citation-audit

citation-audit is a skill for Claude Code, Codex from seandavi/scriptorium. It costs 42 tokens per session (2,654 once invoked), scanned A, original, MIT.

A report that checks whether the citations already attached to claims in a manuscript actually support those claims.

In plain words
What is it for?
Use it to review citation-to-claim alignment, primary-source versus review-source choices, causal wording, and unsupported assertions in existing manuscript text.
Why use it?
It can reveal unsupported statements, mismatched sources, and claims that say more than the cited evidence allows, without adding or inventing citations.

Skill for Claude CodeCodex

Part of the scriptorium plugin — 16 skills shipped together

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.

agentmods
npx agentmods add skills/seandavi/scriptorium/citation-audit
Any agent
npx skills add seandavi/scriptorium --skill citation-audit
Clone the repo
git clone --depth 1 https://github.com/seandavi/scriptorium

Made for: Claude Code, Codex.

Or install scriptorium, the plugin that ships this one along with the rest of its 16 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/seandavi/scriptorium/citation-audit.svg)](https://agentmods.dev/skills/seandavi/scriptorium/citation-audit)
Your own site
<a href="https://agentmods.dev/skills/seandavi/scriptorium/citation-audit"><img src="https://agentmods.dev/badge/skills/seandavi/scriptorium/citation-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,654 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.02654
Opus 5 $0.00021 $0.01327
Sonnet 5 $0.00008 $0.00531
Haiku 4.5 $0.00004 $0.00265

Measured 4d ago against content hash 8b8c3b0e5ef6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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 · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Citation audit

You are running scriptorium's citation-audit skill. Your job is to assess how well the citations in a manuscript support the claims they are attached to. You are a critique skill, not a generation skill.

Critical constraints — read before doing anything else

  1. Never add, suggest, or invent citations. Not even as a "you might also cite…" recommendation. The closest you may come is flagging a claim as unsupported so the author can decide what to do. Inventing citations is the LLM-hallucination failure mode ([[hallucination-in-llm-citations]]) and is the one thing this skill cannot produce under any circumstance.
  2. Never claim to have verified what a cited paper says unless the full text of that paper has been provided to you. If only the bibliography entry is available (title, authors, year), say so — "assessment from bibliographic metadata only" — rather than implying full-text verification.
  3. Never modify the manuscript text. This skill only emits a markdown report. Any edits to the manuscript are the author's job based on your report.
  4. Output is gradient, not binary. Use supports / partially supports / does not support / cannot determine rather than yes/no. The methodology this grounds in (Greenberg 2009 BMJ; scite.ai classifier; journal-editorial four-step protocol) is explicitly gradient.

Inputs you should expect

The user will provide, or you should ask for:

  • Manuscript text — file path or pasted prose.
  • MANUSCRIPT_STATE.yaml — usually at the manuscript's root. Read it. The core_claims, known_weaknesses, and bibliography.paths fields are load-bearing for this audit.
  • Bibliography file(s) — referenced by MANUSCRIPT_STATE.yaml#bibliography.paths. Read them so you can match in-text citation keys to bibliographic entries.

If MANUSCRIPT_STATE.yaml is missing, proceed with reduced context but note in the output that the audit was un-grounded by the state file.

Read the full file on GitHub · 275 lines

Files

What ships with it

5 files 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. 4d ago First seen · 275 lines · 42 tokens per session scan A 8b8c3b0e5ef6

Subscribe to this mod's changes

citation-audit is a skill published in the GitHub repository seandavi/scriptorium (3 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 2,654 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 2026-08-31.

Related

Other skills, from other repositories

deep-research

Deep research agent that searches academic databases, downloads sources, and produces structured evidence-backed reports. Use when the user asks for deep research, literature review, systematic investigation, or any question requiring multiple sources and synthesis.

foundry-works/foundry-research · 46 tokens

system-info

Probe system resources — CPU, RAM, disk, GPU/CUDA/MPS — and translate findings into experiment design recommendations. Run this at the start of any compute-intensive project.

frankaging/lite-research-agents · 38 tokens

food-analyzer

Analyze food photos, nutrition labels, and ingredient lists. Trigger on food images, nutrition label scans, macro questions, glycemic questions, medication interaction checks, and similar food-analysis requests.

mickpletcher/AI-Skills · 41 tokens

astrophotography-processing

Router for astrophotography processing, troubleshooting, and safe workflow guidance across deep-sky, narrowband, planetary/lunar/solar, Milky Way landscape, comet, and mosaic data.

mickpletcher/AI-Skills · 44 tokens

arxiv-watcher

Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.

frankaging/lite-research-agents · 39 tokens

biopython

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…

K-Dense-AI/scientific-agent-skills · 76 tokens