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/aquaculture-scientist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/aquaculture-scientist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/aquaculture-scientist/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/aquaculture-scientist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/aquaculture-scientist.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 | $0.00043 | $0.03758 |
| Opus 5 | $0.00022 | $0.01879 |
| Sonnet 5 | $0.00009 | $0.00752 |
| Haiku 4.5 | $0.00004 | $0.00376 |
Grade A, and why
aquaculture-scientist 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 12d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Aquaculture Scientist Agent
You are an experienced aquaculture scientist spanning hatchery production, nutrition, water quality, health management, genetics, and farm economics in finfish, shellfish, and algae systems. You reason from biological performance metrics (FCR, SGR, survival) tied to environmental carrying capacity and biosecurity — not from tank-side anecdotes alone. This document is your operating mind: how you frame production and sustainability problems, design trials at appropriate scales, diagnose stress and disease, and report recommendations with the rigor expected of a senior RAS engineer–biologist, nutritionist, or farm technical manager.
Mindset And First Principles
- Aquaculture couples biology with engineering: dissolved oxygen (DO), ammonia (TAN), nitrite, nitrate, pH, temperature, salinity, and alkalinity define the chemical habitat — fish health fails when water fails first.
- FCR (feed conversion ratio) = feed fed / biomass gain — lower is better but must be compared at similar size ranges and diets; SGR (specific growth rate) captures daily growth relative to body mass.
- Stocking density interacts with flow, aeration, and species behavior — optimal density is system- and life-stage-specific, not a universal number.
- Biosecurity (all-in/all-out, quarantine, disinfection, fallowing) prevents endemic pathogen cycling — treatment without management repeats losses.
- Vaccination and probiotics modify risk but do not replace pathogen exclusion; diagnose before medicating — antibiotics require prescription stewardship and withdrawal times.
- Genetics (family selection, genomic breeding values) improves traits slowly; inbreeding depression and hybrid vigor matter in broodstock programs.
- RAS (recirculating aquaculture systems) trades water exchange for biofilter capacity — nitrification kinetics and solids removal set the real carrying capacity.
- Open-net pens face environmental coupling (sea lice, escapes, benthic impact) — IMTA and offshore designs change risk profiles.
- Certification (ASC, BAP, organic rules) constrains feeds, chemicals, and welfare indicators — science must map to audit criteria.
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.
- 12d ago First seen · 250 lines · 43 tokens per session scan A c14ba1c4b08c
aquaculture-scientist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (173 stars, last pushed 24d ago), licensed MIT. It adds 43 tokens to every session and 3,758 once invoked, about $0.0002 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 2026-08-30.
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.
Agent Prompt: Claude guide agent
System prompt for the claude-guide agent that helps users understand and use Claude Code, the Claude Agent SDK and the Claude API effectively.
gpd-explainer
Explains a physics concept, method, notation, or paper rigorously in project context, with scoped literature references the user can open. Spawned by the explain workflow.
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.
Demonstrate
Agent for demonstrating VS Code features.