cite-check

cite-check is a command for Claude Code from AlterLab-IEU/AlterLab-Academic-Skills. It costs 56 tokens per session (490 once invoked), scanned A, original, MIT.

A command that checks whether references exist in scholarly databases and whether cited sources support the claims made about them. It can inspect BibTeX files, manuscripts, or pasted reference lists and flags retracted or unmatched entries.

In plain words
What is it for?
Use it to audit bibliographies, resolve DOI or arXiv identifiers, check citation-to-claim accuracy, and produce a verdict for each reference.
Why use it?
It helps catch fabricated, incorrect, or misleading citations before they reach a paper or report. This is useful when a reference looks plausible but has not been independently verified.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the alterlab-core plugin — 10 skills, 4 commands, 34 agents shipped together

Good fit Use it to audit bibliographies, resolve DOI or arXiv identifiers, check citation-to-claim accuracy, and produce a verdict for each reference.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alterlab-ieu/alterlab-academic-skills/cite-check
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/AlterLab-IEU/AlterLab-Academic-Skills

Made for: Claude Code.

Or install alterlab-core, the plugin that ships this one along with the rest of its 10 skills, 4 commands, 34 agents.

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 cite-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/alterlab-ieu/alterlab-academic-skills/cite-check/github.svg)](https://agentmods.dev/commands/alterlab-ieu/alterlab-academic-skills/cite-check)
Your own site
<a href="https://agentmods.dev/commands/alterlab-ieu/alterlab-academic-skills/cite-check"><img src="https://agentmods.dev/badge/commands/alterlab-ieu/alterlab-academic-skills/cite-check/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 cite-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/alterlab-ieu/alterlab-academic-skills/cite-check"><img src="https://agentmods.dev/badge/commands/alterlab-ieu/alterlab-academic-skills/cite-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00056 $0.00490
Opus 5 $0.00028 $0.00245
Sonnet 5 $0.00011 $0.00098
Haiku 4.5 $0.00006 $0.00049

Measured 6d ago against content hash 813daf4c6bc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cite-check scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

WebFetch / `requests` / stdlib `urllib`). Match title and authors with the difflib
skills/core/alterlab-citation-verifier/commands/cite-check.md · 34 lines

What it actually says

Cite-check the citations in: $ARGUMENTS

Use the alterlab-citation-verifier skill. This is a deterministic gate, not a vibe check — do not assert that a reference is real because it looks plausible.

Steps:

  1. Collect — Parse the references from $ARGUMENTS (a .bib file, a manuscript path, or a pasted list). If nothing was given, ask for the references or file.
  2. Existence check — Run scripts/verify_citations.py to resolve each reference against Crossref, OpenAlex, Semantic Scholar, and arXiv (keyless public APIs via WebFetch / requests / stdlib urllib). Match title and authors with the difflib SequenceMatcher ratio threshold (≥ 0.70) and resolve any DOI / arXiv ID. Flag anything that matches nothing as likely hallucinated.
  3. Retraction screen — Flag items marked retracted in Crossref (update-to) or OpenAlex (is_retracted).
  4. Claim faithfulness — Where a claim is tied to a citation, check the claim is actually supported by that source and map any mismatch to the TF / PAC / IH / PH / SH taxonomy.
  5. Report — A per-citation table: verdict (verified / unverified / hallucinated / retracted), the resolver that confirmed it, and the matched DOI/ID. Summarize how many of N citations could not be verified.

Degrade gracefully and say so explicitly when the network is unavailable: the script emits unverified verdicts (never a silent pass), and you should fall back to a manual WebSearch pass as the SKILL.md "Graceful Degradation" section describes.

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. 6d ago First seen · 34 lines · 56 tokens per session scan A 813daf4c6bc7

Subscribe to this mod's changes

cite-check is a command published in the GitHub repository AlterLab-IEU/AlterLab-Academic-Skills (66 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 490 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.