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.
curl -O https://raw.githubusercontent.com/SensorsIot/Embedded-AI-Harness/main/.claude/skills/testbench-test-handling/SKILL.mdgit 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-test-handling)<a href="https://agentmods.dev/skills/sensorsiot/embedded-ai-harness/testbench-test-handling"><img src="https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/testbench-test-handling/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/sensorsiot/embedded-ai-harness/testbench-test-handling"><img src="https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/testbench-test-handling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Privilege Escalation · line 49 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 165 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.
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 | $0.00149 | $0.03626 |
| Opus 5 | $0.00075 | $0.01813 |
| Sonnet 5 | $0.00030 | $0.00725 |
| Haiku 4.5 | $0.00015 | $0.00363 |
Grade B, and why
testbench-test-handling scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
export TESTBENCH_URL=$(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 How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESP32 Test Automation
Base URL: $TESTBENCH_URL — see Step 0
The portal and the MQTT broker are always-on infrastructure. A test never starts, stops or restarts them — doing so breaks whatever else is using the bench, and a test that needs a restart to pass is testing the restart.
The execution protocol
Every test case runs in three phases, and the panel shows which one is current so the operator can follow along without a terminal.
| Phase | Panel shows | What happens |
|---|---|---|
| Preconditions | [TC-100] Preconditions: checking DUT reachable... |
Verify and establish each precondition from the spec. If the AP is not running, start it. Fail only when a precondition is genuinely unrecoverable. |
| Execute | [TC-100] Step 2: <the step from the spec> |
Run the spec's steps one at a time, checking the expected result after each. |
| Result | TC-100: PASS / TC-100: FAIL — <what was seen> |
Record PASS/FAIL/SKIP with the observed value, not just the verdict. |
Rules that decide whether a run is worth anything:
- The spec is the script. Execute its preconditions, steps and pass criteria as written — not an improved version of them.
- Update the panel before each action, never after. The panel is how the operator knows what the bench is doing to the hardware right now.
- Record baselines. Where the spec says "record X as
X_before", capture it and compare in the result phase. - Generate test credentials per run. A random SSID and password for the test AP proves the DUT used what it was provisioned with, rather than a network it had already cached.
- Write the results out. A markdown file with test ID, name, result, details and timestamps — the panel is live state, not a record.
Workflows that span several instruments — provision, reboot, re-provision, soak —
are in references/common-workflows.md.
Step 0: Point at a bench
What ships with it
2 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.
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 First seen · 320 lines · 149 tokens per session scan B c495ba84aa98
testbench-test-handling is a skill published in the GitHub repository SensorsIot/Embedded-AI-Harness (173 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 3,626 once invoked, about $0.0007 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.
Other skills, from other repositories
ea-skill
An AI-assisted workflow for developing and testing embedded-device software. Embedded software runs on hardware such as microcontrollers, and the workflow covers project setup, feature work, tests, device programming, debugging, verification, and records.
m5stack-cap-lora-1262
Hardware reference and firmware helper for the M5Stack Cap LoRa-1262 (SKU U214) — a snap-on cap for the Cardputer Adv (K132-Adv) and CardputerZero that carries a Semtech SX1262 sub-GHz LoRa radio (868–923 MHz, +22 dBm TX, external RP-SMA antenna) and an ATGM336H-6N GNSS receiver (GPS/QZSS/BeiDou/Galileo/GLONASS, UART…
new-device-skill
Build or update an M5Stack hardware skill in this marketplace — a Controller (a board that runs firmware, like Core2 or AtomS3), a Unit (a peripheral you drive from a Controller, like a ToF sensor or a relay), or a Chip (an Espressif SoC capability layer, like esp32-c6). Use whenever adding a new board/unit/chip to…
m5stack-tab5
Hardware reference and development helper for the M5Stack Tab5 (product code C145) — an ESP32-P4-based 5" touchscreen IoT/industrial terminal with an ESP32-C6 wireless co-processor, MIPI-DSI display, MIPI-CSI camera, ES8388 audio codec, BMI270 IMU, RX8130CE RTC, RS485, and a removable NP-F550 battery. Use this skill…
embedded-verification
Use after implementation complete - runs build-flash-monitor loop, verifies runtime behavior, no completion claims without fresh evidence.
embedded-testing-patterns
Embedded C test patterns using Unity, CMock, Ceedling, and QEMU.