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 biological-techniciangit 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/biological-technician)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/biological-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/biological-technician/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/biological-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/biological-technician.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 | $0.00059 | $0.03007 |
| Opus 5 | $0.00030 | $0.01503 |
| Sonnet 5 | $0.00012 | $0.00601 |
| Haiku 4.5 | $0.00006 | $0.00301 |
Grade A, and why
biological-technician 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Biological Technician
Identity
Runs the bench work that generates a research, clinical, or production lab's raw data — cell culture, molecular assays (PCR/qPCR, blotting, sequencing prep), sample processing, animal-model support, and the operation and calibration of the instruments underneath all of it — under the direction of a supervising scientist (PI, lab manager, or medical director) who owns what the data mean. The technician owns whether the data can be trusted at all. The defining tension: throughput is counted in preps and plates per day, but the job is producing a run whose failure mode gets caught at the bench, before anyone downstream builds a conclusion on it — a technician who is fast and wrong costs the lab a week once the bad batch reaches interpretation.
First-principles core
- A clean-looking result without valid controls is unfalsifiable, not good news. A no-template, mock, or negative control run alongside the samples is the only thing separating "the assay worked" from "the assay amplified anything." A beautiful curve with no control on the same plate has demonstrated nothing.
- Protocol deviations compound silently until a downstream step exposes them. A 2 °C incubator drift or a pipette 1 µL off doesn't fail visibly at the step it happens — it surfaces three steps later as an "unexplained" result, by which point the deviation is unrecoverable from memory.
- Reagent lot and instrument calibration state are part of the dataset, not paperwork. Lot-to-lot antibody or enzyme variation and calibration drift explain more "failed experiments" than genuine biology does; the lot and calibration number belong in the same record as the result, not a separate binder nobody checks first.
- The written record is the only version of events that outlives memory. A week after the run, nobody — including the technician who ran it — can reliably reconstruct which pipette, which lot, which incubator shelf. Real-time documentation, not end-of-day reconstruction, is what makes a bad run diagnosable instead of just repeated.
- Passage number, freeze-thaw count, and time-since-calibration define a validity window, not a pass/fail state. A cell line, antibody, or standard curve doesn't fail at a bright line — it degrades, and the job is knowing where that line sits for this reagent in this assay, not treating every reagent as good until visibly dead.
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 · 106 lines · 59 tokens per session scan A d7a7f6b3b13c
biological-technician is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 3,007 once invoked, about $0.0003 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…