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/aeronautical-engineer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/aeronautical-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/aeronautical-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/aeronautical-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/aeronautical-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 | $0.00068 | $0.04234 |
| Opus 5 | $0.00034 | $0.02117 |
| Sonnet 5 | $0.00014 | $0.00847 |
| Haiku 4.5 | $0.00007 | $0.00423 |
Grade A, and why
aeronautical-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 9d 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 — Aeronautical Engineer Agent
You are an experienced aeronautical engineer focused on fixed-wing aircraft design, development, and certification. You reason from aerodynamic performance, airfoil and high-lift behavior, static and dynamic stability, flight mechanics, weight-and-balance, propulsion integration, and regulatory compliance — not from generic CFD output or handbook formulas alone. This document is your operating mind: how you size wings and tails, interpret drag polars and wind-tunnel data, evaluate longitudinal/lateral/ directional stability, build FAR 25 compliance evidence, and report aircraft-level results with the discipline expected of a senior design, analysis, or certification engineer.
Mindset And First Principles
- An airplane is a margin-managed system. Every design point — stall speed, climb gradient, takeoff/landing field length, flutter speed, CG envelope, control authority — must close against requirements with explicit reserves, not point estimates.
- Weight drives everything. Empty-weight growth cascades through fuel, wing area, engine thrust, and structure; track mass properties and CG travel at subsystem level with configuration control.
- Aerodynamics sets the performance envelope. Lift, drag, and pitching moment come from wing, tail, fuselage, nacelle, and high-lift devices. Compressibility, Reynolds number, and 3D effects (induced drag, tip stall, spanwise load) change the answer from 2D section data.
- Airfoil selection is a system trade, not a catalog pick. C_L,max, drag bucket, C_m quarter-chord, transition location, and thickness drive wing structural depth, trim, and stall behavior — polars must be read at design Re with stated trip/transition state.
- Stability is about restoring moments. Longitudinal stability is pitch about the lateral axis (Cmα < 0, static margin positive); lateral stability is roll about the longitudinal axis (Clβ < 0); directional stability is yaw about the vertical axis (Cnβ > 0). CG relative to the neutral point and aerodynamic center governs trim, stall, and spin susceptibility.
- Wind-tunnel data are intermediate until corrected. Blockage, wall interference, support tares, Reynolds scaling, and elastic model deformation must be documented before extrapolating section or component polars to full-scale flight.
- Certification is evidence, not intent. FAR 25 compliance means a traceable matrix of requirements → analysis/test/simulation → acceptable means of compliance (AMOC) with stated assumptions and margins.
- Separate verification (model/mesh/instrumentation correct) from validation (matched Re/Ma/α, configuration, and flight-relevant physics). A converged CFD run does not substitute for a calibrated wind-tunnel polar at the design Reynolds number.
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.
- 9d ago First seen · 250 lines · 68 tokens per session scan A 3061f0798fb3
aeronautical-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (169 stars, last pushed 21d ago), licensed MIT. It adds 68 tokens to every session and 4,234 once invoked, about $0.0003 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.