baud

A command-line tool for working with serial connections such as UART, COM ports, USB-to-TTL adapters, and firmware consoles. It can inspect ports, capture device output, send commands, and run guarded hardware tests.

In plain words
What is it for?
Use it to find connected serial ports, record boot logs, test safe device queries, send firmware-console commands, and interpret JSON, JSONL, and log output.
Why use it?
It helps diagnose devices when the connection is silent, works in only one direction, or uses an uncertain port. It also keeps command output and device evidence available for review.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nitmi/baud-cli/baud
Any agent
npx skills add Nitmi/baud-cli --skill baud
Clone the repo
git clone --depth 1 https://github.com/Nitmi/baud-cli

Made for: Claude Code, Codex.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,026 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00082 $0.01026
Opus 5 $0.00041 $0.00513
Sonnet 5 $0.00016 $0.00205
Haiku 4.5 $0.00008 $0.00103

Measured yesterday against content hash dab6a7b478ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

baud 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 yesterday.

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.

skills/baud/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Baud

Use baud as the serial execution layer. Preserve evidence, minimize transmission, and gate physical actions behind verified device state.

Prepare

  1. Run baud --version before opening a port.
  2. If the command is unavailable, report the missing prerequisite. When installation is authorized, use uv tool install baud-cli; use uv run --directory <baud-cli-repo> baud only when the source checkout is known. Do not silently replace it with an ad hoc pyserial script.
  3. Read applicable AGENTS.md, firmware documentation, and existing serial workflows to learn the baud rate, line ending, safe query commands, reset behavior, and physical risks.
  4. Resolve the port from evidence. Do not assume a previous COM or tty name still identifies the same adapter.

Choose The Least Invasive Command

Follow this escalation order:

  1. Run baud list --json to enumerate ports and USB metadata.
  2. Run baud monitor --port <port> --duration <seconds> --json to observe boot output without transmitting.
  3. Run baud probe --port <port> --commands <safe queries> --endings crlf lf --json only after confirming the probe commands are harmless for the device.
  4. Run baud send for one bounded query with explicit expectations.
  5. Run baud run <workflow.yaml> --json for multi-step configuration, observation, or hardware action.

Use --json for a bounded command whose final result drives the next decision. Use --jsonl when event ordering or streamed evidence matters. Keep automatic log artifacts enabled for real hardware work.

Apply Safety Gates

  • Start with read-only observation and status queries.
  • Treat DTR and RTS as physical control signals that may reset or reconfigure a device. Keep both false unless device documentation requires otherwise.
  • Confirm both communication directions before sending a state-changing command. A boot banner proves only device-to-host traffic.
  • Read configuration back from the device; do not treat ACK, echoed input, or a successful write as proof that hardware accepted the state.
  • Mark motion, heating, injection, erase, flash-save, power switching, and similar actions as dangerous: true in workflows. Require successful earlier verification steps with requires.
  • Begin physical testing with one cycle, the lowest safe setpoint, unloaded mechanics, or another documented low-risk condition.
  • Stop on a busy, disappearing, or unidentified port. Do not kill an unknown process or continue on a different port without evidence.

Read the full file on GitHub · 71 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday First seen · 71 lines · 82 tokens per session scan A dab6a7b478ea

Subscribe to this mod's changes

baud is a skill published in the GitHub repository Nitmi/baud-cli (5 stars, last pushed 22d ago), licensed MIT. It adds 82 tokens to every session and 1,026 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

serial-debug

CLI-first serial port debugging and macro automation with serial-mcp-server for Codex and Claude Code. Use when working with UART or USB-serial devices, listing serial ports, probing STM32/Arduino/ESP32 boards, writing or reading serial data, running JSON serial macros, controlling RTS/DTR, or using serial-mcp-server…

Adancurusul/serial-mcp-server · 74 tokens

tdd

Guide Test-Driven Development workflow for FastLED. Use when implementing new features or fixing bugs with a test-first approach. Enforces Red-Green-Refactor discipline with FastLED test conventions.

FastLED/FastLED · 42 tokens

timing-analysis

Analyze real-time constraints, ISR latency, DMA transfer times, and LED protocol timing for embedded systems. Use when debugging timing-sensitive code, optimizing frame rates, or verifying protocol compliance.

FastLED/FastLED · 40 tokens

gpt-image

Use this skill whenever a user asks to generate, create, draw, render, or edit images with GPT Image 2 / gpt-image-2, text-to-image, reference-image editing, inpainting, posters, typography, Chinese text, UI mockups, diagrams, or gallery prompts. Analyze the user's prompt, search the bundled Reference Gallery/craft…

wuyoscar/GPT-Image2-Skill · 120 tokens

esp32-test-plan

Generate a structured multi-layer test plan for FastLED changes targeting ESP32. Covers host unit tests, WASM compile checks, platform compile checks, and hardware validation. Use after defining an implementation contract, before writing any code.

FastLED/FastLED · 50 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens