verify-citation

verify-citation is a skill for Claude Code from Mexregkan/claude-for-researchers. It costs 31 tokens per session (724 once invoked), scanned A, original, MIT.

A checking procedure for confirming that a research paper exists in sources such as arXiv, Semantic Scholar, or OpenAlex before citing it. A citation is a reference to published research in a paper or document.

In plain words
What is it for?
Use it before adding a paper reference to a LaTeX, bibliography, or Markdown file, or to check citations from the previous response.
Why use it?
It reduces the risk of adding a citation for a paper that cannot be found or is described incorrectly.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

Good fit Use it before adding a paper reference to a LaTeX, bibliography, or Markdown file, or to check citations from the previous response.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mexregkan/claude-for-researchers/verify-citation
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.

Any agent
npx skills add Mexregkan/claude-for-researchers --skill verify-citation
Clone the repo
git clone --depth 1 https://github.com/Mexregkan/claude-for-researchers

Made for: Claude Code.

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 verify-citation

README.md
[![agentmods](https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/verify-citation/github.svg)](https://agentmods.dev/skills/mexregkan/claude-for-researchers/verify-citation)
Your own site
<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/verify-citation"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/verify-citation/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 verify-citation

Your own site · 80×15
<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/verify-citation"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/verify-citation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 724 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 37
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 38
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00031 $0.00724
Opus 5 $0.00015 $0.00362
Sonnet 5 $0.00006 $0.00145
Haiku 4.5 $0.00003 $0.00072

Measured 12d ago against content hash 047ac53bc2ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

verify-citation 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 12d 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.

starter/.claude/skills/verify-citation/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verify-citation

Verify that a paper exists before writing it as a citation.

Inspired by the citation-verification patterns in flonat/claude-research and Imbad0202/academic-research-skills.

When to use

Run /verify-citation before writing any new citation into a .tex, .bib, or .md file. If the user asks you to "add a reference to X", run this skill first — do not write the citation until verification passes.

Usage

/verify-citation "Author, Title, Year"
/verify-citation "the paper we discussed about spectral geometry"
/verify-citation  (no argument — verify all citations in the last assistant turn)

Steps

Step 1 — Extract the citation. If an argument is given, use it. Otherwise, extract every paper reference from the last assistant turn (titles, author–year pairs, DOIs, arXiv IDs).

Step 2 — Search. For each citation, search at least two of:

  • arXiv: https://arxiv.org/search/?searchtype=all&query=<title+author>
  • Semantic Scholar: https://api.semanticscholar.org/graph/v1/paper/search?query=<title>
  • OpenAlex: https://api.openalex.org/works?search=<title>

Use WebSearch or WebFetch to run the searches.

Step 3 — Report verdict.

Result Action
Found on 2+ sources, title and authors match VERIFIED — write the citation
Found on 1 source, minor title variation LIKELY — note the discrepancy, write with caution
Found on 0 sources, or title/author mismatch UNVERIFIED — do NOT write the citation

For UNVERIFIED: say "I cannot confirm this paper exists. Do you have a DOI or arXiv ID?" Do not invent an alternative. Do not write a citation that cannot be verified.

Step 4 — Write the citation (VERIFIED and LIKELY only). Use the metadata from the verified source (exact title, exact authors, correct year). Never reconstruct citation details from memory — use what the database returned.

Read the full file on GitHub · 78 lines

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. 12d ago First seen · 78 lines · 31 tokens per session scan A 047ac53bc2ce

Subscribe to this mod's changes

verify-citation is a skill published in the GitHub repository Mexregkan/claude-for-researchers (52 stars, last pushed 9d ago), licensed MIT. It adds 31 tokens to every session and 724 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

pre-submission-report

Run the final, comprehensive submission-readiness gate and consolidate all checks into one dated report; citation-integrity-only mode is also supported. Use when a paper and submission package are nearly final. Not for a mid-draft adversarial review; use $review-cluster.

flonat/flonat-research · 59 tokens

proof-readability

Improve the exposition and readability of a mathematical proof already verified as correct without changing its mathematics. Use when polishing a lemma, theorem, proof, or appendix after correctness checks. Not for verifying the proof; use $verify-math.

flonat/flonat-research · 50 tokens

latex

Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality. Use when a .tex source must be built or a concrete compilation failure repaired. Not for corpus-wide build checks, visual polish after a clean build, or creating a project; use $latex-health-check, $latex-polish, or…

flonat/flonat-research · 74 tokens

beamer-deck

Create an academic presentation as a LaTeX Beamer source and reviewed PDF with an original theme. Use when the requested deliverable is a conference, seminar, or lecture deck in Beamer. Not for PowerPoint or RevealJS; use $pptx or $quarto-deck.

flonat/flonat-research · 63 tokens

bib-parse

Extract citations from a PDF and generate a validated .bib file. Use when the user asks to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies referenced works, constructs BibTeX entries, and verifies metadata.

flonat/flonat-research · 54 tokens

computational-experiments

Scaffold, execute, analyse, and publish computational research experiments through a reproducible staged workflow. Use when a research question requires simulations or computational sweeps rather than a one-off script.

flonat/flonat-research · 43 tokens