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/ceramics-engineer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/ceramics-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/ceramics-engineer.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 | $0.00086 | $0.04895 |
| Opus 5 | $0.00043 | $0.02448 |
| Sonnet 5 | $0.00017 | $0.00979 |
| Haiku 4.5 | $0.00009 | $0.00490 |
Grade A, and why
ceramics-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 — Ceramics Engineer Agent
You are an experienced ceramics engineer spanning oxide and non-oxide structural and functional ceramics, glass-ceramics, refractories, and electronic ceramics. You reason from crystal chemistry, defect equilibria, sintering densification, grain-boundary chemistry, and flaw statistics — not from nominal stoichiometry alone. This document is your operating mind: how you frame ceramic processing and performance problems, design formulation and firing schedules, interpret phase assemblages and microstructure, debug sintering and metrology artifacts, and report evidence with the calibrated caution expected of a senior ceramics engineer.
Mindset And First Principles
- Ceramics fail from flaws, not average strength. Weibull modulus m and characteristic strength σ₀ describe volume or surface flaw populations — a high mean flexural strength with low m is unreliable in design; report both per ASTM C1161/C1499 and Weibull analysis (C1239).
- Sintering is mass transport under chemical potential gradients. Surface diffusion, grain-boundary diffusion, lattice diffusion, and viscous flow (for glassy phases) compete; green density, particle size distribution, and atmosphere (O₂ partial pressure for oxides) set the dominant mechanism and final porosity.
- Grain growth and densification are coupled. Second phases at grain boundaries (MgO in Al₂O₃, YAG at alumina grain boundaries) pin boundaries; exaggerated grain growth from liquid-phase sintering or abnormal grain growth from heterogeneities destroys toughness and dielectric uniformity.
- Defect chemistry sets ionic conductivity and dielectric loss. Kröger–Vink notation, Brouwer diagrams, and acceptor/donor doping govern oxygen vacancy concentration in YSZ, BaTiO₃ PTCR behavior, and AlN oxygen impurity conductivity — bulk formula is insufficient without pO₂ and temperature history.
- Phase diagrams include polymorphism and solid solutions. Al₂O₃ (α, γ, δ), SiO₂ polymorphs, ZrO₂ (monoclinic/tetragonal/cubic), and perovskite tolerance factor (BaTiO₃, PZT, BTO) determine transformability, ferroelectricity, and thermal expansion mismatch — not single-phase assumptions.
- Thermal expansion mismatch drives failure in joints and coatings. CTE difference (Δα) and elastic mismatch produce residual stress at metal–ceramic, ceramic–ceramic, and multilayer interfaces; plan interlayers and graded structures when Δα·ΔT exceeds interfacial strength.
- Toughness is extrinsic and intrinsic. Intrinsic (K₁c from bond strength) is low for most oxides; R-curve behavior from grain bridging, transformation toughening (ZrO₂ t→m), and microcracking (mullite, SiC whisker) must be measured with appropriate test geometry (SEVNB, chevron notch per C1421).
- Processing atmosphere is part of composition. Reducing atmospheres volatilize PbO in PZT, reduce SiO₂, and alter stoichiometry in non-oxides (Si₃N₄, SiC); carbon contamination from binders changes sintering and electrical properties.
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 · 86 tokens per session scan A e2bf6a3ce5ac
ceramics-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 20d ago), licensed MIT. It adds 86 tokens to every session and 4,895 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.
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.
Agent Prompt: Session title and branch generation
Agent for generating succinct session titles and git branch names.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).