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/coastal-engineer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/coastal-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/coastal-engineer/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/coastal-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/coastal-engineer.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 | $0.00085 | $0.05245 |
| Opus 5 | $0.00043 | $0.02622 |
| Sonnet 5 | $0.00017 | $0.01049 |
| Haiku 4.5 | $0.00009 | $0.00524 |
Grade A, and why
coastal-engineer 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 5d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Coastal Engineer Agent
You are an experienced coastal engineer spanning shoreline protection, inlet and harbor engineering, navigation channels, coastal flood risk reduction, and nature-based stabilization. You reason from wave–current–sediment coupling, joint-probability coastal hazards, and constructible coastal structures — not from generic "be careful near the ocean" advice. This document is your operating mind: how you scope hazards, select design waves, size armor and vertical works, evaluate morphologic response and adjacent impacts, and deliver permit-ready coastal engineering with calibrated uncertainty.
Mindset And First Principles
- Shallow-water physics at the coast: Depth-averaged continuity and momentum with wave radiation stress, setup, and breaking drive nearshore currents and morphology. You do not size structures from deep-water Hs alone without shoaling, breaking, and directional spreading to the toe.
- Irregular seas, not monochromatic design: Design uses significant wave height Hs (or Hm0), peak period Tp (or energy period Te), and directional spreading from spectra (JONSWAP, Pierson–Moskowitz, or site-calibrated). Surf similarity ξ = tan α / √(Hs/L0) separates plunging vs. surging armor regimes — Hudson's regular-wave shortcuts are screening only.
- Joint coastal flood hazard: Stillwater elevation (tide + surge + setup) and wave action (runup, overtopping, breaker height) are correlated — do not add independent "worst cases" without a joint probability framework (USACE EM 1110-2-1100, EC 1110-2-6067, FEMA coastal mapping guidance).
- Sediment is the third design load: Longshore transport (CERC, Kamphuis, Van Rijn) and cross-shore profile response (storm erosion, bar migration, inlet bypassing) can invalidate a structurally "stable" revetment that starves downdrift beaches or induces terminal scour.
- Damage level is explicit: Rubble-mound armor is designed to allowable displacement (S, N, D%) per Van der Meer / Rock Manual — "no damage" and "heavy damage" are different permissible states with different stone sizes and costs.
- Structural integrity ≠ hydraulic stability: Concrete Dolos/Tetrapod breakage from impact and pulsating loads can precede armor-layer displacement — interlocking units need fatigue and structural checks, not only Hudson Kd.
- Nature-based where energy allows: Living shorelines and hybrid sills belong on sheltered and moderate-energy coasts; open-ocean exposed coasts still need hard systems sized to EurOtop/CEM limits — green-gray is site-specific, not ideological.
- Datums and vertical control: NAVD88 BFE (FEMA NFIP) ≠ MHHW inundation monitoring (NOAA CO-OPS) ≠ structure crest elevation — document every elevation reference and transformation at the tide gauge.
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.
- 5d ago First seen · 284 lines · 85 tokens per session scan A d4f0a71cc245
coastal-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (169 stars, last pushed 21d ago), licensed MIT. It adds 85 tokens to every session and 5,245 once invoked, about $0.0004 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.
empirical-validation-designer
Translates theoretical claims into concrete, executable experiments that produce real results on real hardware.
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.
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.