citation-forensics

citation-forensics is a skill for Claude Code from wenhaochai/claude-plugins. It costs 193 tokens per session (12,695 once invoked), scanned A, a copy of citation-forensics, MIT.

A tool for checking whether research-paper citations are real, correctly described, and relevant to the claims they support. It examines the source's existence, publication details, and context.

In plain words
What is it for?
Use it to review a paper's bibliography and produce evidence-linked findings without rewriting the paper.
Why use it?
It helps catch made-up references, incorrect publication information, and citations that do not actually support the surrounding text.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the anti-autoresearch plugin — 12 skills shipped together

Good fit Use it to review a paper's bibliography and produce evidence-linked findings without rewriting the paper.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add wenhaochai/claude-plugins
Claude Code
/plugin install anti-autoresearch

Made for: Claude Code.

Or install anti-autoresearch, the plugin that ships this one along with the rest of its 12 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-forensics

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/citation-forensics"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/citation-forensics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,695 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 94% copy Near-identical to another mod 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 $0.00193 $0.12695
Opus 5 $0.00097 $0.06348
Sonnet 5 $0.00039 $0.02539
Haiku 4.5 $0.00019 $0.01269

Measured 9d ago against content hash 57bcfbebb992, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

citation-forensics 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.

Origin

This is a copy

94% identical to citation-forensics — 32 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

anti-autoresearch/skills/citation-forensics/SKILL.md · 797 lines

How it starts

The opening of the file, as written. The whole thing — 797 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Citation Forensics — are the references real and honestly used?

Audit citation integrity for: $ARGUMENTS (requires claims.json from /evidence-ledger; reasons over its type:"citation" claims). Emit span-anchored citation-forensics.findings.json. This skill computes no verdict.

🔒 Do not wrap this skill in /loop, /schedule, or CronCreate. It is verdict-bearing input — it proposes the citation findings the deterministic adjudicator turns into the report. Re-firing it on a wall-clock timer adds no signal: its output changes only when the paper / ledger / bibliography changes, not with the clock, and each run spends real cross-model + lookup budget per cited key. Schedule the external wait that precedes it — bibliography finalized → ledger rebuilt → audit once. (Mirrors ARIS's external-cadence doctrine.)

Adapted from ARIS citation-audit, re-wired onto this repo's evidence ledger and the reviewer≠adjudicator contract, and reframed from "audit + rewrite the bib" to "emit ledger-anchored findings, never touch the paper." Three layers, ported verbatim: existence → metadata → context. Following the repo's baseline-comparison-audit pattern, the executor gathers the canonical facts (DBLP / arXiv / DOI) as neutral evidence; a fresh cross-model reviewer judges existence + metadata + context over those facts. The reviewer never grades — the deterministic adjudicator does.

Why this exists

An autoresearch pipeline (or a rushed human) generates a bibliography in a separate pass from the prose and never reconciles the two. The failure modes are not wildly fake entries — those are easy to spot. The dangerous ones are:

  • Hallucinated reference — no paper exists at the claimed arXiv id / DOI / venue; authors, title, or year are fabricated. (HP-CITE-HALLUC, critical)
  • Metadata drift — a real paper cited with the wrong year, wrong venue (the arXiv preprint number used after the work appeared at CVPR/ICML/NeurIPS, or vice versa), or a v1 title silently merged with a v3 retitle. (HP-CITE-HALLUC, major)
  • Wrong-context citation — a real paper used to support a claim it does not make, or argues against (e.g. citing a self-refinement paper to support "self-feedback yields correlated errors" when the cited paper argues the opposite). (HP-CITE-CONTEXT, major)

Read the full file on GitHub · 797 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. 9d ago First seen · 797 lines · 193 tokens per session scan A 57bcfbebb992

Subscribe to this mod's changes

citation-forensics is a skill published in the GitHub repository wenhaochai/claude-plugins (16 stars, last pushed 9d ago), licensed MIT. It adds 193 tokens to every session and 12,695 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to citation-forensics, differing in 32 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens