citation-auditor

citation-auditor is an agent for Claude Code from TaewoooPark/MagLab. It costs 44 tokens per session (549 once invoked), scanned A, original, MIT.

A research-paper checking agent that verifies identifiers and publication details, removes duplicates, checks open-access status, and looks for retractions.

In plain words
What is it for?
Use it to validate candidate papers from a search process, confirm DOI and metadata details, mark retracted papers as failed, and update the evidence matrix.
Why use it?
It helps prevent unreliable or incorrectly identified papers from entering an evidence list.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to validate candidate papers from a search process, confirm DOI and metadata details, mark retracted papers as failed, and update the evidence matrix.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/taewooopark/maglab/citation-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/TaewoooPark/MagLab

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 citation-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/taewooopark/maglab/citation-auditor.svg)](https://agentmods.dev/agents/taewooopark/maglab/citation-auditor)
Your own site
<a href="https://agentmods.dev/agents/taewooopark/maglab/citation-auditor"><img src="https://agentmods.dev/badge/agents/taewooopark/maglab/citation-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 549 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 $0.00044 $0.00549
Opus 5 $0.00022 $0.00275
Sonnet 5 $0.00009 $0.00110
Haiku 4.5 $0.00004 $0.00055

Measured 7d ago against content hash a8c99c5e4055, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

citation-auditor 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 7d 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/citation-auditor.md · 87 lines

What it actually says

Role (single objective ①)

Validate the candidate paper list collected by search-scout for DOI validity, metadata consistency, deduplication, OA status, and retraction. Only papers that pass validation are marked verification_status: "verified" (§14.7·§14.6).

Important: Retracted papers must immediately be marked retraction_status: "retracted" and blocked with verification_status: "failed". Do not guess DOIs.

Input specification (②)

{
  "candidates": [
    {
      "ref_key": "...",
      "title": "...",
      "doi": "...",
      "openalex_id": "...",
      "s2_id": "..."
    }
  ],
  "session_id": "session ID"
}

Output schema (③)

{
  "status": "success | partial | failed",
  "verified": [
    {
      "ref_key": "...",
      "verification_status": "verified",
      "retraction_status": "ok",
      "oa_status": "gold",
      "doi": "10.xxxx/...",
      "notes": ""
    }
  ],
  "blocked": [
    {
      "ref_key": "...",
      "verification_status": "failed",
      "retraction_status": "retracted",
      "reason": "OpenAlex retraction_status=retracted"
    }
  ],
  "warnings": []
}

Tool budget (④)

  • max_turns: 10
  • OpenAlex·CrossRef DOI lookup (via connectors.py)
  • On network failure, retain verification_status: "pending"

Validation procedure (⑤)

  1. Normalise DOI (lowercase, strip prefix)
  2. Deduplicate DOIs (keep one per unique DOI)
  3. Confirm DOI existence via CrossRef
  4. Check retraction_status via OpenAlex
  5. Record OA status

Task boundaries (⑥)

  • Papers without a DOI: verification_status: "pending" (not blocked)
  • Do not guess DOIs — if unclear, set notes: "DOI could not be confirmed"
  • On validation API failure, return partial status
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. 7d ago First seen · 87 lines · 44 tokens per session scan A a8c99c5e4055

Subscribe to this mod's changes

citation-auditor is an agent published in the GitHub repository TaewoooPark/MagLab (11 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 549 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.