factcheck

factcheck is a command for coding agents from fcakyon/phd-skills. It costs 28 tokens per session (446 once invoked), scanned A, original, MIT.

A tool for checking research-paper citations and BibTeX records against DBLP and web sources. BibTeX is a file format for storing publication details used by many LaTeX papers.

In plain words
What is it for?
Use it to inspect .bib and .tex files, verify publication metadata, and check specific cited claims, especially numerical ones.
Why use it?
It helps detect incorrect authors, venues, years, titles, and claims that the cited papers do not support.

Command

Part of the phd-skills plugin — 12 skills, 6 commands, 2 agents, 4 hooks 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 commands/fcakyon/phd-skills/factcheck
Clone the repo
git clone --depth 1 https://github.com/fcakyon/phd-skills

Or install phd-skills, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 2 agents, 4 hooks.

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 factcheck

README.md
[![agentmods](https://agentmods.dev/badge/commands/fcakyon/phd-skills/factcheck.svg)](https://agentmods.dev/commands/fcakyon/phd-skills/factcheck)
Your own site
<a href="https://agentmods.dev/commands/fcakyon/phd-skills/factcheck"><img src="https://agentmods.dev/badge/commands/fcakyon/phd-skills/factcheck.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 446 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 $0.00028 $0.00446
Opus 5 $0.00014 $0.00223
Sonnet 5 $0.00006 $0.00089
Haiku 4.5 $0.00003 $0.00045

Measured 4d ago against content hash 7e9d233b04ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

factcheck 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.

plugin/commands/factcheck.md · 58 lines

What it actually says

Citation Fact-Check

You are verifying the accuracy of all citations in a research paper.

Step 1: Find Citation Files

  • Glob for **/*.bib files in the project
  • Read the .bib file(s)
  • Glob for **/*.tex files to find where citations are used

Step 2: BibTeX Metadata Verification

For each BibTeX entry:

  1. Search DBLP for the paper title via web search (query: site:dblp.org "paper title")
  2. Verify:
    • Author names match exactly (spelling, order, completeness)
    • Publication venue is correct (conference name, journal name)
    • Year is the publication year (not submission or preprint year)
    • Paper title matches the published version (not preprint title)
  3. Flag any discrepancies with the corrected values

Step 3: Cited Claims Verification

Search the .tex files for citation patterns (\cite{...}, \citep{...}, \citet{...}).

For each citation that includes a specific claim (especially numerical):

  1. Extract the claim and the cited paper key
  2. Search for the cited paper online
  3. Verify the claim appears in the paper (specific table, figure, or text)
  4. If the claim cannot be verified, suggest qualitative rewording

Step 4: Output

Produce a structured report:

## Citation Verification Report

### BibTeX Corrections Needed
| Key | Field | Current | Correct | Source |
|-----|-------|---------|---------|--------|

### Unverified Claims
| .tex location | Claim | Cited paper | Status | Suggestion |
|--------------|-------|------------|--------|------------|

### Corrected BibTeX Entries
(Ready-to-paste corrected entries for any that need fixing)
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 · 58 lines · 28 tokens per session scan A 7e9d233b04ed

Subscribe to this mod's changes

factcheck is a command published in the GitHub repository fcakyon/phd-skills (382 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 446 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.