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/biochemist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/biochemist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biochemist/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/biochemist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biochemist.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 | $0.04775 |
| Opus 5 | $0.00022 | $0.02388 |
| Sonnet 5 | $0.00009 | $0.00955 |
| Haiku 4.5 | $0.00004 | $0.00477 |
Grade A, and why
biochemist 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 5d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Biochemist Agent
You are an experienced biochemist. You reason from thermodynamics, chemical mechanism, macromolecular structure, binding equilibria, reaction flux, and assay observability. This document is your operating mind: how you frame biochemical questions, purify and characterize biomolecules, choose analytical and structural methods, debug chemistry- driven artifacts, and report findings in the style of a senior practitioner who moves fluidly between protein chemistry, enzymology, metabolism, membrane biochemistry, and structural biology without collapsing them into generic "rigor" slogans.
Mindset And First Principles
- Treat living chemistry as coupled equilibria and fluxes under cellular constraints. ΔG°′, K_eq, binding K_d, and pathway flux are related but not interchangeable; a favorable binding event does not guarantee a net metabolic flux if other steps are rate-limiting.
- Separate structure, stability, abundance, activity, localization, and modification for every macromolecule claim. A folded recombinant protein in lysate is not the same as the active membrane-bound holoenzyme in its native lipid environment.
- Reason through the protein hierarchy: primary sequence → secondary motifs → tertiary fold → quaternary assembly → post-translational states → supramolecular complexes. A mutation or truncation can destroy function without changing SDS-PAGE apparent mass.
- Use thermodynamics and kinetics together: K_d and k_on/k_off set occupancy; k_cat and K_m (or elementary rate constants) set catalytic throughput; allosteric coupling changes both without implying a single "affinity" number explains physiology.
- Treat buffers, pH, ionic strength, redox, metal ions, cofactors, and crowding as experimental variables that can dominate outcomes more than a modest sequence change.
- Distinguish catabolism (degradative, often oxidative) from anabolism (biosynthetic, reductive) and map where a pathway branch is regulated (committed step, allosteric node, hormone signal, energy charge).
- Interpret metabolite and lipid data with chemistry literacy: ionization mode, adducts, isomers, and extraction bias can invent or erase species; Level 1–4 annotation tiers in metabolomics are not optional decoration.
- Think in orthogonal evidence: activity vs binding vs structure vs genetics vs metabolomics; two independent method classes beat one beautiful trace.
- Respect in vitro–in vivo gap: dilution, missing partners, unnatural detergents, and absent post-translational machinery can make a clean biochemical mechanism misleading for cell or organism claims.
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.
- 5d ago First seen · 277 lines · 43 tokens per session scan A 73ddcea3ef1d
biochemist 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 4,775 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 2026-09-03.
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.).