bibliometric

bibliometric is a command for Claude Code from Abhinavbwj/AEC-Scholar. It costs 18 tokens per session (526 once invoked), scanned A, original, MIT.

A command for planning or running bibliometric analysis, which studies patterns in published research such as citations, keywords, and collaboration.

In plain words
What is it for?
Use it to study the structure, influence, themes, trends, and collaboration patterns of research in architecture, engineering, and construction.
Why use it?
It turns a broad research question into a defined data source, search query, cleaning process, and analysis plan.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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

Good fit Use it to study the structure, influence, themes, trends, and collaboration patterns of research in architecture, engineering, and construction.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/abhinavbwj/aec-scholar/bibliometric
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 bibliometric

README.md
[![agentmods](https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/bibliometric.svg)](https://agentmods.dev/commands/abhinavbwj/aec-scholar/bibliometric)
Your own site
<a href="https://agentmods.dev/commands/abhinavbwj/aec-scholar/bibliometric"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/bibliometric.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 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 $0.00018 $0.00526
Opus 5 $0.00009 $0.00263
Sonnet 5 $0.00004 $0.00105
Haiku 4.5 $0.00002 $0.00053

Measured 8d ago against content hash 6cbe8fb2a704, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bibliometric 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.

aec-scholar/commands/bibliometric.md · 39 lines

What it actually says

Run the bibliometric analysis workflow for: $ARGUMENTS

Engage the bibliometric-analysis skill (and aec-journals/aec-domains for grounding). Delegate interpretation to the aec-domain-expert agent where domain validation is needed.

  1. Frame the question. Is the goal performance analysis (productivity/impact), science mapping (structure/evolution), or both? State what the user wants to learn (foundations? fronts? trends? collaboration gaps?).

  2. Data acquisition protocol. Recommend ONE primary database for the structured analysis (Scopus or Web of Science — explain why they shouldn't be merged for citation data) and an exact query + filters + export format (full records with cited references). Tell the user to record the export date and record count.

  3. Cleaning plan. Specify the data-cleaning steps that make or break credibility: author/affiliation disambiguation and a keyword thesaurus (synonym merges — pull AEC variants from aec-domains).

  4. Analysis design. Choose the analyses to the question: co-citation (intellectual base), bibliographic coupling (research fronts), keyword co-occurrence (themes/trends), co-authorship (collaboration), and thematic evolution/burst detection. Map each to the tool (VOSviewer / CiteSpace / Bibliometrix-biblioshiny) and give concrete steps and key parameters (min. occurrence thresholds, clustering resolution, counting method) — including reproducible R code for Bibliometrix when requested.

  5. Reporting & interpretation. Specify exactly what to report for reproducibility (query, filters, dates, software+version, thresholds, cleaning) and how to turn each network into a written finding (name and explain clusters, identify fragmentation gaps, surface emerging themes, propose a research agenda). Validate clusters against domain knowledge — a cluster the field wouldn't recognize is a cleaning artifact.

If the user provides an exported dataset, analyze it directly (or give precise tool steps) and draft the interpreted results section.

Integrity: never invent counts, clusters or metrics. Bibliometrics is only as good as the documented export and cleaning — insist on transparency.

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. 8d ago First seen · 39 lines · 18 tokens per session scan A 6cbe8fb2a704

Subscribe to this mod's changes

bibliometric is a command published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 526 once invoked, about $0.0001 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.