aer-consistency

aer-consistency is a skill for Claude Code, Codex from brycewang-stanford/AER-Skills. It costs 85 tokens per session (2,571 once invoked), scanned A, original, MIT.

A consistency checker for a nearly finished economics manuscript. It compares claims and references across the abstract, text, tables, figures, and bibliography.

In plain words
What is it for?
Use it after revisions or rerunning results to verify repeated numbers, table and figure references, and matches between in-text citations and the bibliography.
Why use it?
It helps find mismatched numbers, sample sizes, exhibit references, percentage conversions, and citations before editors or reviewers do.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the aer-skills plugin — 15 skills shipped together

Good fit Use it after revisions or rerunning results to verify repeated numbers, table and figure references, and matches between in-text citations and the bibliography.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brycewang-stanford/aer-skills/aer-consistency
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 brycewang-stanford/AER-Skills --skill aer-consistency
Clone the repo
git clone --depth 1 https://github.com/brycewang-stanford/AER-Skills

Made for: Claude Code, Codex.

Or install aer-skills, the plugin that ships this one along with the rest of its 15 skills.

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 aer-consistency

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/brycewang-stanford/aer-skills/aer-consistency"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/aer-skills/aer-consistency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,571 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: 3 findings, up to medium

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 →

  • medium Agent Snooping · line 213
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 215
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Excessive Agency · line 236
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00085 $0.02571
Opus 5 $0.00043 $0.01286
Sonnet 5 $0.00017 $0.00514
Haiku 4.5 $0.00009 $0.00257

Measured 12d ago against content hash fc0eb889ae93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aer-consistency 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit_manuscript.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/aer-consistency/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AER Consistency

Overview

Referees and editors run cheap integrity checks before engaging with ideas: does the abstract's number appear in the tables? Do the Ns add up? Does "Table 4" exist? Does every citation resolve? A single mismatch reframes the entire report from "is this right?" to "what else is wrong?" — and for AI-assisted manuscripts these mismatches are the modal failure, because text and tables are often generated in separate passes.

This skill is the full-manuscript integrity audit. It is mechanical by design: every check below has a yes/no answer obtained by comparing two artifacts, not by judgment. Run it after every revision round, not only before first submission.

When to Use

  • The body sections and exhibits exist and the manuscript is being assembled
  • After an R&R revision, when numbers and exhibit ordering changed
  • Before aer-referee-sim (so the simulated referees attack substance, not typos) and before aer-submission
  • Any time results were re-run — even "tiny" re-runs desynchronize text

Audit 1 — The Headline-Number Register

Build a register of every number that appears more than once in the manuscript, then verify each row against its single source of truth (the table or the replication output):

NUMBER            SOURCE            ABSTRACT  INTRO  RESULTS  CONCL  MATCH
4.2 log points    Tab 3 col 4       yes       yes    yes      yes    OK
s.e. 1.1          Tab 3 col 4       yes       no     yes      no     OK
$84 billion       cited source      no        yes    no       yes    OK
N = 37,824        Tab 1             no        no     yes      no     OK

Rules:

  • Every quoted estimate matches its table to the digit, including the standard error. No re-rounding in prose: if the table says 0.042 (0.011), the text says 4.2, not 4 or 4.20.
  • The abstract, introduction, and conclusion quote the same headline specification. Quoting column 3 in the abstract and column 4 in the intro is a real and common failure.
  • Externally sourced numbers (the hook's "$84 billion") carry a citation at first use, and the same value everywhere.

Read the full file on GitHub · 241 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 241 lines · 85 tokens per session scan A fc0eb889ae93

Subscribe to this mod's changes

aer-consistency is a skill published in the GitHub repository brycewang-stanford/AER-Skills (49 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 2,571 once invoked, about $0.0004 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

data-management-plan

Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data…

pedrohcgs/claude-code-my-workflow · 143 tokens

new-diagram

Scaffold a new TikZ diagram from the snippet gallery with prevention rules pre-applied (explicit node dimensions, coordinate map, directional edge labels). Compiles standalone, invokes tikz-reviewer with citations from tikz-measurement.md, and loops on revisions until APPROVED.

pedrohcgs/claude-code-my-workflow · 60 tokens

food-ppt

Turn a food & nutrition review report, evidence brief, or manuscript into a fully EDITABLE PowerPoint (.pptx) that opens in PowerPoint / Keynote / Google Slides with every title, bullet, table, and figure as a native editable object — nothing flattened to an image. Converts the outputs of food-research…

PangenomeAI/academic-skills-food-nutrition · 208 tokens

agri-ppt

Turn an agricultural-science review report, evidence brief, or manuscript into a fully EDITABLE PowerPoint (.pptx) — every title, bullet, table, and figure a native editable object, nothing flattened to an image. Same machinery as food-ppt, but for agricultural work: converts the outputs of agri-research…

PangenomeAI/academic-skills-food-nutrition · 184 tokens

tikz-figure-review

Review and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered…

shubham0704/claude-skills · 177 tokens

ieee-latex

Compile, diagnose, and fix IEEEtran LaTeX manuscripts for JSAC, TWC, TCOM, WCL, CL, and related IEEE journals: documentclass options, BibTeX/IEEEtran bibliography, undefined citations/refs, overfull hboxes, figure/table placement, algorithm/equation numbering, Index Terms, EDICS, biographies, and final PDF checks. Use…

TenWalk/ieee-skills · 161 tokens