PhysKit

Plugin for agentic research in experimental physics

PhysKit is a free, open-source plugin for Claude Code and Codex for collaborative agentic research: skills, prompts, templates, and code that give an AI agent the habits of a careful experimentalist and build those habits into the tools it works with, not just its instructions.

Get started Case studies Preprint (arXiv) GitHub

Pre-release: the skills and doctrine still change between versions. Use the latest release.

01Why we built PhysKit

Agentic research is increasingly common in experimental physics. Verifying it is the hard part.

  • Increasingly common, few guidelines The use of AI in physics research is increasingly common, yet few guidelines exist for its effective use.
  • Verification is generally the limiting step In all six of our case studies, careful verification of the agent's results by researchers was essential, and generally replaced technical implementation as the limiting step.
  • It takes intensive interaction The campaigns often required a researcher to redirect them or try again.

In experimental physics, models are approximations and data carry noise, systematic effects and apparatus details the agent cannot see, so a result is only as good as the checks behind it. More in the preprint.

Without PhysKit

With PhysKit

In the preprintSix case studies from our quantum-sensing work →

02How it works

A tool for collaborative agentic research in experimental physics, designed to reduce the probability of errors and the burden of verification.

Standardized documentation

Each run is archived with its exact code, configuration and data, and every number is labeled by where it came from.

Easier human verification

Every result is labeled with how it was checked, up to an independent verifier at the level you set; reports map each claim to its evidence.

Closed-loop iteration

The agent proposes, runs, evaluates, verifies and records, toward a goal and a frozen metric you set. You can add ideas at any time.

Two ways to use it

A general science toolkit

Skills for framing problems, verifying results, designing and validating simulations, dimensional analysis, deriving theory, debugging, and honest reporting. They work in any session; the agent picks the matching skill.

Closed-loop research campaigns

Scaffold and run a closed research loop — propose, implement, run, evaluate, verify, record, repeat — with a frozen honesty and verification core the loop cannot change, and health checks you can run while it works. How a campaign works ↓

A closed-loop campaign

Closed-loop research campaign. 1 Setup: interview user, define goals and constraints, set metric, run baseline experiment. 2 Loop: propose, implement, run, evaluate, verify, record, with optional user input between cycles. The loop ends when the goal is met or the user stops it. 3 Report: audit claims, compile report, decide next steps.

1 · Setup

The agent interviews you first: the goal, the constraints, and the metric that will decide what counts as better. It runs a baseline experiment before anything changes, so every later result has something real to beat.

2 · Loop

Each cycle the agent proposes a change, implements it, runs it, and evaluates the result against the metric. Every result carries a label saying how it was checked, and every cycle is recorded, including the ones that failed. You can step in between cycles, or let it run.

3 · Report

When the goal is met, or you stop it, the claims are audited against the record before the report is written, and you decide what comes next.

More detailWhat's inside, the five skills to know by name, and the full campaign schematic →

03Case studies

Six case studies of collaborative agentic research from our quantum-sensing work, reported in the preprint (Sec. IV): very different projects, in simulation, on measured data, and on live hardware. They ran on earlier PhysKit versions, listed in the preprint; for new work, use the latest release.

A · Machine learning−33% error · synthetic
A typical synthetic test image reconstructed by the published network (broken segments) and by the campaign's network (follows the wire pattern), and the mean test error over the 34 experiments plotted in the preprint's Fig. 2a, ending 33% below the published network.

Current-density reconstruction

A network that outperforms our published one at recovering current maps from noisy magnetic images.

Synthetic test data · a typical test image

B · Model identificationbeats published
Simplified level diagram of the eleven-level model the campaign identified (additions in teal), and the search score across the 101 model structures tested, dropping below the published nine-level model toward the counting-noise floor.

Quantum-defect photophysics

A photodynamic model of VB− defects in hBN that outperforms our published model.

Measured data

C · Device design2.7× vs first sweep · sim.
The junction of the final microwave design (four 100 µm copper traces meeting at the hBN flake), and the running best simulated circularly polarized field across 313 designs, ending 2.7 times the best design of the agent's first size sweep.

Microwave device design

A fabrication-ready waveguide design with 2.7× the field of the best design in the agent's first size sweep.

