consistency-audit

consistency-audit is a skill for Claude Code from wanshuiyin/Anti-Autoresearch. It costs 133 tokens per session (10,604 once invoked), scanned A, original, MIT.

A checker for contradictions inside a research paper, including differences between its summary, methods, tables, results, and appendix. It compares the method described with the method actually evaluated.

In plain words
What is it for?
Use it to review a paper from its PDF, check arithmetic and reported results, and identify mismatches that need human review.
Why use it?
It finds claims, numbers, or experiment descriptions that do not agree within the paper, without requiring outside reference data.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Good fit Use it to review a paper from its PDF, check arithmetic and reported results, and identify mismatches that need human review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wanshuiyin/anti-autoresearch/consistency-audit
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 wanshuiyin/Anti-Autoresearch --skill consistency-audit
Clone the repo
git clone --depth 1 https://github.com/wanshuiyin/Anti-Autoresearch

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 consistency-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/wanshuiyin/anti-autoresearch/consistency-audit/github.svg)](https://agentmods.dev/skills/wanshuiyin/anti-autoresearch/consistency-audit)
Your own site
<a href="https://agentmods.dev/skills/wanshuiyin/anti-autoresearch/consistency-audit"><img src="https://agentmods.dev/badge/skills/wanshuiyin/anti-autoresearch/consistency-audit/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 consistency-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanshuiyin/anti-autoresearch/consistency-audit"><img src="https://agentmods.dev/badge/skills/wanshuiyin/anti-autoresearch/consistency-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,604 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 255
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
How audits are shown
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 $0.00133 $0.10604
Opus 5 $0.00067 $0.05302
Sonnet 5 $0.00027 $0.02121
Haiku 4.5 $0.00013 $0.01060

Measured 12d ago against content hash fb16bc9ad238, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

consistency-audit 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/consistency-audit/SKILL.md · 666 lines

How it starts

The opening of the file, as written. The whole thing — 666 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consistency Audit — the paper vs itself

Audit intra-paper self-consistency for: $ARGUMENTS (requires claims.json from /evidence-ledger). Emit span-anchored consistency-audit.findings.json; the deterministic adjudicator — not this skill — computes the verdict.

🔒 Do not wrap this skill in /loop, /schedule, or CronCreate. It is verdict-bearing input — it proposes the findings the deterministic adjudicator turns into the report. Re-firing it on a wall-clock timer adds no signal: its output changes only when the paper / ledger changes, not with the clock. Schedule the external wait that precedes it — ledger built → audit once. (Mirrors ARIS's external-cadence doctrine.)

The flagship instrument. Internal contradiction is the single most defensible thing you can check on an unknown submission: it needs no external GT, runs at L0 (PDF-only), and is exactly where machine-generated papers crack — they hallucinate local coherence. Recall scales with the ledger: a PDF-text (L0) ledger extracts only number/scope spans, so the table/caption/method-drift checks gain teeth at L1 (LaTeX), where tables and captions are actually extracted. Adapted from ARIS paper-claim-audit, reframed from "paper vs result files" to "paper vs itself." There is no external ground truth in this skill.

Why this exists

An autoresearch pipeline (or rushed human) writes the abstract, the tables, the method section, and the appendix in separate passes and never reconciles them. The result is a paper that disagrees with itself:

  • abstract quotes 85.3% accuracy; the best row of its own Table 2 is 84.7%;
  • "improves by 16%" when 73.1 → 78.0 is +6.7% relative / +4.9 points;
  • "mean over 5 seeds" where the number is the single best seed, and N=3 in the table;
  • method section says "no test-time labels"; the experimental-setup paragraph loads gold labels for calibration;
  • "comprehensive evaluation across diverse benchmarks" on two datasets, one domain.

Read the full file on GitHub · 666 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. 12d ago First seen · 666 lines · 133 tokens per session scan A fb16bc9ad238

Subscribe to this mod's changes

consistency-audit is a skill published in the GitHub repository wanshuiyin/Anti-Autoresearch (153 stars, last pushed 3d ago), licensed MIT. It adds 133 tokens to every session and 10,604 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

codex-autoresearch

Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests repeated measurement with a complete experiment contract.

TheGreenCedar/codex-autoresearch · 55 tokens

replay

Audit a past pruning or approval decision by creating a counterfactual branch from a saved snapshot without mutating the live graph. Use when the user asks what would have happened under another decision, disputes a paused branch, or wants to inspect an earlier checkpoint.

whenpoem/aiscientist · 54 tokens

research-sop

Run an end-to-end, auditable research workflow from question framing through literature, competing hypotheses, experiment selection, implementation, verification, and claim handoff. Use whenever the user asks to investigate, compare, test, validate, or establish an empirical research claim, including when they do not…

whenpoem/aiscientist · 85 tokens

debug-sop

Diagnose errors, failed tests, crashes, hangs, regressions, suspicious outputs, and unexpected experimental results through reproducible hypothesis-driven debugging. Use whenever a script or system behaves incorrectly, even if the user only says it is broken or pastes an error. Respect diagnosis-only requests…

whenpoem/aiscientist · 68 tokens

writeup-sop

Produce or revise research reports, result-bearing Markdown, paper sections, and manuscripts without overstating evidence. Use whenever writing text that reports experimental metrics, statistical conclusions, hypothesis rankings, theorem claims, or research findings. Do not trigger for ordinary README edits…

whenpoem/aiscientist · 67 tokens

preregister

Lock a confirmatory falsification target and its fixed multiple-comparison family before observing the confirmatory result. Use before promoting an exploratory finding to a main claim or whenever several related hypotheses need Bonferroni control. Records metric, threshold, family id/size, correction, and seed budget.

whenpoem/aiscientist · 62 tokens