paper-trail-audit-article

paper-trail-audit-article is a command for Claude Code from roomi-fields/paper-trail. It costs 53 tokens per session (876 once invoked), scanned A, original, MIT.

A command that audits every citation in an academic article against its source PDF and creates a RECEIPTS.md report. It supports LaTeX citations and two common Markdown link formats.

In plain words
What is it for?
Checking article citations, resolving references in a registry, validating source PDFs, and optionally adding warnings to a backup copy of the article.
Why use it?
It helps detect citations that are valid, need adjustment, invalid, or cannot be verified. This makes unsupported or mismatched references easier to find.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the paper-trail plugin — 6 skills, 22 commands, 6 agents, 3 hooks shipped together

Good fit Checking article citations, resolving references in a registry, validating source PDFs, and optionally adding warnings to a backup copy of the article.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/roomi-fields/paper-trail/paper-trail-audit-article
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/roomi-fields/paper-trail

Made for: Claude Code.

Or install paper-trail, the plugin that ships this one along with the rest of its 6 skills, 22 commands, 6 agents, 3 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 paper-trail-audit-article

README.md
[![agentmods](https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-audit-article/github.svg)](https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-audit-article)
Your own site
<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-audit-article"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-audit-article/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 paper-trail-audit-article

Your own site · 80×15
<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-audit-article"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-audit-article.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 876 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 $0.00053 $0.00876
Opus 5 $0.00026 $0.00438
Sonnet 5 $0.00011 $0.00175
Haiku 4.5 $0.00005 $0.00088

Measured 9d ago against content hash 9fe74faccb3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

paper-trail-audit-article 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.

commands/paper-trail-audit-article.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/paper-trail:audit-article — Per-citation audit of an article

Invoke the citation-receipts skill to audit every citation in an academic article file against the actual source PDFs.

Usage

/paper-trail:audit-article <path-to-paper.tex>
/paper-trail:audit-article <path-to-paper.md>
/paper-trail:audit-article <path> --warn       # insert inline warnings in .bak

What it does

  1. Parses citations from the file :
    • LaTeX : \cite{key}, \citep{key}, \citet{key}
    • Markdown : [[slug]] (Obsidian) or [text](refs/slug.md) (flat)
  2. For each citation :
    • Resolves the slug to a ref in the registry
    • If ref isn't sota_cited_confirmed → flag as TO_AUDIT_REF first
    • Reads the PDF (via lib/validate_pdf_content and pdftotext)
    • Invokes claim-checker sub-agent for the specific claim audit
  3. Produces RECEIPTS.md at the same location as the article

Output

RECEIPTS.md format (inspired by James Weatherhead's receipts plugin MIT) :

# RECEIPTS — <article path>

Generated: <ISO timestamp>
Source: <count> citations parsed
Skill: paper-trail/citation-receipts

---

## Citation 1 — [Smith2020] (DOI:10.1234/example)

**Status**: VALID

**Claim in manuscript** (line 42):
> "Smith and Doe proved that X is NP-hard for case Y."

**Source statement** (PDF p.5, §3.2):
> "Theorem 3.2. The problem X is NP-hard for all instances satisfying Y."

**Notes**: Attribution correct, verb « proved » matches the source's
formal theorem statement.

---

## Citation 2 — [Jones2019]

**Status**: INVALID

**Claim in manuscript** (line 78):
> "Jones (2019) showed that Z is decidable in polynomial time."

**Source statement** (PDF p.12):
> "We leave the question of Z's complexity as future work."

**Required correction**: Remove citation or replace with the actual
source proving Z's polynomial decidability.

---

## Recap

| Status | Count |
|---|---|
| VALID | 14 |
| ADJUST | 3 |
| INVALID | 2 |
| UNVERIFIABLE | 1 |

Total: 20 citations audited.

Action required: 6 citations needing rework before submission.

Read the full file on GitHub · 115 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 · 115 lines · 53 tokens per session scan A 9fe74faccb3d

Subscribe to this mod's changes

paper-trail-audit-article is a command published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 876 once invoked, about $0.0003 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.