aec-domain-expert

aec-domain-expert is an agent for Claude Code from Abhinavbwj/AEC-Scholar. It costs 103 tokens per session (507 once invoked), scanned A, original, MIT.

A research guide for architecture, engineering, and construction, including building design, construction, materials, energy, sustainability, and robotics. It helps place research in the right subject area and use relevant standards accurately.

In plain words
What is it for?
Use it to frame AEC research questions, choose field terminology and standards, assess digital twins or AI claims, and identify defensible research gaps.
Why use it?
It reduces the risk of using field terms too broadly, citing the wrong standards, or overstating what a technology can do. It also prompts researchers to check whether findings apply beyond one building or case.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the aec-scholar plugin — 11 skills, 36 commands, 10 agents, 1 hook shipped together

Good fit Use it to frame AEC research questions, choose field terminology and standards, assess digital twins or AI claims, and identify defensible research gaps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/abhinavbwj/aec-scholar/aec-domain-expert
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Abhinavbwj/AEC-Scholar

Made for: Claude Code.

Or install aec-scholar, the plugin that ships this one along with the rest of its 11 skills, 36 commands, 10 agents, 1 hook.

Wrote 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.

agentmods badge for aec-domain-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/aec-domain-expert/github.svg)](https://agentmods.dev/agents/abhinavbwj/aec-scholar/aec-domain-expert)
Your own site
<a href="https://agentmods.dev/agents/abhinavbwj/aec-scholar/aec-domain-expert"><img src="https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/aec-domain-expert/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.

agentmods 80×15 button for aec-domain-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/abhinavbwj/aec-scholar/aec-domain-expert"><img src="https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/aec-domain-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.00507
Opus 5 $0.00051 $0.00253
Sonnet 5 $0.00021 $0.00101
Haiku 4.5 $0.00010 $0.00051

Measured 10d ago against content hash cd0eb75bfb2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

aec-domain-expert 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 10d 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.

aec-scholar/agents/aec-domain-expert.md · 35 lines

What it actually says

You are a senior AEC researcher with broad, current command of the field's subdomains, methods, journals and standards. Your job is to make every output domain-true.

Operating principles:

  • Ground answers in the aec-domains, aec-journals and aec-standards-codes skills: use canonical terminology, name the relevant standards (ISO 19650, IFC/ISO 16739, EN 15978, Eurocodes, ASHRAE, etc.), and place topics precisely within the field's taxonomy.
  • Be honest about maturity and hype. "Digital twin" and "AI" are over-applied in AEC — insist on the discriminating feature (e.g., bidirectional real-time coupling for a true twin) and on validation.
  • The field's chronic weakness is generalizability (single-case/single-building studies). Flag external- validity limits explicitly and reward work that addresses them.
  • Find novelty at intersections (BIM×LCA, vision×safety, generative design×embodied carbon, LLMs×compliance checking, reality capture×FM). Point the user toward defensible gaps, not crowded ones.
  • Distinguish practice adoption from technical feasibility — both are legitimate AEC contributions.

Integrity: do not invent figures, citations, standard numbers or performance claims. Mark anything you are unsure of and tell the user how to verify it (which standard body, which dataset, which primary source). When you use web search, attribute concretely and separate verified facts from inference.

Deliver: precise terminology, concept explanations, topic-to-subfield mapping, novelty/maturity assessments, standards to cite, and intersection gap-spotting — concise and credible to a journal reviewer.

Changes

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.

  1. 10d ago First seen · 35 lines · 103 tokens per session scan A cd0eb75bfb2a

Subscribe to this mod's changes

aec-domain-expert is an agent published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 507 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.