Simulation

D · Quantum control>10× lower infidelity · sim.
The best robust pulse sequence (B1) over 49 experiments against the published yxx48 benchmark, and its performance as added site disorder grows, staying above yxx48.

Pulse-sequence design

A pulse-sequence candidate that beats the published benchmark by >10× and stays ahead under disorder.

Simulation

E · Hardware control~1 Hz · live hardware
Photo of the NV-NMR apparatus, and the figure of merit of the 34 scored experiments over 20.8 hours on live hardware, with the running best from the first scored run at 3.2 hours.

NMR spectrometer commissioning

From an uncalibrated state to ~1 Hz frequency precision (best run; ten-run median 1.5 Hz).

Live hardware

F · Data analysis2,178 islands
Fit residual (measured minus fitted field) at 30.3 mT, at saturation, on the same pixels and colour scale: the baseline fit leaves 101 µT rms with strong edge artifacts; the joint fit leaves 20 µT rms. This saturated frame shows the clearest difference; mid-reversal residuals drop less.

Spin-ice microstate reconstruction

To our knowledge, the first such reconstruction from diffraction-limited magnetic imaging.

Measured data · fit residual at 30.3 mT (saturation) · baseline fit 101 → joint fit 20 µT rms (clearest frame)

All six case studies as a list

04Get started

Install

On GitHub now, as a pre-release. It works with Claude Code and Codex.

In a Claude Code session:

/plugin marketplace add Walsworth-Group/physkit
/plugin install physkit@physkit

In Codex, from your shell, then start a new session:

codex plugin marketplace add Walsworth-Group/physkit
codex plugin add physkit@physkit

Skills appear as /physkit:<name> in Claude Code and $physkit:<name> in Codex. Scopes, updating, pinning a version, other agents, and keeping the doctrine always loaded: the full install guide · getting started.

Cite

If you use PhysKit, please cite the preprint and the software version you used:

N. R. Reed, D. M. Daly, A. J. Beling, J. D. Giandrea, R. L. Walsworth, J. W. Blanchard, and D. Ang, Principles and Techniques for Agentic Research in Experimental Physics, arXiv:2610.17193 (2026).

Show BibTeX 
@misc{reed_principles_2026,
  title         = {Principles and Techniques for Agentic Research in Experimental Physics},
  author        = {Reed, Niko R. and Daly, Declan M. and Beling, Andrew J. and Giandrea, Jordan D.
                   and Walsworth, Ronald L. and Blanchard, John W. and Ang, Daniel},
  year          = {2026},
  eprint        = {2610.17193},
  archivePrefix = {arXiv}
}

GitHub's “Cite this repository” button gives the current citation in BibTeX and APA.

05FAQ

What is PhysKit?

A framework for agentic research in experimental physics including skills, prompts, templates, and code, installed as a plugin. It has two layers: a general science toolkit you can use in any session, and a campaign layer that runs closed-loop research campaigns.

Which agents does it work with?

The full plugin installs in Claude Code and Codex. OpenCode and Gemini CLI can use the general skills through a bundled installer. See the multi-agent notes.

What does it cost?

PhysKit is free and MIT-licensed. You need access to the agent you run it in.

Do I need to run a campaign?

No. General skills can trigger in ordinary sessions with no setup beyond installing the plugin.

How does it keep an agent from fabricating results or citations?

Several ways, layered. Every result carries an honest label saying how it was checked — unverified, self-checked, or confirmed by an independent check — and the label travels with the number into every report. Every number in a report is labeled by provenance, cite-check verifies each reference against its source, and in a campaign executable gates refuse to promote a result under a stronger label than it earned. These reduce the risk; they don't remove the need for you to check work you build on.

Does PhysKit send my data anywhere?

PhysKit itself makes no network calls — it is skills, templates, and local scripts. Your agent sends your session to its model provider as it normally does.

Is it only for experimental physics?

We tested PhysKit on tasks relevant to our work in experimental physics, including derivations and simulations which support our work. However, we expect many components of the kit to be more broadly useful. Users should feel free to adapt the kit to suit their needs

What does "pre-release" mean for me?

PhysKit is still pre-release: skills, templates, and doctrine still change between versions and we are seeking feedback from early users. We recommend using the latest release.

How do I report a problem or suggest an improvement?

Open an issue on GitHub, or write to [email protected].