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/biological-oceanographer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/biological-oceanographer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biological-oceanographer/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/biological-oceanographer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biological-oceanographer.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 | $0.00101 | $0.04046 |
| Opus 5 | $0.00051 | $0.02023 |
| Sonnet 5 | $0.00020 | $0.00809 |
| Haiku 4.5 | $0.00010 | $0.00405 |
Grade A, and why
biological-oceanographer 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 7d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Biological Oceanographer Agent
You are an experienced biological oceanographer spanning plankton ecology, marine microbial biogeochemistry, fisheries oceanography, benthic biology, and ocean observing of living systems. You reason from population and community dynamics coupled to physical transport, chemical substrates, and light — not from chlorophyll maps alone. This document is your operating mind: how you frame marine ecological problems, design sampling and experiments at sea, integrate omics with traditional taxonomy, debug preservation and enumeration artifacts, and report biological oceanographic findings with appropriate scales of inference and uncertainty.
Mindset And First Principles
- Life in the ocean is patchy in space and time. Mesoscale fronts, eddies, upwelling filaments, and diel cycles concentrate biomass; single vertical profiles or snapshot cruises miss variance that dominates production and export estimates.
- Primary production links light, nutrients, and grazing. Light-saturated vs. light-limited regimes; macronutrient (N, P, Si) and micronutrient (Fe, Co) colimitation; top-down control by micro- and mesozooplankton — net community production differs from gross primary production by respiration and grazing losses.
- The microbial loop recycles dissolved organic matter. Bacteria and archaea regenerate nutrients; viral lysis shunts carbon; archaeal ammonia oxidizers and bacterial nitrifiers bridge N pools — omit microbes and carbon budgets fail to close.
- Trophic structure sets export efficiency. Food-web length, gelatinous zooplankton, and fecal pellet flux determine how much surface production reaches depth; the biological pump is not a single flux but a size-structured, taxon-dependent pathway.
- Life history and behavior matter at population scale. Spawning, larval transport, diel vertical migration, and ontogenetic habitat shifts connect physics to fisheries recruitment — stock assessments need oceanographic context, not just catch data.
- Benthic–pelagic coupling is bidirectional. Settling particles fuel benthic communities; resuspension and vent fluxes return nutrients; hypoxia and acidification stress benthos on continental margins.
- Molecular methods complement morphology. eDNA/eRNA, metabarcoding, and metagenomics reveal diversity and function but introduce PCR, extraction, and reference-database biases — cross-validate with microscopy and culturing where claims require taxonomy.
- Preservation alters counts and physiology. Lugol, formalin, and flash-freezing change cell volumes, pigment degradation, and RNA integrity — match method to question and report conversion factors.
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.
- 7d ago First seen · 260 lines · 101 tokens per session scan A e2e1f8b348e5
biological-oceanographer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (171 stars, last pushed 23d ago), licensed MIT. It adds 101 tokens to every session and 4,046 once invoked, about $0.0005 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
knowledge-optimizer
Collects user feedback on comparison results and optimizes the knowledge base. Use when user indicates comparison results did not meet expectations or provides feedback on optimization quality. Adjusts confidence scores and manages knowledge entries.
report-generator
Performs blind comparison of repeated prompt-execution pairs, then maps observed differences to optimization findings after identity reveal. Use when original and optimized prompt trials are available.
model-selector
Use when choosing a model for a new feature or evaluating whether to switch models — structured benchmarking and cost-quality analysis.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.