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.
npx skills add Leonezz/openbaud --skill scaffoldgit clone --depth 1 https://github.com/Leonezz/openbaudWrote 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/skills/leonezz/openbaud/scaffold)<a href="https://agentmods.dev/skills/leonezz/openbaud/scaffold"><img src="https://agentmods.dev/badge/skills/leonezz/openbaud/scaffold/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/skills/leonezz/openbaud/scaffold"><img src="https://agentmods.dev/badge/skills/leonezz/openbaud/scaffold.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 | $0.00049 | $0.04214 |
| Opus 5.5 | $0.00020 | $0.01686 |
| Sonnet 5.5 | $0.00010 | $0.00843 |
| Haiku 4.5 | $0.00005 | $0.00421 |
Grade A, and why
openbaud 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 11d 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.
This is a copy
100% identical to openbaud — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with serial devices through openbaud
openbaud gives you audited serial-port access (MCP tools) plus a knowledge format in this workspace. Your goal when touching a device is never just to make one interaction work — it is to sediment verified knowledge so the next session (or the next person) starts where you finished.
Workspace layout
devices/<name>/profile.yaml— transport parameters + default framing + optional selectordevices/<name>/commands/*.yaml— named, typed, executable commandsdevices/<name>/workflows/*.yaml— fixed command sequences with afinallyblockdevices/<name>/notes.md— quirks, datasheet errata, open questionscaptures/*.obcap— lossless wire captures (JSONL: ts_ms, dir, hex).openbaud/audit.jsonl— every write you performed, append-only.openbaud/out/— full copies of oversized tool results (seefull_resultbelow)reports/— derived analysis you write for people (charts, summaries); cite the capture each one came from so it stays auditablescripts/— one-off analysis helpers that are not device knowledge (device behavior belongs in commands, never in a script)
Exploration workflow
- Identify:
list_ports— USB VID/PID and product strings often identify the adapter or device. Checkdevices/first: knowledge may already exist. - Read the datasheet before sending anything. Extract candidate commands, frame structure, checksum algorithm, baud rate. Record page references.
- Hypothesize → verify in small steps:
openthe port, userequestwith an explicitmatchrule. Start a capture (capture_start) before longer experiments so evidence is preserved.capture_start/capture_stopreturn the capture's workspace-relativepath(captures/<file>) — pass it verbatim tocapture_frames,session_timeline, orreplay:<path>. - Record as you go in
devices/<name>/notes.md: what you sent, what came back, what it means, what surprised you. - Sediment: once a behavior is confirmed, write it as a command YAML (see
below). Then re-verify through
run_command— the declarative spec must reproduce the hand-built result. - Mark provenance: add
provenance.datasheet(page reference) and, after verifying against the live device,provenance.verifiedwith the capture path and what you observed. Never markverifiedwithout a real device interaction backing it.
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.
- 11d ago Changed · +55 lines 995d84de4c15
- 1mo ago Changed · +10 lines 2cf1d8d6247d
- 1mo ago First seen · 245 lines · 49 tokens per session scan A dd6bcf0c45e3
openbaud is a skill published in the GitHub repository Leonezz/openbaud (7 stars, last pushed 12d ago), licensed MIT. It adds 49 tokens to every session and 4,214 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to openbaud, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
hardware-iot-bus
Low-level I2C and SPI bus peripheral control for embedded Linux boards (Orange Pi, Raspberry Pi, RISC-V).
ek-omniprobe-ai
A local bridge for reading serial-port text and standard samples, then analysing logs and signal waveforms and adjusting device settings safely. Serial ports are connections commonly used to communicate with embedded devices.
boardrepo
Read and review real PCB projects on BoardRepo. Search published hardware designs, open a board's schematic connectivity, bill of materials and files, run KiCad's DRC and ERC, and check a design against a fabrication house's limits. Use whenever the user names a BoardRepo board or URL, asks to find a published board…
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
hardware-health-check
Out-of-band hardware health via Redfish BMC (read-only) — power state, component health, thermal and power readings, firmware inventory, SEL log triage. Use when determining whether a host is powered off versus unreachable, checking hardware faults, reviewing thermal or PSU state, or triaging BMC event logs.
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.