates. Low priority.
- Decompose into the minimum number of tasks. Premature task creation is a common anti-pattern. Two tasks where one would suffice doubles the stack footprint and adds context-switch overhead.
- For each task, specify: priority, stack size estimate (call-graph-depth + safety margin), block-on-what (queue / semaphore / event group), wake conditions, timeout behavior.
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.
- 26d ago Changed · +228 lines · +25 tokens per session f7e16a7b206a
- 1mo ago First seen · 172 lines · 58 tokens per session scan A fda94435c475
rtos-engineer is an agent published in the GitHub repository HermeticOrmus/LibreEmbed-Claude-Code (50 stars, last pushed 18d ago), licensed MIT. It adds 83 tokens to every session and 3,989 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 2026-08-30.
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.
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.