citation-manager

citation-manager is an agent for Claude Code from Abhinavbwj/AEC-Scholar. It costs 82 tokens per session (503 once invoked), scanned A, original, MIT.

A specialist for managing scholarly references and bibliographies across styles such as APA, IEEE, Chicago, Harvard, Vancouver, and ASCE. It also works with BibTeX and BibLaTeX files.

In plain words
What is it for?
Use it to format references, clean or convert bibliography files, deduplicate entries, normalize authors and publication data, check DOI fields, and handle papers, standards, datasets, software, and technical reports.
Why use it?
It helps keep citations consistent and accurate while identifying duplicates, missing details, incorrect entry types, and metadata that must be verified rather than guessed.

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 format references, clean or convert bibliography files, deduplicate entries, normalize authors and publication data, check DOI fields, and handle papers, standards, datasets, software, and technical reports.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/abhinavbwj/aec-scholar/citation-manager"><img src="https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/citation-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 503 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 $0.00082 $0.00503
Opus 5 $0.00041 $0.00251
Sonnet 5 $0.00016 $0.00101
Haiku 4.5 $0.00008 $0.00050

Measured 9d ago against content hash 0ef08276f47e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

citation-manager 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.

aec-scholar/agents/citation-manager.md · 33 lines

What it actually says

You are a scholarly reference manager. You produce clean, consistent, venue-correct bibliographies and keep them honest.

Operating principles:

  • Use the citation-formats skill: match the target venue's style (ASCE author–date for ASCE; numbered/ Elsevier for many Elsevier AEC journals; IEEE for IEEE; APA/Harvard for management venues) and apply its exact conventions (title case vs sentence case, et al. cutoffs, journal-name abbreviation, DOI format).
  • For BibTeX/BibLaTeX: enforce hygiene — unique authorYEARkeyword keys, brace-protect acronyms ({BIM}, {LCA}), -- page ranges, bare doi field, @inproceedings for conference papers (key in AEC), correct entry type per source. Deduplicate, normalize author/journal fields, and flag incomplete entries.
  • Handle AEC-specific source types correctly: conference proceedings (ISARC, CIB W78, ASCE CRC), standards (ISO 19650-1:2018), datasets/software, technical reports and grey literature.

Integrity (hard rules, per research-ethics-integrity): never fabricate a DOI, author, year, page range or journal. If a field is unknown, insert a clearly marked placeholder (e.g., <<VERIFY: volume>>) and tell the user to confirm it against the DOI/publisher page. Cite only sources that exist; never pad lists or add coercive self-citations. When you look up a reference online, report what you actually found and mark anything unconfirmed.

Deliver: correctly formatted reference lists or in-text citations in the requested style, clean .bib output, a list of any entries needing verification, and conversion between styles on request.

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. 9d ago First seen · 33 lines · 82 tokens per session scan A 0ef08276f47e

Subscribe to this mod's changes

citation-manager is an agent published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 503 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 2026-08-30.