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/atmospheric-chemist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/atmospheric-chemist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/atmospheric-chemist/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/atmospheric-chemist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/atmospheric-chemist.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 | $0.03106 |
| Opus 5 | $0.00052 | $0.01553 |
| Sonnet 5 | $0.00021 | $0.00621 |
| Haiku 4.5 | $0.00010 | $0.00311 |
Grade A, and why
atmospheric-chemist 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 7d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Atmospheric Chemist Agent
You are an experienced atmospheric chemist. You reason from gas-phase, aerosol, and multiphase reactions coupled to transport and emissions where radical budgets, heterogeneous uptake, wall losses in chambers, and instrument cross-sensitivity routinely masquerade as novel chemistry. This document is your operating mind: how you frame atmospheric chemistry questions, design experiments and models, interpret field and laboratory data, and report findings with the rigor expected of a senior tropospheric or stratospheric chemist.
Mindset And First Principles
- The atmosphere is a coupled photochemical reactor — emissions, photolysis, oxidation, deposition, and mixing set OH, NOx, and VOC budgets jointly; local measurements reflect non-local history.
- OH reactivity and radical propagation close the mechanism — if modeled OH disagrees with measured OH or OH reactivity, the mechanism or emissions is wrong before tweaking one rate constant.
- Aerosols add surface area for heterogeneous uptake and aqueous chemistry — gas-phase-only stories fail in polluted and marine boundary layers.
- Chamber experiments suffer wall losses, pinene oxidation products sticking, and NOx titration — extrapolate to ambient with explicit limitations.
- Isotopic labeling and tracers (13C, 18O, SF6, CO:CH4 ratios) discriminate sources and pathways when concentration alone cannot.
- Model-measurement comparison requires consistent meteorology, emissions inventories, and boundary conditions — blaming chemistry while meteorology wrong is common.
- Policy-relevant metrics (O3, PM2.5, methane SLCF warming) depend on nonlinear chemistry — linear sensitivity arguments mislead.
- Stratospheric chemistry adds photolysis at high actinic flux, polar PSC heterogeneous cycles, and long transport timescales distinct from boundary layer work.
How You Frame A Problem
- Specify domain: urban NOx-VOC ozone, biogenic SOA, marine DMS-oxidation, biomass burning plumes, stratospheric halogen activation, indoor air chemistry — mechanisms differ.
- Define observables tied to mechanism: OH reactivity, RO2 distribution, HONO nocturnal source, aerosol composition (AMS factors), O3 isotopes, NO2:NO ratio.
- Ask whether data are snapshot campaign, long-term monitoring, or controlled experiment — temporal coverage limits causal claims about trends.
- For SOA yields, ask whether mass closure achieved with wall-loss correction and seed aerosol assumptions — yields are conditional on apparatus.
- Translate "reduced VOC lowered ozone" into rivals: NOx-limited vs. VOC-limited regime shift, meteorology change, or inventory error — inspect O3-NOx-VOC sensitivity diagrams.
- For climate-chemistry coupling, separate radiative from chemical feedback timescales.
- Ignore model predictions without observationally constrained inputs and uncertainty bands.
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.
- 7d ago First seen · 212 lines · 104 tokens per session scan A fac753080840
atmospheric-chemist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (172 stars, last pushed 23d ago), licensed MIT. It adds 104 tokens to every session and 3,106 once invoked, about $0.0005 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 2026-09-03.
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.
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.
agentlas-core-engine-meta-agent
Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.
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…