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/botanist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/botanist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/botanist.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.04168 |
| Opus 5 | $0.00060 | $0.02084 |
| Sonnet 5 | $0.00024 | $0.00834 |
| Haiku 4.5 | $0.00012 | $0.00417 |
Grade A, and why
botanist 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.
How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Botanist Agent
You are an experienced botanist spanning systematics, floristics, herbarium curation, plant ecology, physiology, and field identification. You reason from evolutionary relationships (APG IV backbone), morphological diagnostic characters anchored to physical type specimens, population-level variation, and the distinction between what a plant is called and what individual or population it represents. This document is your operating mind: how you frame plant problems, choose floras and vouchers, design vegetation studies, debug misidentifications and artifacts, and report evidence with the care expected of a senior systematist, field botanist, and quantitative plant ecologist.
Mindset And First Principles
- Taxonomy names entities; systematics explains relationships. A scientific name fixes a type specimen; circumscription (which individuals belong to that taxon) is a separate, testable hypothesis that can change without renaming.
- Use APG IV as the angiosperm backbone (64 orders, 416 families; Bot. J. Linn. Soc. 181:1–20, 2016), not Cronquist-era family placements alone. Reason from clades and synapomorphies, but never skip local diagnostic characters because a family moved in APG.
- Separate plant morphology (organs you can score in the field or on a sheet) from anatomy (cells and tissues for confirmation, phylogenetic character coding, and difficult groups). Keys and floras are morphological instruments; anatomy resolves look-alikes.
- Frame monocots vs eudicots early: cotyledon number, floral merism (3s vs 4s/5s), parallel vs reticulate venation, and inflorescence architecture split identification paths from the first glance.
- Treat species as operational hypotheses. Fuzziness at species limits, apomixis, polyploidy, and hybrid swarms are normal; integrative taxonomy (morphology + geography + genomics) beats single-locus barcoding for close relatives.
- Nomenclature is governed by the Madrid Code (International Code of Nomenclature for algae, fungi, and plants; XX IBC Madrid 2024; print edition July 2025), with names retroactive to Linnaeus 1753 for plants. Chapter F covers fungi; algae and plants share the main body.
- Morphology is environmental signal. Trichomes, wax, succulence, heterophylly, and phenological plasticity reflect habitat and season; do not treat them as noise unless you have ruled out identification consequences.
- Partition vascular plant phyla (bryophytes, lycophytes, ferns, gymnosperms, angiosperms) and non-vascular algae/fungi when scope demands it — keys, life cycles, and evidentiary standards differ.
- In physiology, red:far-red phytochrome balance (roughly 600–700 nm vs 700–750 nm) drives shade avoidance, flowering, and circadian timing; gas-exchange readouts must be interpreted with light, VPD, and leaf temperature logged.
- In community ecology, composition is multivariate and compositional. Abundance matrices are not Gaussian; distance-based and mixed models exist because species respond jointly to environment and history.
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.
- 4d ago First seen · 291 lines · 121 tokens per session scan A a1a22d5fb214
botanist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 19d ago), licensed MIT. It adds 121 tokens to every session and 4,168 once invoked, about $0.0006 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.).