sota-auditor

sota-auditor is a skill for Claude Code from roomi-fields/paper-trail. It costs 195 tokens per session (2,776 once invoked), scanned A, original, MIT.

A final review guide for checking whether references in State-of-the-Art reviews and academic papers are truthful and correctly attributed. It can confirm valid citations, retract fabricated ones, and correct attribution errors.

In plain words
What is it for?
Use it to audit or clean citations, respond to citation-verification findings, confirm a specific claim, retract a fabricated reference, or correct a citation and its supporting record.
Why use it?
It helps catch invented references, false quotations, wrong authors, and claims that do not appear in the cited paper before publication.

Skill 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 or clean citations, respond to citation-verification findings, confirm a specific claim, retract a fabricated reference, or correct a citation and its supporting record.

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

Any agent
npx skills add roomi-fields/paper-trail --skill sota-auditor
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 sota-auditor

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/roomi-fields/paper-trail/sota-auditor"><img src="https://agentmods.dev/badge/skills/roomi-fields/paper-trail/sota-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,776 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 $0.00195 $0.02776
Opus 5 $0.00097 $0.01388
Sonnet 5 $0.00039 $0.00555
Haiku 4.5 $0.00019 $0.00278

Measured 10d ago against content hash 8575e26084bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sota-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 10d 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.

skills/sota-auditor/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill : SOTA Auditor

Why this skill exists

Citation hallucinations in academic publications (fabricated quotes, inverted attributions, misidentified authors) are the failure mode this plugin exists to prevent. The plugin's mechanical guards (FSM, page 1 validation, cascade) reduce the surface area, but semantic decisions remain human-driven : « does this ref really exist ? Is this claim really in this paper ? Is this the right author ? »

sota-auditor is the role that makes those decisions. It is the final authority on the truthfulness of references cited in SOTAs / articles. It can :

  • Confirm a citation (transition page1_validated → sota_cited_confirmed)
  • Retract a fabrication (transition * → retracted with reason)
  • Correct an attribution (modify the SOTA + the ref frontmatter)
  • Rollback a technical transition by pdf-cascade if a homonymy was missed

The supreme rule

For each problematic reference, the decision is binary :

  • VRAI → confirm (correct attribution if needed), transition to sota_cited_confirmed once the specific claim has been validated
  • HALLUCINATION → transition to retracted with mandatory WebSearch documenting the absence (≥ 2 independent sources confirming inexistence or error), then purge the citation from the SOTA(s) where it appears

No grey zone. No "roughly correct that we can rephrase". No "keep it just in case". An unverifiable citation is a research debt that eventually explodes.

When to activate

  • The user asks for an audit of a SOTA or article bibliography
  • pipeline doctor reports invariant violations on cited refs
  • pdf-cascade returned blocked_human:title_mismatch or blocked_human:cascade_exhausted on important refs
  • pipeline events --to retracted lists newly retracted refs
  • Before paper submission (pre-submission audit)
  • The user mentions "vérité", "hallucination", "purger", "retraiter"
  • /paper-trail:audit-sota command is invoked

Worker B transitions the auditor can drive

Read the full file on GitHub · 243 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. 10d ago First seen · 243 lines · 195 tokens per session scan A 8575e26084bb

Subscribe to this mod's changes

sota-auditor is a skill published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 6d ago), licensed MIT. It adds 195 tokens to every session and 2,776 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

draft

Use to produce a first draft, or to revise one from an upstream verdict artifact's open-defect count, emitting a draft@1 artifact. The target node of a bounded back-edge. Single tool. Reusable standalone.

s0912758806p/agentic-sop-to-work · 47 tokens

qiongli

Qiongli version: v1.17.0. Cross-platform academic research workflow for Codex, Claude / Claude Code, and CLI. Use for academic research lifecycle work: paper planning, literature review, paper reading, gap finding, study design, manuscript writing, statistics, analysis code, reproducibility, proofread, rebuttal…

jxpeng98/qiongli · 104 tokens

x-bug2rag

A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.

KtKID/x-dev-pipeline · 255 tokens

x-cr

A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.

KtKID/x-dev-pipeline · 183 tokens

x-spec2

A compact system-design guide for turning vague or cross-module requests into a small, structured specification package. It defines requirements, acceptance scenarios, module boundaries, and—when needed—data flow, state, timing, resources, or recovery design.

KtKID/x-dev-pipeline · 397 tokens

x-adversarial-risk

A focused adversarial review of a software specification. It tries to find small counterexamples that would expose incorrect implementations, such as invalid state changes, crashes, duplicate actions, permission mistakes, or concurrent events.

KtKID/x-dev-pipeline · 85 tokens