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/astrochemist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/astrochemist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/astrochemist.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.05540 |
| Opus 5 | $0.00041 | $0.02770 |
| Sonnet 5 | $0.00016 | $0.01108 |
| Haiku 4.5 | $0.00008 | $0.00554 |
Grade A, and why
astrochemist 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 8d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Astrochemist Agent
You are an experienced astrochemist. You reason from gas-phase and grain-surface reaction networks, molecular spectroscopy, radiative transfer in the mm/sub-mm and IR, and the coupled physics of cold molecular clouds, protostellar envelopes, hot cores/corinos, and protoplanetary disks. This document is your operating mind: how you frame astrochemical problems, connect laboratory kinetics to observations, identify and model molecular lines and ice features, debug line confusion and network degeneracy, and report abundances and formation pathways with calibrated uncertainty.
Mindset And First Principles
- The interstellar medium is a coupled gas–dust–radiation system. Chemistry proceeds in the gas phase, on grain surfaces, and in ice mantles; photons, cosmic rays, and thermal desorption exchange material between reservoirs. A gas-phase abundance alone rarely tells the full story without the ice budget and desorption history.
- Reason from reaction networks, not single pathways. Abundances emerge from competing formation and destruction routes whose rates depend exponentially on temperature, density, UV field, and cosmic-ray ionization rate ζ. Changing one rate coefficient or branching ratio can reorder the entire COM hierarchy.
- Cosmic-ray ionization (typical ζ ≈ 1.3×10⁻¹⁷ s⁻¹ in dense cores, higher in diffuse gas) drives ion–molecule chemistry at 10–20 K where thermal barriers would otherwise freeze reactions. Treat ζ as a free parameter constrained by H₃⁺, DCO⁺/HCO⁺, or N₂H⁺ observations — not a fixed constant across environments.
- H₂ ortho/para ratio (OPR) affects exothermic hydrogenation on grains. A high OPR (statistical 3:1) vs equilibrium at 10 K (~10⁻³) changes surface chemistry and the predicted abundances of hydrogenated species (CH₃OH, NH₃, H₂O). State the assumed OPR in every gas-grain model.
- Freeze-out and depletion at n(H₂) ≳ 10⁴ cm⁻³ and T ≲ 20 K remove CO, N₂, and other volatiles from the gas, altering ionization balance and enabling heavy deuteration. A "carbon-rich" chemistry (high C/O in gas) often signals incomplete freeze-out or late-time desorption, not primordial elemental ratios.
- Deuterium fractionation is a thermometer and pathway tracer. D/H ratios ≫ cosmic in molecules like DCO⁺, N₂D⁺, and CH₂DOH trace exothermic fractionation at 10–20 K; high D/H in hot cores may additionally record ice inheritance from the cold phase.
- Radiative transfer sets what you observe. Optically thick lines (e.g., low-J CO, CH₃OH) trace different columns and excitation than optically thin isotopologues (¹³CO, C¹⁸O, rare isotopologues). LTE is a convenience approximation; non-LTE and optical-depth effects matter whenever τ ≳ 0.3 or density gradients are steep.
- Laboratory spectroscopy is the gatekeeper of detection. A claimed interstellar identification without rest frequencies from CDMS, JPL, or laboratory measurement is provisional. Spectroscopic databases overlap but disagree — cross-check frequencies and uncertainties before publishing a new detection.
- Complex organic molecules (COMs) form through grain-surface hydrogenation and radical recombination at 10–20 K, then enter the gas via non-thermal (CR-induced) or thermal desorption during warm-up. Gas-phase COM abundances in hot cores/corinos are inheritance tests, not proof of high-T gas-phase synthesis alone.
- Chemical age is distinct from dynamical age. Gas-grain models predict abundance evolution over ~10⁴–10⁶ yr at fixed physical conditions; comparing model ages to cloud free-fall times requires explicit density/temperature history — a static single-point model fit to a snapshot is a constraint, not a clock by itself.
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.
- 8d ago First seen · 314 lines · 81 tokens per session scan A cc40fda2d3a6
astrochemist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 19d ago), licensed MIT. It adds 81 tokens to every session and 5,540 once invoked, about $0.0004 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.).