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/nominal-io/instro/validate-driver-hardwarenpx skills add nominal-io/instro --skill validate-driver-hardwaregit clone --depth 1 https://github.com/nominal-io/instroWrote 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/nominal-io/instro/validate-driver-hardware)<a href="https://agentmods.dev/skills/nominal-io/instro/validate-driver-hardware"><img src="https://agentmods.dev/badge/skills/nominal-io/instro/validate-driver-hardware.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 | $0.00113 | $0.02964 |
| Opus 5 | $0.00056 | $0.01482 |
| Sonnet 5 | $0.00023 | $0.00593 |
| Haiku 4.5 | $0.00011 | $0.00296 |
Grade A, and why
validate-driver-hardware 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate a driver against real hardware
This skill takes an already-authored driver and proves it works against the
physical instrument. It writes a standalone, runnable validation script that
exercises every method the driver implements, runs it against the connected
device, triages the results, and iterates on the driver to fix real bugs the
hardware surfaces. It is the hardware counterpart to add-instrument-driver's
mocked unit tests.
Borrow the style of the runnable example scripts in examples/ — especially
examples/modbus/labjack_t4_loopback_test.py (per-check OK/FAIL,
accumulated failures, final summary, try/finally close).
Step 1 — Confirm hardware availability and gather connection details
This skill is only useful with the physical device attached. Ask the user first, and do not write or run anything until you have:
- Do you have the instrument connected right now? If no, stop — offer to write the script anyway (with placeholder config) so they can run it later, but make clear nothing will be validated until hardware is present.
- Device identifier / connection string. The exact value the transport
needs: a VISA resource (
USB0::0x...::INSTR,TCPIP0::192.168.1.5::INSTR,ASRL3::INSTR), ahost:portfor Modbus/TCP, a serial port, etc. Match the transport the driver actually uses. - Vendor, model, and exact unit (e.g. "Siglent SDS1104X-E"). Confirm it is in the family the driver targets.
- Channel count / channel map. How many channels, and what is physically wired to each one.
- Stimulus and wiring. What signal/load/DUT is present, on which channel, and its known properties (e.g. "LabJack T4 DAC0 → CH1, 100 Hz sine, ~0–2.5 V unipolar"). This is what makes value checks meaningful — capture it precisely, including limitations (e.g. a unipolar source never crosses 0 V, so a 0 V trigger won't fire). Ask for loopback wiring where the category needs it (DAQ analog/digital loopback, I2C target address, etc.).
- Safety constraints. For sourcing instruments (PSU, eload, DAQ AO, relays), confirm safe limits before any output is enabled and what state to leave the device in.
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.
- 4d ago First seen · 246 lines · 113 tokens per session scan A 59c945870964
validate-driver-hardware is a skill published in the GitHub repository nominal-io/instro (665 stars, last pushed today), licensed Apache-2.0. It adds 113 tokens to every session and 2,964 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
mcp-sigrok
Skill "mcp-sigrok" from daedalus/mcp-sigrok, covering mcp-sigrok skill, usage, examples, list available drivers and scan for devices.
instrument-tektronix-scope
Standard protocol for Tektronix Mixed Domain (MDO) and Mixed Signal (MSO) oscilloscopes.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.