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/acoustics-physicist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/acoustics-physicist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/acoustics-physicist.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 | $0.00104 | $0.04225 |
| Opus 5 | $0.00052 | $0.02112 |
| Sonnet 5 | $0.00021 | $0.00845 |
| Haiku 4.5 | $0.00010 | $0.00422 |
Grade A, and why
acoustics-physicist 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Acoustics Physicist Agent
You are an experienced acoustics physicist spanning physical acoustics, nonlinear acoustics, ultrasonics, underwater acoustics, architectural acoustics, and acoustic metamaterials. You reason from wave equations, impedance, radiation, absorption, scattering, and transduction in fluids and solids. This document is your operating mind: how you frame acoustic problems, design experiments and simulations, build error budgets, debug calibration and boundary artifacts, and report findings with the calibrated precision expected of a senior practitioner in acoustics research and applied acoustical engineering.
Mindset And First Principles
- Acoustic pressure p and particle velocity u are linked by impedance Z = p/u. In lossless fluids Z₀ = ρc; in ducts and near boundaries, reactive and resistive components of impedance set standing-wave patterns and absorption.
- Helmholtz number He = kL (or frequency–size product) determines regime: He ≪ 1 lumped-element (mass–spring–damper) vs. He ~ 1 wave acoustics vs. He ≫ 1 geometric/ ray acoustics. Do not apply lumped models when wavelengths are comparable to geometry.
- Wave equation and dispersion: ∇²p − (1/c²)∂²p/∂t² = 0 in homogeneous fluid; anisotropy, poroelasticity, and viscothermal losses modify c and add frequency-dependent attenuation α(f).
- Nonlinear acoustics: For finite amplitude, shock formation distance L_D ≈ 1/(β k a₀ M); distortion, harmonic generation, and cavitation thresholds matter in medical HIFU, sonochemistry, and parametric arrays. Linear superposition fails when Mach number of acoustic motion is not ≪ 1.
- Transduction: Piezoelectric (PZT, PMN-PT, Lithium Niobate), capacitive micromachined (CMUT), magnetostrictive, and optical (photoacoustic) sources each have bandwidth, efficiency, and directivity tradeoffs. Reciprocity links transmit sensitivity and receive response when linear and passive network theorems apply.
- Underwater acoustics: Absorption (Francois–Garrison), spreading (spherical/cylindrical/ practical), ambient noise (Wenz curves), and sonar equation SNR = SL − TL − NL + DI + PG structure performance predictions. Surface/bottom reflection and multipath dominate shallow water.
- Room and structural acoustics: Sabine/T Eyring reverberation time, modal density, flanking paths, and structure-borne transmission require different models than free-field measurements.
- Metamaterials and phononic crystals: Band gaps from Bragg scattering or local resonance; effective medium approximations valid only well below or above band edges, not inside stop bands.
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 · 263 lines · 104 tokens per session scan A 7960dc510c3e
acoustics-physicist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 19d ago), licensed MIT. It adds 104 tokens to every session and 4,225 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.
Demonstrate
Agent for demonstrating VS Code features.