citation-audit

citation-audit is a skill for Claude Code from Mathews-Tom/armory. It costs 115 tokens per session (2,460 once invoked), scanned A, original, MIT.

A tool for checking whether the sources cited in a research manuscript are real, correctly identified, and accurately represented. It fetches the cited papers and compares them with the manuscript's claims.

In plain words
What is it for?
Use it with LaTeX manuscript files and a BibTeX bibliography to inspect citation contexts, verify sources such as arXiv papers, and suggest metadata or wording corrections.
Why use it?
It catches made-up papers, incorrect author or publication details, dead links, and claims that say the opposite of what the source reports.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the armory plugin — 85 skills shipped together

Good fit Use it with LaTeX manuscript files and a BibTeX bibliography to inspect citation contexts, verify sources such as arXiv papers, and suggest metadata or wording corrections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mathews-tom/armory/citation-audit
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 Mathews-Tom/armory --skill citation-audit
Clone the repo
git clone --depth 1 https://github.com/Mathews-Tom/armory

Made for: Claude Code.

Or install armory, the plugin that ships this one along with the rest of its 85 skills.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/mathews-tom/armory/citation-audit.svg)](https://agentmods.dev/skills/mathews-tom/armory/citation-audit)
Your own site
<a href="https://agentmods.dev/skills/mathews-tom/armory/citation-audit"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/citation-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,460 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: 1 finding, 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 Excessive Agency · line 169
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00115 $0.02460
Opus 5 $0.00057 $0.01230
Sonnet 5 $0.00023 $0.00492
Haiku 4.5 $0.00012 $0.00246

Measured 9d ago against content hash 8e29d32cfb89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

citation-audit 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.

skills/citation-audit/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Citation Audit Skill

Purpose

Verify every citation in a manuscript against its actual source. LLMs hallucinate citations, invent arXiv IDs, misattribute findings, and confuse authors. This skill catches all of that by fetching and reading each cited work.

Why This Exists

LLMs are unreliable with citations in three distinct ways:

  1. Ghost papers — The paper does not exist. Title, authors, or venue are fabricated.
  2. Wrong metadata — The paper exists but the bib entry has the wrong arXiv ID, wrong authors, wrong year, or wrong venue.
  3. Inverted claims — The paper exists and the bib is correct, but the manuscript mischaracterizes what the paper says.

All three are invisible to structural audits (cross-reference checks, compilation tests). They require reading the actual cited work.

Inputs

  • The manuscript .tex file(s)
  • The .bib file
  • Web access (to fetch papers from arXiv, conference sites, URLs)

Execution

Phase 1: Extract citation contexts

For each \citep{}, \citet{}, \cite{} in the manuscript:

  1. Record the bib key
  2. Record the surrounding sentence or paragraph (the claim context)
  3. Classify the claim type:
    • FACTUAL: "X et al. found Y" / "X et al. measured Y"
    • METHODOLOGICAL: "We follow X" / "We use the benchmark from X"
    • POSITIONAL: "Unlike X, we..." / "X does not measure..."
    • PARENTHETICAL: "(X, 2024)" — no specific claim, just a reference
  4. For FACTUAL and POSITIONAL claims, extract the specific assertion the manuscript makes about the cited work

Phase 2: Verify bib entry metadata

For each bib entry, verify against the actual source:

For arXiv papers (eprint field present):

  1. Fetch https://arxiv.org/abs/{eprint_id}
  2. Compare: title, authors, year
  3. If the fetched paper has a DIFFERENT title/authors than the bib entry, this is a WRONG ID or GHOST PAPER

For conference/journal papers (booktitle or journal field):

  1. Search for the paper by title + author on the web
  2. Verify: venue, year, author list
  3. If the paper cannot be found at the stated venue, flag as UNVERIFIABLE or GHOST PAPER

Read the full file on GitHub · 249 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 249 lines · 115 tokens per session scan A 8e29d32cfb89

Subscribe to this mod's changes

citation-audit is a skill published in the GitHub repository Mathews-Tom/armory (316 stars, last pushed 2d ago), licensed MIT. It adds 115 tokens to every session and 2,460 once invoked, about $0.0006 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

openagentskill-registry

Discover, compare, audit, and safely install reusable AI Agent Skills with OpenAgentSkill. Use whenever an agent needs a capability it does not already have, must compare Skill alternatives, or needs evidence before installing third-party instructions.

Leon-Drq/openagentskill · 51 tokens

manager

A session-to-GitHub tracker that creates, updates, and reads issues across repositories, including their labels, parent epics, and project-board placement.

serejaris/personal-corp-os · 63 tokens

weekly-retro

A structured weekly retrospective for a one-person business run with AI agents. It gathers evidence from code, project tools, and canonical business files, then records findings and outcomes.

serejaris/personal-corp-os · 49 tokens

art-director

Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.

serejaris/personal-corp-os · 26 tokens

html-draft

Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on…

serejaris/personal-corp-os · 130 tokens

pm-metrics

A product-metrics review aid that examines trends, unusual changes, possible causes, and recommended actions. It can organize a main product metric into lower-level measures, inspect retention and funnels, read A/B tests, and compare results with goals.

serejaris/personal-corp-os · 160 tokens