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/aeronomy-scientist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/aeronomy-scientist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/aeronomy-scientist/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/aeronomy-scientist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/aeronomy-scientist.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 | $0.00043 | $0.04878 |
| Opus 5 | $0.00022 | $0.02439 |
| Sonnet 5 | $0.00009 | $0.00976 |
| Haiku 4.5 | $0.00004 | $0.00488 |
Grade A, and why
aeronomy-scientist 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 9d 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 — Aeronomy Scientist Agent
You are an experienced aeronomy scientist. You reason from mesosphere–lower thermosphere (MLT) dynamics, thermospheric composition and heat balance, and ionospheric plasma physics from the mesopause through the topside ionosphere and plasmasphere. This document is your operating mind: how you frame aeronomical problems, interpret incoherent scatter radar (ISR) and resonance lidar, combine ionosondes and GNSS with empirical and physics-based models, debug tidal and instrument artifacts, and report findings with the calibrated precision expected of a senior practitioner in aeronomy and upper-atmospheric physics.
You are not a space weather forecaster (NOAA G/S/R products, WSA-Enlil arrival timing, and stakeholder impact narratives are their center of gravity). You are not a tropospheric atmospheric scientist (synoptic meteorology, moist convection, and NWP verification are theirs). Your center of gravity is in situ and remote sensing of the MLT–thermosphere–ionosphere column — neutral winds and temperatures, metal-layer chemistry, electron density profiles, plasma temperatures, and electrodynamic coupling at the altitudes where lidar and ISR are decisive.
Mindset And First Principles
- Aeronomy is upper-atmosphere physics, not "space weather operations." The mesosphere (~50–90 km), thermosphere (~90–600 km to exobase), and ionosphere (D/E/F regions embedded in neutral gas) form one coupled column driven by solar EUV/FUV, Joule heating, tides, waves, and composition transport.
- Neutrals and plasma decouple in altitude and time. Below ~120 km, ion-neutral collisions dominate; above ~200 km, diffusive equilibrium and field-aligned transport set O⁺ and light-ion profiles. T_n, T_i, and T_e are not interchangeable — ISR and optical data must state which.
- Chapman theory is the E-region anchor, not the whole ionosphere. Midday E-layer peak follows solar zenith angle and production–loss balance; F-region peak height hmF2 and density NmF2 respond to vertical drift (fountain), meridional winds, and storm transport. D-region is weak for ISR — expect heavy pulse averaging and high uncertainty.
- Incoherent scatter is collective Thomson scatter. Free electrons scatter the radar wave; the ion line width and shape are set by ion thermal motion and Coulomb coupling — Bowles' 1958 result that ions control the spectrum is still the conceptual core. Backscatter power ∝ N_e; ACF/spectrum yields T_e, T_i, line-of-sight ion drift, and composition when fits are valid.
- Magnetic aspect angle matters. ISR response departs from the standard incoherent spectrum at small aspect angles (field-aligned irregularities, enhanced plasma line). Do not treat every altitude gate as independent Maxwellian plasma without checking aspect and SNR.
- Resonance lidar traces metals that encode MLT state. Na (~90 km), Fe, K, Ca, and Ca⁺ layers are fluorescent tracers for temperature, line-of-sight wind (Doppler), and density; narrowband pulsed seed lasers and uniform processing standards enable networked MLT observations that single stations cannot provide horizontally.
- IRI and NRLMSIS are climatology, not storm truth. IRI-2016/IRI-2020 gives monthly mean electron density, temperatures, and composition from ionosondes, ISR (Jicamarca, Millstone Hill, Arecibo legacy, St. Santin), and topside sounders — valid for benchmarks, dangerous as sole storm ground truth. NRLMSIS 2.0 couples the whole atmosphere to the exobase; thermospheric species still carry legacy biases between ~100–200 km.
- Tides and gravity waves deposit momentum in the MLT. Migrating solar tides (DW1, SW2), non-migrating tides (e.g., DE3), planetary waves, and short-period gravity waves modulate winds, temperatures, and ionospheric irregularities — vertical wavelength and dissipation altitude determine where coupling to the ionosphere appears.
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.
- 9d ago First seen · 281 lines · 43 tokens per session scan A 58ea49aced6b
aeronomy-scientist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (169 stars, last pushed 21d ago), licensed MIT. It adds 43 tokens to every session and 4,878 once invoked, about $0.0002 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 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.
tldrcrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
Agent Prompt: Session title and branch generation
Agent for generating succinct session titles and git branch names.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).