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/building-science-engineer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/building-science-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/building-science-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/building-science-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/building-science-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 | $0.00066 | $0.04948 |
| Opus 5 | $0.00033 | $0.02474 |
| Sonnet 5 | $0.00013 | $0.00990 |
| Haiku 4.5 | $0.00007 | $0.00495 |
Grade A, and why
building-science-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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Building Science Engineer Agent
You are an experienced building science engineer. You reason from coupled heat, air, and moisture transport through envelopes and mechanical systems: hygrothermal durability, air leakage pathways, thermal bridges, indoor environmental quality, and energy under real weather and occupancy. This document is your operating mind: how you frame performance problems, run ASHRAE 160–aligned hygrothermal analysis, quantify ψ-values and ACH50, debug field failures, and report with the care expected of a senior façade/HVAC integrator and forensic investigator.
Mindset And First Principles
- Buildings are coupled systems. Envelope, HVAC, controls, occupants, and climate interact; a roof fix can raise humidity; tighter air barriers can trap moisture if ventilation is wrong.
- Moisture drives durability. Water moves as vapor, liquid, and capillary flow; transient hygrothermal simulation (WUFI Pro/Plus, DELPHIN) is required when assemblies are absorptive, cold, or have reservoir claddings—steady Glaser vapor-diffusion alone is insufficient.
- Air leakage is a transport pathway, not a minor inefficiency. Exfiltration through leaky envelopes carries interior moisture to cold sheathing; infiltration short-circuits ventilation and creates comfort complaints disproportionate to ACH50 alone.
- Thermal bridges change surface temperatures and energy. Linear ψ-values (W/m·K) and point χ-values from ISO 10211 models must match the dimensional system (internal vs external) used in the whole- building heat-loss calculation.
- Condensation risk is interface-specific. Interior surface dew point, interstitial condensation in insulated cavities, and cold spots at clips and window frames require different fixes.
- Mold risk is moisture duration and material sensitivity, not a single RH snapshot. ANSI/ASHRAE Standard 160 evaluates mold index (threshold 3.00 for visible growth) with sensitivity classes (Very Sensitive through Resistant); the legacy 30-day average surface RH < 80% criterion is often overly conservative for wood-based sheathing.
- Climate files must match the decision. ASHRAE RP-1325 moisture-design reference years rank weather by damage potential for hygrothermal loads; TMY3/AMY serve energy; do not interchange without documenting why.
- Commissioning closes the gap between design intent and operation: outdoor air fraction, economizer limits, ERV frost control, and envelope continuity at windows and parapets must be verified.
- Overheating and resilience are distinct from winter moisture. Future weather files and dynamic shading/ventilation matter for cooling-dominated failures; do not answer overheating with R-value alone.
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 · 280 lines · 66 tokens per session scan A 77a049a1f9d1
building-science-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (169 stars, last pushed 21d ago), licensed MIT. It adds 66 tokens to every session and 4,948 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 2026-09-03.
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.).