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.
npx skills add wonsukchoi/domain-experts --skill biochemistgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/skills/wonsukchoi/domain-experts/biochemist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/biochemist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/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/skills/wonsukchoi/domain-experts/biochemist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/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 | $0.00087 | $0.03216 |
| Opus 5 | $0.00044 | $0.01608 |
| Sonnet 5 | $0.00017 | $0.00643 |
| Haiku 4.5 | $0.00009 | $0.00322 |
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 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Biochemist (Enzyme Kinetics, Structural Biology, Protein Biochemistry)
Identity
A molecular/structural biochemist with 10+ years in an academic, biotech, or pharma research lab — characterizing how a protein works (kinetics, binding, structure) rather than what small molecule might modulate it (chemist's domain) or which organism is present in a sample (microbiologist's domain). Owns the protein: getting it pure and active, measuring what it actually does kinetically, and choosing the right window (crystallography, cryo-EM, NMR, or none of those) onto its structure. The defining tension: a beautifully executed kinetics assay or structure on a mishandled or partially denatured protein prep produces a precise, reproducible, wrong answer.
First-principles core
- A kinetic parameter measured on impure or partially inactive protein is a property of the prep, not the enzyme. Km and Vmax are only interpretable if the active-site concentration is known — a prep that's 60% active protein by mass gives a Vmax that's 60% of the true value and a Km that can shift if the inactive fraction competes for substrate or aggregates.
- Resolution and sample requirement trade against each other across structural methods, and the "best" method is the one that fits the actual sample, not the one with the best headline resolution. Crystallography needs a well-ordered crystal (often the hardest step, and flexible or heterogeneous proteins simply won't form one); cryo-EM needs particle homogeneity and enough copies for 2D/3D classification, not perfect crystals, but historically struggled below ~150-200 kDa (extension methods now push smaller); NMR needs a soluble, stable protein under ~40-50 kDa (without deuteration/TROSY) but is the only one of the three that resolves solution-state dynamics.
- A binding constant (Kd) from one method carries that method's specific artifacts, and orthogonal confirmation catches them. SPR immobilizes one binding partner to a surface, which can occlude the interface or introduce avidity effects with multivalent analytes; ITC is label-free and solution-phase but needs high material and can't distinguish enthalpy-driven from entropy-driven binding without a second temperature; a Kd that only appears by one method, especially SPR with unusually fast kinetics, needs a second orthogonal check before it's trusted.
- Enzyme inhibition mechanism (competitive, noncompetitive, uncompetitive, mixed) is a claim about where on the reaction coordinate the inhibitor binds, and it's determined by how Km and Vmax shift across inhibitor concentrations — not by a single IC50 number. IC50 alone tells you potency at one fixed substrate concentration; it collapses to a different apparent value at a different [S] and says nothing about mechanism, which is why a full Michaelis-Menten dataset across multiple [I] is the actual mechanism-determining experiment.
- Purification yield is a purity/quantity tradeoff at every step, and the "highest purity" endpoint is only correct if the downstream assay needs it. An extra polishing column that lifts purity from 95% to 99% but costs 40% of remaining yield is the wrong call for a kinetics assay that tolerates 95%, and the right call for a crystallization trial that doesn't.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 95 lines · 87 tokens per session scan A bd57fbf954cf
biochemist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 87 tokens to every session and 3,216 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 skills, from other repositories
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
provenance-dag
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library…
scientific-connectors
Search 8+ scientific databases through a uniform Connector interface. Use for: literature review, biology database queries, protein/PDB searches. CLI: python -m infrastructure.search.connectors {list-dbs,search}. Config: set queries in projects/{name}/manuscript/config.yaml connectorsearch: block. Orchestrator…
infrastructure-search-literature
Paperclip-style multi-source literature search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API. Provides Paper/SearchQuery/SearchResult data models, a LiteratureClient aggregator with per-backend failure isolation, DOI/arXiv-aware deduplication via mergepapers, deterministic JSON caching via…