Embedded-AI-Harness: Skill for Claude Code

.claude/skills/testbench-logging/SKILL.md

testbench-logging is a skill for Claude Code from SensorsIot/Embedded-AI-Harness. It costs 122 tokens per session (2,746 once invoked), scanned B, original, MIT.

A logging procedure for reading output and crash information from ESP32 devices on a test bench. It supports serial monitoring and network-based UDP logs.

In plain words
What is it for?
Use it to capture boot messages, wait for matching log patterns, retrieve continuous UDP logs, and investigate crash output from ESP32 hardware.
Why use it?
It helps diagnose device startup, connection, and crash problems when logs may come from different devices or when the USB serial port is occupied.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is SensorsIot/Embedded-AI-Harness's own configuration. It tells Claude Code how to work on Embedded-AI-Harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Embedded-AI-Harness configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is export TESTBENCH_URL=$(sudo python3 .claude/skills/esp-idf-handling/discover-testbench.py \.

Reuse

Borrowing it

Nothing to install: this file belongs to SensorsIot/Embedded-AI-Harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SensorsIot/Embedded-AI-Harness/main/.claude/skills/testbench-logging/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SensorsIot/Embedded-AI-Harness

Made for: Claude Code.

Wrote 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.

agentmods badge for testbench-logging

README.md
[![agentmods](https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/testbench-logging/github.svg)](https://agentmods.dev/skills/sensorsiot/embedded-ai-harness/testbench-logging)
Your own site
<a href="https://agentmods.dev/skills/sensorsiot/embedded-ai-harness/testbench-logging"><img src="https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/testbench-logging/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.

agentmods 80×15 button for testbench-logging

Your own site · 80×15
<a href="https://agentmods.dev/skills/sensorsiot/embedded-ai-harness/testbench-logging"><img src="https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/testbench-logging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,746 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 216
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 231
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Privilege Escalation · line 17
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Data Exfiltration · line 53
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 5.1 $0.00122 $0.02746
Opus 5 $0.00061 $0.01373
Sonnet 5 $0.00024 $0.00549
Haiku 4.5 $0.00012 $0.00275

Measured 10d ago against content hash 1664b671a22a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

testbench-logging scanned grade B with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

export TESTBENCH_URL=$(sudo python3 .claude/skills/esp-idf-handling/discover-testbench.py \

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "$TESTBENCH_URL/api/info" # confirm before anything else
.claude/skills/testbench-logging/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ESP32 Debug Logging

Base URL: $TESTBENCH_URL — see Step 0

Step 0: Point at a bench

There are several benches and their addresses move, so nothing here writes one down. $BENCH is not usable either — a container cannot resolve mDNS. Discover the bench and export its URL:

export TESTBENCH_URL=$(sudo python3 .claude/skills/esp-idf-handling/discover-testbench.py \
                         --url --name <bench-hostname>)
curl -s "$TESTBENCH_URL/api/info"        # confirm before anything else

--url refuses to guess when more than one bench answers, so --name is required whenever a second bench is powered on. TESTBENCH_URL is the same variable pytest --wt-url falls back to.

Two logging methods are available. Choose based on your situation:

Serial Monitor UDP Logs
Works without WiFi Yes No
Boot/crash output Yes No
Pattern matching Built-in (regex + timeout) Manual (poll + grep)
Blocks serial port Yes (one session per slot) No
Multiple devices One slot at a time All devices simultaneously
Long-running Limited by timeout Continuous (buffer persists)

Endpoints

Request and response shapes: serial in FSD Appendix D.2, UDP log in D.7, the portal's own activity log in D.14.

Three different logs, and picking the wrong one wastes a test run: /api/serial/* is what the device printed over USB, /api/udplog is what it sent over the network, and /api/log is what the portal did — never device output.

Serial Monitor

Reads serial output via RFC2217 proxy. Optionally waits for a regex pattern.

# Wait up to 10s for a pattern match
curl -X POST $TESTBENCH_URL/api/serial/monitor \
  -H 'Content-Type: application/json' \
  -d '{"slot": "SLOT1", "pattern": "WiFi connected", "timeout": 10}'

# Just capture output for 5s (no pattern)
curl -X POST $TESTBENCH_URL/api/serial/monitor \
  -H 'Content-Type: application/json' \
  -d '{"slot": "SLOT1", "timeout": 5}'

Read the full file on GitHub · 234 lines

Files

What ships with it

1 file 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. 10d ago First seen · 234 lines · 122 tokens per session scan B 1664b671a22a

Subscribe to this mod's changes

testbench-logging is a skill published in the GitHub repository SensorsIot/Embedded-AI-Harness (173 stars, last pushed 29d ago), licensed MIT. It adds 122 tokens to every session and 2,746 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

firmware-debugger

(oh-my-embedded) Firmware debugging via GDB and serial monitor. Breakpoints, memory inspection, stack traces, JTAG/SWD. Requires debug probe.

captainluzik/oh-my-embedded · 38 tokens

hardware-logging

Debug firmware on a real board using hwlog structured serial logs. Use whenever working with ESP32/embedded firmware — flashing, testing on hardware, reading device output, or diagnosing crashes, reboots, or silent boards.

gurul/hardware-logging · 48 tokens

embedded-debugging

Debug embedded firmware on real hardware through the jlink-mcp server — crashes, hangs, peripheral misconfiguration, silent devices. Covers loading ELF symbols for source-level backtraces, supplying an SVD for named peripheral fields, and the halt/read/resume discipline. Use whenever debugging a microcontroller over a…

Klievan/jlink-mcp · 77 tokens

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

embedded-debugging

Senior embedded debugging expert. Defaults to Classic AUTOSAR on ARM Cortex-M/R targets and operates in two modes: (1) Problem-report triage — take a field PR / bug ticket and produce symptom classification, affected-element mapping, ranked hypotheses, data-collection plan, and step-by-step investigation; (2) Targeted…

ptsilivis/autonomousguy · 208 tokens

debug-gdb-openocd

An OpenOCD and GDB debugging tool for embedded firmware. OpenOCD connects a computer to many microcontroller debug probes, and GDB is used to inspect and control the program.

LeoKemp223/embed-ai-tool · 47 tokens