add-lab-equipment-device

add-lab-equipment-device is a skill for Codex from 1622352030/lab-equipment-mcp. It costs 108 tokens per session (1,707 once invoked), scanned A, original, MIT.

A workflow for adding support for laboratory instruments to the lab-equipment-mcp repository. It covers devices such as oscilloscopes, power supplies, multimeters, signal generators, and electronic loads.

In plain words
What is it for?
Use it when onboarding a new instrument, adding a connection method, or extending an existing device driver using its manuals and physical interface details.
Why use it?
It reduces the risk of adding device support without confirming the instrument’s connection, command protocol, data formats, safety limits, and acceptance checks.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it when onboarding a new instrument, adding a connection method, or extending an existing device driver using its manuals and physical interface details.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/1622352030/lab-equipment-mcp/add-lab-equipment-device
Install

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.

Any agent
npx skills add 1622352030/lab-equipment-mcp --skill add-lab-equipment-device
Clone the repo
git clone --depth 1 https://github.com/1622352030/lab-equipment-mcp

Made for: Codex.

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 add-lab-equipment-device

README.md
[![agentmods](https://agentmods.dev/badge/skills/1622352030/lab-equipment-mcp/add-lab-equipment-device/github.svg)](https://agentmods.dev/skills/1622352030/lab-equipment-mcp/add-lab-equipment-device)
Your own site
<a href="https://agentmods.dev/skills/1622352030/lab-equipment-mcp/add-lab-equipment-device"><img src="https://agentmods.dev/badge/skills/1622352030/lab-equipment-mcp/add-lab-equipment-device/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 add-lab-equipment-device

Your own site · 80×15
<a href="https://agentmods.dev/skills/1622352030/lab-equipment-mcp/add-lab-equipment-device"><img src="https://agentmods.dev/badge/skills/1622352030/lab-equipment-mcp/add-lab-equipment-device.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00108 $0.01707
Opus 5 $0.00054 $0.00853
Sonnet 5 $0.00022 $0.00341
Haiku 4.5 $0.00011 $0.00171

Measured 11d ago against content hash 653ed518d094, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

add-lab-equipment-device 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 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.

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.

skills/add-lab-equipment-device/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Lab Equipment Device

Add equipment support only after proving the physical interface, host environment, command protocol, and acceptance path. Preserve existing devices and keep model-specific behavior isolated. For recurring failure patterns from the AFG-2125 implementation, read lessons-learned.md before coding.

Workflow

  1. Inspect the repository, README.md, src/lab_equipment_mcp/core/, existing device drivers, tests, and the device documentation tree. Check the current branch and worktree before edits.
  2. Obtain the user manual and programmer/programming manual. Ask the user to download protected or vendor-gated manuals. Read the relevant files completely enough to establish interfaces, remote commands, identity response, termination rules, data formats, and safety restrictions. For PDFs, inspect the rendered command-tree and waveform figures as well as extracted text; record exact page numbers and distinguish optional bracket notation from literal command characters.
  3. Confirm with the user which physical interface is connected now. Do not infer USBTMC from a USB connector alone; distinguish USB host/device, USBTMC, virtual COM, RS-232, LAN VXI-11, LAN raw socket, HiSLIP, GPIB, and vendor-specific transports.
  4. Record every interface the model supports, even when only one is available for testing. Read interfaces.md and implement a DeviceProfile with one InterfaceSpec per supported path.
  5. Diagnose the computer environment before coding. Check device enumeration, VISA resources, serial ports, IP reachability, drivers, runtimes, Python packages, and exclusive-session conflicts. Install safe command-line dependencies when authorized. If installation requires a vendor download, license acceptance, administrator UI, reboot, or manual hardware action, give the user the official download link and exact steps, then wait for confirmation.
  6. Establish a read-only connection and identity query before changing instrument settings. Prefer *IDN?; use the manual's documented equivalent when SCPI is unsupported. Capture the firmware revision and preserve it in the device guide because command behavior can be firmware-specific.
  7. Prepare Git contribution work before edits. Read contribution-workflow.md. Fork the upstream repository for external contributors, clone the fork, add upstream, update the default branch, and create a dedicated feature branch. Repository owners may branch directly but must not develop on main.
  8. Implement shared transport behavior in core/ only when multiple devices can reuse it. Put vendor/model identity, commands, ranges, response parsing, and quirks under devices/<vendor>/<model>.py or a model package.
  9. Prefix MCP tool names with the model or family. Mark read-only and state-changing tools with MCP annotations. Block reset, calibration, firmware, file deletion, output-enable, and other risky operations by default unless the project explicitly defines a guarded workflow. For every state-changing command, verify the requested value by read-back when the instrument supports it; otherwise return an explicit unverified/firmware-quirk result rather than claiming success.
  10. Cover every command applicable to the target model that is documented in the programmer's manual. Each command must have either a dedicated typed MCP tool or a model-prefixed complete SCPI command/query entry point. Do not omit documented command groups merely because they were not part of the initial hardware test; mark them as implemented-but-untested and preserve manual-defined option/module conditions.
  11. Add the device guide under docs/<vendor>/<MODEL>.md. Document manuals used, supported interfaces, tested interfaces, cable/pin requirements, driver links with verification dates, installation, example prompts, and troubleshooting.
  12. Complete every applicable gate in acceptance.md. Do not claim an interface is tested when it was only implemented or simulated. For waveform sources, prefer a physical receiver MCP (oscilloscope, counter, load, or analyzer) for closed-loop acceptance; if no usable receiver MCP is available, ask the user to observe the panel/connected instrument and record the observation as user-observed, not agent-measured. SCPI read-back alone remains lower-confidence. Restore the original safe state in a finally path.
  13. Commit focused changes. Push to the contributor's fork or, when authorized, push the branch to the owner's repository and open/prepare a pull request. Report untested interfaces and residual risks explicitly.

Read the full file on GitHub · 112 lines

Files

What ships with it

5 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.

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. 11d ago First seen · 112 lines · 108 tokens per session scan A 653ed518d094

Subscribe to this mod's changes

add-lab-equipment-device is a skill published in the GitHub repository 1622352030/lab-equipment-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,707 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 2026-08-31.

Related

Other skills, from other repositories

neuroskill-bci

Use live BCI cognitive and mood state from NeuroSkill.

NousResearch/hermes-agent · 18 tokens

ruview-advanced-sensing

Advanced RuView capabilities — RuvSense multistatic sensing (attention-weighted fusion, geometric diversity, persistent field model), cross-viewpoint fusion across multiple nodes, RF tomography (ISTA L1 solver, voxel grids), longitudinal biomechanics drift, pre-movement intention signals, adversarial signal detection…

ruvnet/RuView · 84 tokens

ruview-applications

Run RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-keypoint pose estimation (WiFlow), sleep monitoring & apnea screening, environment mapping, Mass Casualty Assessment (MAT), and the 3D point-cloud fusion demo. Use when someone wants to actually do something…

ruvnet/RuView · 79 tokens

lab-hardware-cad

Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…

K-Dense-AI/scientific-agent-skills · 106 tokens

opentrons-integration

Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow…

K-Dense-AI/scientific-agent-skills · 79 tokens

pylabrobot

Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.

K-Dense-AI/scientific-agent-skills · 49 tokens