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 agentmods add skills/sensorsiot/embedded-ai-harness/testbench-debugnpx skills add SensorsIot/Embedded-AI-Harness --skill testbench-debuggit clone --depth 1 https://github.com/SensorsIot/Embedded-AI-HarnessWrote 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/sensorsiot/embedded-ai-harness/testbench-debug)<a href="https://agentmods.dev/skills/sensorsiot/embedded-ai-harness/testbench-debug"><img src="https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/testbench-debug.svg" alt="Measured on agentmods" 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 | $0.00106 | $0.05424 |
| Opus 5 | $0.00053 | $0.02712 |
| Sonnet 5 | $0.00021 | $0.01085 |
| Haiku 4.5 | $0.00011 | $0.00542 |
Grade C, and why
testbench-debug scanned grade C with 3 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 6d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST $TESTBENCH_URL/api/debug/stop -d '{}' Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo cp openocd-esp32/bin/openocd /usr/local/bin/openocd-esp32 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl $TESTBENCH_URL/api/devices How it starts
The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testbench GDB Debugging
Remote GDB debugging of ESP32 devices through the testbench Pi. OpenOCD runs on the Pi, GDB connects from the container over TCP.
Architecture:
[Container] [Pi (testbench)] [ESP32]
GDB ──── TCP :3333 ────── OpenOCD ──── USB JTAG ──────── CPU
(or)
OpenOCD ──── ESP-Prog ── JTAG pins
Three Approaches
| Approach | Chips | Extra Hardware | Serial During Debug |
|---|---|---|---|
| USB JTAG (FR-024) | C3, S3 (native USB only) | None | Yes |
| Dual-USB (FR-025) | S3 (two USB connectors) | None | Yes + app USB |
| ESP-Prog (FR-026) | All ESP32 variants | ESP-Prog (~$15) + cable | Yes |
Auto-Debug (Zero Config)
OpenOCD starts automatically when a device is plugged in or at boot. No API call needed.
How it works:
- Device hotplugged → serial proxy starts → auto-detect tries OpenOCD configs
- Chip identified via JTAG TAP ID → OpenOCD starts on the assigned GDB port
- If USB JTAG fails (e.g. classic ESP32), falls back to ESP-Prog probe if available
- GDB port reported in
/api/devicesresponse
Check debug status:
curl $TESTBENCH_URL/api/devices
# Look for: "debugging": true, "debug_chip": "esp32s3", "debug_gdb_port": 3335
Manual override (optional -- only needed to force-stop or force-start):
# Force stop (won't auto-restart until next hotplug)
curl -X POST $TESTBENCH_URL/api/debug/stop -d '{}'
# Force start with specific chip
curl -X POST $TESTBENCH_URL/api/debug/start \
-d '{"chip": "esp32c3"}'
JTAG Reset (Preferred When Available)
When a debug session is active, the testbench automatically uses JTAG reset instead of DTR/RTS serial reset. This is transparent — the same /api/serial/reset API is used.
Why JTAG reset is better:
- No USB re-enumeration (device node stays stable)
- No flapping risk
- No 2-second boot delay
- Works even when serial port is unresponsive
- Can halt the CPU to stop boot loops
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.
- 6d ago First seen · 528 lines · 106 tokens per session scan C 1b912f2f5cbf
testbench-debug is a skill published in the GitHub repository SensorsIot/Embedded-AI-Harness (172 stars, last pushed 25d ago), licensed MIT. It adds 106 tokens to every session and 5,424 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 3 findings (sends data to an external url, 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.
Other skills, from other repositories
esp32-log-triage
Parse and classify ESP32 serial log output to identify FastLED-related errors, RMT/I2S/SPI driver faults, timing violations, RTOS issues, and crash signatures. Use when debugging unexpected device behavior, boot failures, or LED output problems on ESP32.
embedded-debug
Firmware crash analysis, stack trace decoder, and register dump interpreter for ESP32/ARM/AVR platforms. Use when debugging device crashes, panics, guru meditation errors, hard faults, or analyzing core dumps.
memory-audit
Audit embedded code for stack overflow risks, heap fragmentation, static allocation patterns, and memory leaks. Use when investigating OOM crashes, optimizing memory usage, or reviewing memory-critical code on constrained devices.
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.
nucleo-anima-debug
Debug and develop NucleoOS firmware/ANIMA logic on the PC without flashing — the host harness compiles the real C and runs it locally. Use when working on ANIMA (the offline NL assistant), retrieval cascade, NLU, knowledge graph, or any firmware logic, and when deciding how to verify a change. Lists the gate suites to…
firmware-debugger
(oh-my-embedded) Firmware debugging via GDB and serial monitor. Breakpoints, memory inspection, stack traces, JTAG/SWD. Requires debug probe.