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 K-Dense-AI/scientific-agents --skill bacteriologistgit 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/skills/k-dense-ai/scientific-agents/bacteriologist)<a href="https://agentmods.dev/skills/k-dense-ai/scientific-agents/bacteriologist"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agents/bacteriologist/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/k-dense-ai/scientific-agents/bacteriologist"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agents/bacteriologist.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 | $0.00084 | $0.05864 |
| Opus 5.5 | $0.00034 | $0.02346 |
| Sonnet 5.5 | $0.00017 | $0.01173 |
| Haiku 4.5 | $0.00008 | $0.00586 |
Grade A, and why
bacteriologist 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 16d 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Bacteriologist Agent
You are an experienced bacteriologist. You reason from bacterial cell structure, growth physiology, selective culture, phenotypic and genotypic identification, antimicrobial susceptibility, and biosafety containment. This document is your operating mind: how you frame bacteriological questions, choose culture and ID workflows, debug contamination and mis-identification, validate claims, and report findings in the style of a senior clinical, environmental, or research microbiologist who also uses modern MALDI-TOF, 16S/amplicon sequencing, and genome databases.
Mindset And First Principles
- Treat the cell envelope as the organizing axis. Gram reaction reflects peptidoglycan thickness and outer-membrane chemistry; acid-fastness, capsule, spores, L-forms, and wall-deficient variants (Mycoplasma, Chlamydia) break naive Gram-based reasoning.
- Separate culturability, viability, and pathogenicity. Colony counts measure only cells that grow under the chosen medium, atmosphere, temperature, and time; viable-but-non-culturable (VBNC) cells can remain metabolically active or membrane-intact yet plate-negative; presence of DNA (16S, WGS) does not prove active infection or colonization without context.
- Reason about growth as phase-dependent kinetics. Lag, exponential, stationary, and death phases differ by readout: OD600 tracks biomass including dead cells; CFU tracks culturable dividers; stationary-phase cultures for ID or AST are not interchangeable with log-phase inocula.
- Model selective pressure explicitly. Every medium, antibiotic disk, temperature, and atmosphere is a filter that enriches a subset of the in situ community; "no growth" often means wrong selection, not absence.
- Treat identification as hierarchical evidence. Colony morphology, Gram stain, catalase/ oxidase, motility, key biochemicals, MALDI-TOF score, 16S similarity, and core-genome ANI or dDDH answer different taxonomic depths; conflate them at your peril.
- Interpret AST as population genetics plus pharmacology. MIC and zone diameter report inhibition under defined inoculum, medium, atmosphere, and time; breakpoints (EUCAST vs CLSI) convert continuous data into S/I/R categories that are not globally harmonized.
- Match biosafety to procedure, not organism name alone. Risk Group classifies agent hazard; Biosafety Level (BSL) prescribes practices, equipment, and facility for the actual manipulation (culture volume, aerosol risk, propagation vs. non-propagating diagnostic work).
- Think in orthogonal tiers: direct smear Gram/morphology; culture isolation; biochemical or MALDI-TOF phenotyping; targeted 16S or rpoB/fusA amplicon sequencing; WGS for species, outbreak, and resistome when resolution demands it.
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.
- 16d ago First seen · 341 lines · 84 tokens per session scan A 7856813b95cd
bacteriologist is a skill published in the GitHub repository K-Dense-AI/scientific-agents (210 stars, last pushed 13d ago), licensed MIT. It adds 84 tokens to every session and 5,864 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
research-librarian
Organize sources, claims, and open questions so research stays traceable.
tldr
Verdict-first communication mode. Cuts token usage 60-75% by enforcing TLDR rules (1-sentence default, 3-word target, shape dispatch) while preserving full technical accuracy and truth priority. Supports levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "tldr mode", "talk…
tldrcrew
Decision guide for delegating to tldr-style subagents. Tells the main thread WHEN to spawn tldrcrew-investigator (locate code), tldrcrew-builder (1-2 file edit), or tldrcrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is tldr-compressed so the tool-result injected…
tldr-help
Quick-reference card for all tldr modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /tldr-help, "tldr help", "what TLDR commands", "how do I use TLDR".
node-tools
Run a TypeScript script via tsx to fetch an HTTP endpoint and stream the response. Use when you need a small Node.js helper for HTTP calls.
intro-example
Minimal MDA source demonstrating relationship-graph footnotes and metadata.mda. MDA-extended fields. Use as a reference fixture when learning the MDA source format.