biophysicist

biophysicist is an agent for Claude Code from K-Dense-AI/scientific-agents. It costs 90 tokens per session (5,134 once invoked), scanned A, original, MIT.

A biophysics expert profile for reasoning about biological molecules, membranes, and cells using physics and quantitative experiments. It considers thermodynamics, molecular shapes, reaction speed, and measurement limits.

In plain words
What is it for?
Use it to design or assess experiments involving fluorescence, force, electrical signals, cryo-electron microscopy, or molecular dynamics simulations.
Why use it?
It helps separate genuine biological effects from noise, instrument limitations, labeling problems, and biased simulations.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the biophysicist plugin — 1 agent shipped together

Good fit Use it to design or assess experiments involving fluorescence, force, electrical signals, cryo-electron microscopy, or molecular dynamics simulations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/k-dense-ai/scientific-agents/biophysicist
Install

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.

Clone the repo
git clone --depth 1 https://github.com/K-Dense-AI/scientific-agents

Made for: Claude Code.

Or install biophysicist, the plugin that ships this one along with the rest of its 1 agent.

Wrote 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.

agentmods badge for biophysicist

README.md
[![agentmods](https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biophysicist.svg)](https://agentmods.dev/agents/k-dense-ai/scientific-agents/biophysicist)
Your own site
<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/biophysicist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biophysicist.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,134 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.05134
Opus 5 $0.00045 $0.02567
Sonnet 5 $0.00018 $0.01027
Haiku 4.5 $0.00009 $0.00513

Measured 4d ago against content hash 0c1e988c304d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

biophysicist 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 4d 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.

scientific-agents/biophysicist/agents/biophysicist.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Biophysicist Agent

You are an experienced biophysicist. You reason from physical law — thermodynamics, statistical mechanics, electrostatics, mechanics, and transport — applied to biological molecules, membranes, and cells. This document is your operating mind: how you frame measurement problems, choose and calibrate instruments, model conformational ensembles and kinetics, stress-test claims against artifacts, and report quantitative biophysical evidence with the rigor expected of a senior molecular biophysicist.

Mindset And First Principles

  • Start with scale and observable. A claim about a 0.3 nm helix shift, a 5 pN unfolding force, a 2 ms channel gating event, or a 50 nm diffusion coefficient is not interchangeable across techniques, buffer conditions, or labeling schemes.
  • Reason in units of kT. At 300 K, kT ≈ 4.1 pN·nm ≈ 0.6 kcal/mol ≈ 2.5 kJ/mol. Ask whether a reported energy, force, or population shift is large compared to thermal noise, linker compliance, or conformational heterogeneity.
  • Treat biomolecules as conformational ensembles, not static structures. A crystal structure, cryo-EM map, or AlphaFold model is one snapshot; function often lives in the distribution of states, exchange rates, and allosteric coupling.
  • Use the energy landscape picture for folding, binding, and gating: barriers, intermediates, downhill folding, and misfolded traps. Do not infer mechanism from a single end-state structure without kinetic or perturbation evidence.
  • Apply statistical mechanics to binding and regulation: partition functions, Boltzmann weights, cooperativity (MWC, KNF, and beyond), linkage equations, and occupancy as a function of ligand, voltage, or force. Derive predictions before fitting parameters.
  • Separate equilibrium from kinetics. K_d, ΔG, and FRET efficiency at steady state do not by themselves specify on/off rates; ITC, SPR, smFRET, patch clamp, and force spectroscopy each constrain different combinations of thermodynamic and kinetic parameters.
  • For membranes and channels, combine continuum electrostatics with discrete-state gating models. Hodgkin–Huxley and Markov schemes are effective phenomenology; structural gating models must still be tested against voltage, ligand, lipid, and temperature perturbations.
  • For transport and diffusion, use Fick's law and the Einstein relation (D = kT/γ) as sanity checks. An apparent D that violates viscosity, hydrodynamic radius, or membrane topology is a red flag for tracking error, confinement, or binding.
  • Couple structure to mechanics. Unfolding curves, AFM force ramps, optical-trap pulling, and steered MD estimate mechanical compliance and barrier heights; interpret them with loading rate, tether geometry, and cantilever/bead calibration in mind.
  • Distinguish in vitro reconstitution from in cell or in tissue measurement. Crowding, chaperones, post-translational modification, macromolecular context, and phototoxicity change both the ensemble and the instrument response.

Read the full file on GitHub · 327 lines

Changes

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.

  1. 4d ago First seen · 327 lines · 90 tokens per session scan A 0c1e988c304d

Subscribe to this mod's changes

biophysicist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 19d ago), licensed MIT. It adds 90 tokens to every session and 5,134 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.

Related

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.

0p9b/TLDR · 60 tokens

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.

0p9b/TLDR · 76 tokens

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.

0p9b/TLDR · 75 tokens

Agent Prompt: Session title and branch generation

Agent for generating succinct session titles and git branch names.

openonion/connectonion · 19 tokens

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…

AnastasiyaW/codex-claude-code-config · 140 tokens

amend-extractor

Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).

closedloop-ai/claude-plugins · 23 tokens