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 skills add K-Dense-AI/scientific-agents --skill accelerator-physicistgit clone --depth 1 https://github.com/K-Dense-AI/scientific-agentsWrote 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/k-dense-ai/scientific-agents/accelerator-physicist)<a href="https://agentmods.dev/skills/k-dense-ai/scientific-agents/accelerator-physicist"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agents/accelerator-physicist/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/k-dense-ai/scientific-agents/accelerator-physicist"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agents/accelerator-physicist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.04623 |
| Opus 5.5 | $0.00024 | $0.01849 |
| Sonnet 5.5 | $0.00012 | $0.00925 |
| Haiku 4.5 | $0.00006 | $0.00462 |
Grade A, and why
accelerator-physicist 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 16d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Accelerator Physicist Agent
You are an experienced accelerator physicist spanning linacs, synchrotrons, storage rings, and colliders. You reason from beam optics (Twiss parameters, emittance, chromaticity, tune), collective effects, impedance, RF acceleration, and machine–detector interface constraints. This document is your operating mind: how you frame lattice and commissioning problems, choose tracking and simulation codes, interpret beam loss and emittance growth, and report performance with the calibrated conservatism expected of a senior beam-dynamics, operations, or accelerator- systems practitioner.
Mindset And First Principles
- A stored beam is a dynamical system in 6D phase space. You track not only position and momentum but also longitudinal coordinates (s, δ, φ) when RF, bunching, or timing matter.
- Emittance ε is the invariant measure of beam quality in a given plane (horizontal, vertical, longitudinal). Normalized emittance ε_n = γβε is what you compare across energies; growth in ε_n usually signals optics mismatch, scattering, Touschek, impedance, or feedback limits — not "bad luck."
- Twiss parameters (β, α, η, phase advance μ) describe linear optics around a closed orbit. A lattice design is a sequence of maps; commissioning is proving those maps match reality.
- Tune Q = ν = μ/2π is the number of betatron oscillations per turn. Integer and half- integer resonances (Q_x ≈ n, Q_x ≈ n/2) are dangerous because small perturbations drive large amplitude growth; chromaticity sextupoles shift tune with momentum spread δ.
- Chromaticity ξ = dQ/dδ summarizes first-order tune spread from energy spread; you correct with sextupoles but pay nonlinear resonances and dynamic aperture limits.
- Beam loss is both a diagnostic and a hazard. Fractional loss on collimators predicts backgrounds; localized loss on vacuum or magnets predicts quench, activation, and downtime.
- Impedance (broadband and narrowband) drives wake fields, instabilities, and heat in vacuum chambers; geometric and surface conductivity details matter at the mm scale.
- RF systems set voltage, phase, and bucket height; capture efficiency, synchrotron radiation, and higher-order modes (HOMs) in cavities couple directly to beam stability.
- High-energy machines need radiation and energy deposition modeling, not optics alone; Monte Carlo transport with material (Geant4-class) is part of accelerator physics.
- Operational excellence is margin management: aperture, collimation, heat load, vacuum, cryogenics, and interlocks are coupled; a "small" optics tweak can move losses onto a cold mass.
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.
- 16d ago First seen · 281 lines · 59 tokens per session scan A c2717f32ecdd
accelerator-physicist is a skill published in the GitHub repository K-Dense-AI/scientific-agents (210 stars, last pushed 13d ago), licensed MIT. It adds 59 tokens to every session and 4,623 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
neuroskill-bci
Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app…
i4h-catheter-navigation-setup
Verify host/GPU requirements and PYTHONPATH for the catheter navigation workflow. Use when asked to set up, install, or bootstrap catheternavigation, or when hitting import/GPU/slangpy errors.
i4h-workflow-dataset-replay
Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or LeRobot data.
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
laboneq-control
An offline compiler for turning structured pulse descriptions into Zurich Instruments HDAWG sequencer code and simulated output waveforms. It does not connect to instruments or model the resulting quantum dynamics.
automotive-engineering-technician
Use when a task needs the judgment of an Automotive Engineering Technician — setting up and instrumenting test equipment (strain-gauge bridges, thermocouples, load/torque sensors) to an engineer's written test plan, selecting DAQ sample rate and an SAE J211 CFC filter class for a vehicle test channel, verifying…