Borrowing it
Nothing to install: this file belongs to nominal-io/instro. 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/nominal-io/instro/main/.agents/skills/add-instrument-driver/SKILL.mdgit 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/add-instrument-driver)<a href="https://agentmods.dev/skills/nominal-io/instro/add-instrument-driver"><img src="https://agentmods.dev/badge/skills/nominal-io/instro/add-instrument-driver.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 | $0.00102 | $0.03223 |
| Opus 5 | $0.00051 | $0.01612 |
| Sonnet 5 | $0.00020 | $0.00645 |
| Haiku 4.5 | $0.00010 | $0.00322 |
Grade A, and why
add-instrument-driver 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 2d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add an instrument driver from a manual/API
This skill turns a vendor programming reference into a correct, tested,
registered driver PR. It follows the repo's existing conventions exactly — read
AGENTS.md ("How to add a vendor driver", "Patterns and constraints",
"DAQ driver state tracking") before deviating. When in doubt, duplicate
explicit code rather than abstract. This repo deliberately prefers duplication
over shared mixins/factories.
Prerequisites — gather before writing code
- The programming reference. A path to a PDF/doc/HTML file, or a URL. If the user hasn't provided one, ask for it — do not guess SCPI commands or API code from model knowledge.
- Vendor and model (e.g. "Siglent SPD3303"). Confirm the exact model family the driver should cover; SCPI surfaces and APIs are often shared across a series.
- Category. One of
psu,dmm,eload,daq,i2c,modbus,scope,awg,ethernetip. Infer from the instrument type; confirm with the user if ambiguous. - Tracking issue + branch. Per
AGENTS.md, no untracked work. Confirm an issue exists (or create one) and branch offmainnamed after it (e.g.issue-142-siglent-spd-driver). - Core vs. contrib. Default to core (
instro/<category>/drivers/) if the user is a maintainer, otherwise use contrib (packages/instro-contrib/instro/contrib/<category>/drivers/). Some instruments only exist in unstable (packages/instro-unstable/). SeeCONTRIBUTING.mdfor the bar. Ask if unclear.
Step 1 — Extract a structured command spec from the manual
Manuals are large and noisy. Delegate parsing to the manual-spec-extractor
subagent (.claude/agents/manual-spec-extractor.md) so the heavy document
tokens stay out of this conversation. Give it:
- the manual location (path or URL),
- the target category and its required methods (read them from the category base class — see Step 3),
- the vendor/model.
It returns a structured spec: per-method SCPI command(s), the error-query form and OK-prefix, the channel model, value formatting (decimal places, units), and which optional category methods the instrument supports. Review the spec against the manual yourself for anything safety- or wire-critical before coding.
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.
- 2d ago Changed 35efb0f9eeb6
- 7d ago First seen · 237 lines · 102 tokens per session scan A 360fee8cec61
add-instrument-driver is a skill published in the GitHub repository nominal-io/instro (669 stars, last pushed yesterday), licensed Apache-2.0. It adds 102 tokens to every session and 3,223 once invoked, about $0.0005 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.
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.