paper-trail-audit-sota

paper-trail-audit-sota is a command for Claude Code from roomi-fields/paper-trail. It costs 36 tokens per session (578 once invoked), scanned A, original, MIT.

A bibliography audit command for a SOTA, or state-of-the-art review, which is a summary of existing research on a topic. It checks the references cited in an existing Markdown SOTA file against a registry.

In plain words
What is it for?
Use it to audit cited references and create a Markdown report. With the optional purge setting, it removes citations to retracted references after creating a backup.
Why use it?
It reveals citations that are confirmed, need checking, retracted, inaccessible, unknown, or linked incorrectly. This helps prevent unreliable or broken references from remaining in a research summary.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it to audit cited references and create a Markdown report. With the optional purge setting, it removes citations to retracted references after creating a backup.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-audit-sota"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-audit-sota.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 578 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 $0.00036 $0.00578
Opus 5 $0.00018 $0.00289
Sonnet 5 $0.00007 $0.00116
Haiku 4.5 $0.00004 $0.00058

Measured 12d ago against content hash d97732f434a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

paper-trail-audit-sota 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 12d 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-sota.md · 69 lines

What it actually says

/paper-trail:audit-sota — Audit a SOTA's bibliography

Invoke the sota-auditor skill to audit references cited in an existing SOTA file.

Usage

/paper-trail:audit-sota <path-to-SOTA.md>
/paper-trail:audit-sota <glob-pattern>
/paper-trail:audit-sota <path> --purge      # auto-remove retracted citations

What it does

  1. Reads the SOTA markdown file

  2. Extracts all cited refs via the adapter (wikilinks Obsidian, or markdown links flat)

  3. For each cited ref, looks up the state in the registry

  4. Produces a classification report :

    Cited ref State Status
    arnold_1982_* sota_cited_confirmed OK
    chemillier_2003_* page1_validated TO_VALIDATE (claim audit needed)
    wilson_2021_* retracted HALLUCINATION (to remove)
    unknown_slug (not in registry) UNKNOWN (broken wikilink)
    paywall_2020_* blocked_human:cascade_exhausted INACCESSIBLE
  5. If --purge is set, AUTO-REMOVE the HALLUCINATION wikilinks from the SOTA (in a .bak copy first), and add a note at the bottom of the SOTA listing what was removed

Output

Markdown audit report :

# Audit SOTA — <path>

## Status summary
- OK: N
- TO_VALIDATE: N
- HALLUCINATION: N (purged) or N (action required: remove)
- UNKNOWN: N
- INACCESSIBLE: N

## Details
[Table of all cited refs with their status]

## Required actions
[List of action items for the curator]

Pre-submission

For papers, run /paper-trail:audit-sota on every SOTA cited by the paper, then /paper-trail:audit-article on the paper itself.

Cross-reference

  • /paper-trail:audit-article — per-citation audit (downstream)
  • /paper-trail:cascade <slug> — acquire missing refs
  • /paper-trail:doctor — check registry-level invariants
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. 12d ago First seen · 69 lines · 36 tokens per session scan A d97732f434a5

Subscribe to this mod's changes

paper-trail-audit-sota is a command published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 578 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.