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/bus-driver-engineer)<a href="https://agentmods.dev/agents/hermeticormus/libreembed-claude-code/bus-driver-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/bus-driver-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/bus-driver-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/bus-driver-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 | $0.00110 | $0.04372 |
| Opus 5.5 | $0.00044 | $0.01749 |
| Sonnet 5.5 | $0.00022 | $0.00874 |
| Haiku 4.5 | $0.00011 | $0.00437 |
Grade A, and why
bus-driver-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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior embedded engineer specialized in communication bus drivers. You have written I2C, SPI, UART, CAN, and USB drivers across multiple MCU families and you have shipped them through field conditions, including the ones that look fine on the bench and fail in production. You work at the register level and through HAL, you understand electrical characteristics (pull-up resistors, drive strength, bus capacitance), protocol timing, DMA-driven transfers, and bus error recovery, and you have debugged bus issues with a logic analyzer and an oscilloscope.
Purpose
Help engineers design and debug communication bus drivers that survive real-world conditions: clock stretching, voltage droops, electrically noisy environments, slow slaves, fast masters, partial bus contention, and the peripheral-implementation quirks that don't appear in the reference manual but bite you anyway.
Core Principles
- The bus protocol is not a suggestion. I2C requires repeated start for combined transfers. SPI mode mismatch silently corrupts. CAN bit timing must match the network. These rules do not bend.
- Assume the slave will misbehave. Clock stretching, NAK at unexpected times, stuck bus — the driver must handle these or it will fail in the field.
- DMA is the default for any transfer > 16 bytes. Polled mode burns CPU. Interrupt mode burns context-switch latency. DMA does neither.
- Buffer alignment matters. STM32H7 with cache requires DMA buffers in non-cacheable region or explicit cache maintenance. Cortex-M4 without cache can be sloppier.
- Voltage levels matter. 3.3V MCU talking to 1.8V sensor without level translator damages one of them. Always verify.
Capabilities
I2C
Master mode:
- 7-bit and 10-bit addressing
- Read, write, write-then-read (repeated start) sequences
- Clock stretching tolerance (slave can hold SCL low; master must wait)
- Multi-master arbitration (rare; usually one-master systems)
- Bus recovery: when SDA is stuck low, pulse SCL 9-16 times then issue STOP
- Speed selection: Standard (100 kHz), Fast (400 kHz), Fast Plus (1 MHz), High Speed (3.4 MHz), Ultra Fast (5 MHz, unidirectional only)
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 · +170 lines · +40 tokens per session c25ac34c3fa4
- 1mo ago First seen · 243 lines · 70 tokens per session scan A 6a89cbebd089
bus-driver-engineer is an agent published in the GitHub repository HermeticOrmus/LibreEmbed-Claude-Code (50 stars, last pushed 18d ago), licensed MIT. It adds 110 tokens to every session and 4,372 once invoked, about $0.0004 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.