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/captainluzik/oh-my-embeddedWrote 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/captainluzik/oh-my-embedded/review-firmware)<a href="https://agentmods.dev/commands/captainluzik/oh-my-embedded/review-firmware"><img src="https://agentmods.dev/badge/commands/captainluzik/oh-my-embedded/review-firmware/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/captainluzik/oh-my-embedded/review-firmware"><img src="https://agentmods.dev/badge/commands/captainluzik/oh-my-embedded/review-firmware.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 | $0.00019 | $0.01264 |
| Opus 5 | $0.00010 | $0.00632 |
| Sonnet 5 | $0.00004 | $0.00253 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
review-firmware 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 10d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perform a structured embedded firmware code review on the C/C++ source files in this project. Focus on issues that matter in constrained, real-time, and safety-sensitive environments.
Arguments
$ARGUMENTS may contain:
- A specific file or directory to review (e.g.
src/motor.c,components/sensors/). - A severity filter:
p0,p1,p2,p3to show only findings at that level or above. - The keyword
isrto focus exclusively on interrupt service routine issues. - The keyword
rtosto focus exclusively on RTOS/concurrency issues.
Step 1: Locate source files
If $ARGUMENTS specifies a path, review only that path. Otherwise scan:
main/,src/,lib/,components/,Core/Src/(STM32CubeIDE layout)- Include:
*.c,*.cpp,*.h,*.hpp - Exclude:
build/,.pio/,managed_components/, third-party vendor directories.
List the files you will review before starting.
Step 2: Review categories
Work through each category below. For every finding, record:
- Severity (P0-P3, defined below)
- File and line number
- Short title
- Explanation of why it's a problem in an embedded context
- Suggested fix with a corrected code snippet where helpful
Severity levels
| Level | Meaning |
|---|---|
| P0 | Critical. Will cause crashes, data corruption, or undefined behavior at runtime. Fix before shipping. |
| P1 | High. Likely to cause hard-to-reproduce bugs, race conditions, or silent failures under load. |
| P2 | Medium. Bad practice that reduces reliability or portability. Should be fixed. |
| P3 | Low. Style, readability, or minor improvement. Fix when convenient. |
Category A: Memory safety
- Stack overflows: large arrays or structs declared on the stack inside ISRs or deeply nested calls.
- Heap fragmentation: repeated
malloc/freein a loop or ISR without a pool allocator. - Buffer overruns:
strcpy,sprintf,getswithout bounds checking. - Use-after-free or double-free patterns.
- Uninitialized variables used before assignment.
- Integer overflow in pointer arithmetic or array indexing.
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.
- 10d ago First seen · 112 lines · 19 tokens per session scan A f8b8ba04cffb
review-firmware is a command published in the GitHub repository captainluzik/oh-my-embedded (24 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 1,264 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 commands, from other repositories
ruview-app
Run a RuView sensing application — presence, vitals, pose, sleep, environment mapping, MAT, point cloud, or a novel RF app.
ruview-start
Get started with RuView — pick the fastest path (Docker demo, repo build, or live ESP32) and walk through it.
review-diff
Review the current working diff for correctness, security, and reuse.
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.
size
A command that reads a Keil compiler .map file, a build report describing where firmware uses memory. It reports Flash, RAM, stack, and heap allocation and compares usage with warning limits.
iot
You are an iot-protocol-engineer agent with deep expertise across MQTT, CoAP, LwM2M, BLE GATT, LoRaWAN, Thread, and Zigbee. Help the user choose the right protocol for their constraints and design the protocol layer correctly.