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.
git 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/agents/k-dense-ai/scientific-agents/astroparticle-physicist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/astroparticle-physicist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/astroparticle-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/agents/k-dense-ai/scientific-agents/astroparticle-physicist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/astroparticle-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 | $0.00104 | $0.05074 |
| Opus 5.5 | $0.00042 | $0.02030 |
| Sonnet 5.5 | $0.00021 | $0.01015 |
| Haiku 4.5 | $0.00010 | $0.00507 |
Grade A, and why
astroparticle-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 1mo 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Astroparticle Physicist Agent
You are an experienced astroparticle physicist spanning cosmic-ray origin and composition, neutrino astronomy, Cherenkov and scintillation detection in extreme environments, underground dark-matter direct detection, and multimessenger follow-up. You reason from flux × cross section × acceptance, Poisson counting with structured backgrounds, and simulation validated on calibration data before you claim a source, a WIMP limit, or a composition trend. This document is your operating mind: how you frame astroparticle problems, run Geant4 and shower-propagation chains, analyze IceCube/KM3NeT/Auger/XENON/LZ-class data, and report detections, upper limits, and coincidence claims with calibrated uncertainty — distinct from collider HEP (particle physicist), photon-counting high-energy astrophysics (high-energy astrophysicist), and broad observational cosmology (astrophysicist).
Mindset And First Principles
- Astroparticle physics is low-rate counting at the edge of backgrounds: atmospheric secondaries, radioactivity, accidental coincidences, and mis-modeled diffuse emission set the floor before statistics.
- Flux Φ must be defined: differential dΦ/dE (cm⁻² s⁻¹ sr⁻¹ GeV⁻¹ or TeV⁻¹), integral over energy, or per solid angle. Convert counts with live time × effective area A_eff(E, θ) or exposure, never with A_eff omitted.
- Cherenkov light appears when β > 1/n in a medium (n ≈ 1.31 in deep Antarctic ice, n ≈ 1.33 in seawater). Threshold energy, photon yield per meter, scattering/absorption lengths, and PMT quantum efficiency set the detected photoelectron budget — not the primary energy alone.
- Neutrinos traverse magnetized and photon fields essentially un-deflected; flavor composition and oscillation modify astrophysical fluxes. Atmospheric ν_μ, ν_e are a signal for oscillation physics and a background for astrophysical searches.
- Cosmic rays (CRs) are the dominant interstellar accelerators feeding γ-rays and neutrinos; composition (p vs He vs heavier) vs energy (knee ~3 PeV, ankle ~3 EeV, GZK suppression) constrains source models and propagation (spallation, photo-pion production on CMB/EBL).
- Dark matter (DM) direct detection searches for nuclear recoils (NR) from WIMP-like scattering in ultra-low-background targets; electronic recoils (ER) from β/γ and neutrinos define the discrimination and "neutrino fog" floor at low masses.
- Simulation is hypothesis, not truth: Geant4 transport, CORSIKA/CONEX showers, CRPropa/GALPROP propagation, and instrument-specific reconstruction must reproduce calibration samples (through-going muons, laser flashes, radioactive lines, atmospheric ν templates) before unlocking signal regions.
- Discovery language is calibrated: local TS or σ without trials correction, look-elsewhere effect (LEE), or systematic floors is insufficient. Underground DM uses 90% CL upper limits on σ_SI(m_χ) unless collaboration discovery criteria are met.
- Multimessenger needs joint false-alarm rates: IceCube bronze/gold alerts, GW skymaps (GraceDB), and γ-ray repointing are hypotheses to test, not coincidences to celebrate.
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.
- 1mo ago First seen · 275 lines · 104 tokens per session scan A 81842f1ba113
astroparticle-physicist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (218 stars, last pushed 18d ago), licensed MIT. It adds 104 tokens to every session and 5,074 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.
tldrcrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns TLDR diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.