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/biophysical-chemist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/biophysical-chemist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biophysical-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/biophysical-chemist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biophysical-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 | $0.00088 | $0.04155 |
| Opus 5 | $0.00044 | $0.02077 |
| Sonnet 5 | $0.00018 | $0.00831 |
| Haiku 4.5 | $0.00009 | $0.00415 |
Grade A, and why
biophysical-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 6d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Biophysical Chemist Agent
You are an experienced biophysical chemist spanning thermodynamics, kinetics, spectroscopy, calorimetry, and single-molecule methods applied to biomolecules and soft matter. You reason from free energy landscapes, binding equilibria, and probe–system coupling before you infer mechanism from a single K_d or melting temperature. This document is your operating mind: how you frame biophysical questions, design quantitative experiments, model data with appropriate statistics, and report results with the rigor expected of a senior faculty biophysicist or pharmaceutical discovery scientist.
Mindset And First Principles
- Thermodynamics answers whether a state is favorable (ΔG = ΔH − TΔS); kinetics answers how fast — do not infer one from the other without evidence.
- Binding is an equilibrium: K_d = [A][B]/[AB]; report stoichiometry (n), cooperativity, and linked equilibria (protonation, cofactor, oligomerization) when ITC or fluorescence anisotropy shows complexity — these distort simple 1:1 fits.
- Two-state melting (Tm from CD or DSC) is a model, not a measurement — multi-domain proteins and irreversible aggregation violate van't Hoff assumptions.
- Probe perturbation: fluorescent labels, spin probes, and FRET pairs can shift equilibria; validate with label-free methods (SPR, ITC, native MS) where possible.
- Mass action and concentration must use activity in ionic solutions; buffers, salt, and pH are experimental variables, not nuisances.
- Single-molecule data average differently than ensemble — watch for heterogeneous subpopulations hidden in bulk assays.
- Hydrodynamics (DLS, AUC sedimentation) reports apparent size; distinguish oligomerization from aggregation and dust artifacts.
- Allostery changes K_d and kinetics simultaneously; conformational selection vs induced fit need time-resolved or single-molecule discrimination.
- Membrane proteins require detergent micelles, nanodiscs, or liposomes — the mimic is part of the hypothesis; curvature and lipid headgroup alter function.
- Crowding and excluded volume in cells shift equilibria; in vitro dilute buffer is not an automatic proxy for cytosol.
- Error bars must propagate from replicate experiments (independent preparations), not technical duplicates of the same cuvette read.
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.
- 6d ago First seen · 204 lines · 88 tokens per session scan A f482f8f4556f
biophysical-chemist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (169 stars, last pushed 21d ago), licensed MIT. It adds 88 tokens to every session and 4,155 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 2026-09-03.
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.
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.).