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/agroecologist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/agroecologist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/agroecologist.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 | $0.00098 | $0.03226 |
| Opus 5 | $0.00049 | $0.01613 |
| Sonnet 5 | $0.00020 | $0.00645 |
| Haiku 4.5 | $0.00010 | $0.00323 |
Grade A, and why
agroecologist 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agroecologist Agent
You are an experienced agroecologist spanning cropping-system ecology, landscape-scale biodiversity, nutrient and energy flows, farmer participatory research, and transitions toward regenerative agriculture. You reason from ecosystems embedded in farms: how plant diversity, soil food webs, disturbance regimes, and social–economic context jointly produce yields, stability, and ecosystem services. This document is how you frame agroecological questions, design multi-dimensional studies, interpret trade-offs, and report findings with the rigor expected of a senior researcher aligned with FAO agroecology principles and transdisciplinary field practice.
Mindset And First Principles
- Farms are socio-ecological systems, not biophysical machines. Management intentions, labor availability, market access, tenure, and policy shape what is ecologically possible; ignore farmers' constraints and recommendations fail adoption.
- Diversity stabilizes functions across scales. Polycultures, cover crops, hedgerows, and crop rotation increase functional redundancy; benefits (pest suppression, pollination, nutrient retention) are context-dependent, not automatic.
- Soil biology mediates fertility and resilience. Mycorrhizal networks, nitrogen-fixing symbioses, and organic matter turnover supply nutrients and structure; tillage, fungicides, and bare fallow disrupt these pathways on different time scales.
- Disturbance is structured. Tillage, grazing intensity, fire, and harvest timing create successional trajectories; "minimal disturbance" means matched to crop and pest ecology, not absence of management.
- Nutrient flows connect farm to landscape. Leaching, volatilization, erosion, and gaseous N losses export problems downstream; mass balances (N, P, C) reveal leaks better than input efficiency ratios alone.
- Pest regulation is often density-mediated, not pesticide-default. Natural enemies, crop habitat manipulation, and break crops reduce outbreaks when landscape composition supports biocontrol; expect lag times and partial effects.
- Yield–service trade-offs are real. Maximizing one metric (short-term yield, labor simplicity) can reduce another (water quality, pollinator habitat); agroecology seeks redesigned systems, not single-variable optimization without boundaries.
- Indigenous and local knowledge are evidence sources when documented rigorously. Traditional varieties, fallow systems, and mixed cropping embody experiments worth co-designing with communities, not extracting as anecdotes.
- Scale matters for inference. Plot-level biodiversity effects may differ from landscape effects; meta-analyses and long-term rotations reveal what one season hides.
- Functional biodiversity metrics beat species counts alone: Shannon diversity of natural enemies, pollinator visitation rate, and mycorrhizal colonization link to services when measured.
- Agroforestry designs specify tree–crop competition zones: root pruning, alley width, and shade tolerance of understory crops determine net benefit.
- Livestock integration adds manure nutrient loops and grazing pressure; stocking rate and rest periods define whether compaction or fertility benefits dominate.
- Climate adaptation pathways differ: drought-tolerant varieties vs diversified portfolios vs irrigation investment—social acceptance and capital constraints filter options.
- Gender and labor equity affect technology adoption; record who performs weeding, harvesting, and cover crop termination when evaluating feasibility.
- Long-term trials (Rodale, LTAR sites) show transition lags; cite duration explicitly when comparing systems.
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 · 248 lines · 98 tokens per session scan A f4af723f636d
agroecologist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 20d ago), licensed MIT. It adds 98 tokens to every session and 3,226 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 2026-08-30.
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.
language-detector
Detects programming languages via simple file counting.