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/bom)<a href="https://agentmods.dev/commands/captainluzik/oh-my-embedded/bom"><img src="https://agentmods.dev/badge/commands/captainluzik/oh-my-embedded/bom/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/bom"><img src="https://agentmods.dev/badge/commands/captainluzik/oh-my-embedded/bom.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 | $0.00010 | $0.00907 |
| Opus 5.5 | $0.00004 | $0.00363 |
| Sonnet 5.5 | $0.00002 | $0.00181 |
| Haiku 4.5 | $0.00001 | $0.00091 |
Grade A, and why
bom 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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract a Bill of Materials from the KiCad schematic in the current project and output it in a structured format.
Arguments
$ARGUMENTS may contain:
- An output format:
csv(default),json, ormarkdown. - An output file path (e.g.
bom.csv,hardware/bom.json). - The keyword
jlcpcbto format the CSV specifically for JLCPCB SMT assembly.
Step 1: Find the schematic
Search the project directory for KiCad schematic files:
*.kicad_sch
If multiple .kicad_sch files exist, prefer the top-level one (usually matches the project directory name or contains the most component references). List all found files and state which one you're using.
Step 2: Parse components
Read the .kicad_sch file. It's a text-based S-expression format. Extract every (symbol ...) block that has a reference starting with a letter (R, C, U, J, Q, L, D, etc.) and is not a power symbol or graphical annotation.
For each component, collect:
- Reference (e.g.
R1,C4,U2) - Value (e.g.
10k,100nF,STM32F103C8T6) - Footprint (e.g.
Resistor_SMD:R_0402) - LCSC part number if present in the
LCSCorlcscproperty field. - Manufacturer part number if present in
MPNorManufacturer_Part_Numberfields. - Datasheet URL if present.
Step 3: Group and deduplicate
Group components by identical (Value + Footprint). Within each group:
- List all references together (e.g.
R1, R3, R7). - Count the quantity.
- Show the LCSC/MPN if available.
Sort groups by reference prefix, then by value.
Step 4: Output the BOM
Standard CSV (default)
Reference,Value,Footprint,Quantity,LCSC,MPN,Datasheet
"R1, R3, R7",10k,Resistor_SMD:R_0402,3,C25804,,
"C1, C2",100nF,Capacitor_SMD:C_0402,2,C307331,,
"U1",STM32F103C8T6,Package_QFP:LQFP-48_7x7mm,1,,STM32F103C8T6,https://...
JLCPCB CSV format
JLCPCB requires specific column names for their SMT assembly service:
Comment,Designator,Footprint,LCSC Part #
10k,"R1, R3, R7",Resistor_SMD:R_0402,C25804
100nF,"C1, C2",Capacitor_SMD:C_0402,C307331
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.
- 1mo ago First seen · 99 lines · 10 tokens per session scan A 51e8ff6c4a2c
bom is a command published in the GitHub repository captainluzik/oh-my-embedded (31 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 907 once invoked, about $0.0000 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 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.
iot
Pick an IoT protocol from power, range, data rate, and reliability constraints, then design its topics, security, and power budget.
bare-metal
Scaffold a bare-metal project, shrink code size, decode a linker map file, or generate flash commands.
embedded-test
Generate Unity tests, CMock mocks, a hardware-in-the-loop scaffold, or a coverage report.
fpga
Generate a Verilog module, a Vivado or Quartus synthesis script, programming commands, or the MCU-side interface driver.