verify-citations

verify-citations is a skill for Claude Code from Agentic-Assets/corbis-literature-starter-kit. It costs 26 tokens per session (624 once invoked), scanned A, original, MIT.

A citation-auditing tool for LaTeX papers that checks references against a BibTeX database and online research records. BibTeX is a file format commonly used to store paper details.

In plain words
What is it for?
It is for checking all citations in a paper, or verifying one selected reference, before submission or publication.
Why use it?
It finds citation keys missing from the bibliography and flags reference details that do not match the actual publication.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Part of the corbis-literature-starter-kit plugin — 6 skills, 6 commands, 1 agent, 1 hook, 1 MCP server shipped together

Good fit It is for checking all citations in a paper, or verifying one selected reference, before submission or publication.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentic-assets/corbis-literature-starter-kit/verify-citations
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 Agentic-Assets/corbis-literature-starter-kit --skill verify-citations
Clone the repo
git clone --depth 1 https://github.com/Agentic-Assets/corbis-literature-starter-kit

Made for: Claude Code.

Or install corbis-literature-starter-kit, the plugin that ships this one along with the rest of its 6 skills, 6 commands, 1 agent, 1 hook, 1 MCP server.

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-citations

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentic-assets/corbis-literature-starter-kit/verify-citations/github.svg)](https://agentmods.dev/skills/agentic-assets/corbis-literature-starter-kit/verify-citations)
Your own site
<a href="https://agentmods.dev/skills/agentic-assets/corbis-literature-starter-kit/verify-citations"><img src="https://agentmods.dev/badge/skills/agentic-assets/corbis-literature-starter-kit/verify-citations/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-citations

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentic-assets/corbis-literature-starter-kit/verify-citations"><img src="https://agentmods.dev/badge/skills/agentic-assets/corbis-literature-starter-kit/verify-citations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 624 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 $0.00026 $0.00624
Opus 5 $0.00013 $0.00312
Sonnet 5 $0.00005 $0.00125
Haiku 4.5 $0.00003 $0.00062

Measured 10d ago against content hash b556e10e372c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-citations 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.

.agents/skills/verify-citations/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Citations Skill

Audit citations for correctness. Checks that every \cite{KEY} has a matching BibTeX entry and verifies each entry against online search.

Examples

  • /verify-citations -- auto-detect the .tex and .bib files in the project
  • /verify-citations paper/my_paper.tex -- audit a specific file
  • /verify-citations --key blume1983 -- verify single entry

Workflow

  1. Find the main .tex file: check paper/, latex_template/, then the project root for files containing \documentclass. If multiple candidates exist, ask the user which to audit. Extract all \cite{KEY} and \citep{KEY} commands.

  2. Find the .bib file: check the same directory as the .tex file, then the project root. Read the full BibTeX database.

  3. For each citation key: a. Check KEY exists in .bib -- if missing, flag as MISSING b. Extract: author, title, year, journal from the BibTeX entry c. Use search_papers to verify: "{title}" {first author surname} {year} d. Use get_paper_details to confirm details when a match is found e. Build comparison table:

    Field BibTeX value Search result Match?
    Authors {from .bib} {from search} Y/N/--
    Title ... ... Y/N/--
    Year ... ... Y/N/--
    Journal ... ... Y/N/--

    Use Y = confirmed, N = mismatch, -- = not found in search. CRITICAL: If search returns blank for a field, write "NOT FOUND IN SEARCH" -- NEVER fill from memory.

  4. Classify each citation:

    • OK: ALL fields confirmed
    • PARTIAL: Authors + title confirmed, journal/volume not found
    • MISMATCH: Fields contradict search results
    • UNVERIFIED: Cannot find paper online
    • MISSING: Key in \cite{} but not in .bib
  5. For forthcoming papers: use search_papers with additional queries as fallback to check journal placement

  6. Output verification report:

    Citation Audit: [detected .tex file]
    Total: N citations checked
    OK: X | Partial: Y | Mismatch: Z | Missing: W
    
    --- FLAGGED ENTRIES ---
    [KEY] STATUS: details...
    

Read the full file on GitHub · 57 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. 10d ago First seen · 57 lines · 26 tokens per session scan A b556e10e372c

Subscribe to this mod's changes

verify-citations is a skill published in the GitHub repository Agentic-Assets/corbis-literature-starter-kit (11 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 624 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.

Related

Other skills, from other repositories

fin-viz-launch

A tool for turning research data and a written description into academic charts. It can choose a suitable chart type, create plotting code with matplotlib or seaborn, and save the result as a high-resolution PDF, SVG, or PNG.

csmar432/finai-research · 45 tokens

experiment-design

Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental evaluation strategies. Triggers on phrases like "design ablation", "plan experiment", "what experiments should I run", "baseline comparison", or "experiment matrix".

fcakyon/phd-skills · 57 tokens

paper-verification

Use when the user wants to verify paper claims against code or data, audit numerical accuracy, check formula-code alignment, or validate citation accuracy. Triggers on phrases like "verify claims", "check numbers", "do the numbers match", "formula vs code", "audit the paper", or "cross-check results".

fcakyon/phd-skills · 67 tokens

paper-writing

Use when the user wants to write, structure, or revise academic paper sections, improve notation consistency, or refine figures and tables. Triggers on phrases like "write the abstract", "structure the methods", "improve this section", "notation consistency", "figure refinement", or "paper structure".

fcakyon/phd-skills · 63 tokens

reproduce

End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial official code, missing training scripts, missing hyperparameters, and private datasets via similar-public-dataset substitution. Use when the user asks to reproduce, implement, replicate, or re-run a…

fcakyon/phd-skills · 75 tokens

kami-deck

A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.

nexu-io/open-design · 49 tokens