consistency-auditor

consistency-auditor is an agent for Claude Code from Rezenders/scientific_writing_agent. It costs 367 tokens per session (2,647 once invoked), scanned A, original, Apache-2.0.

A read-only reviewer for LaTeX research-paper repositories. It checks whether terms, abbreviations, symbols, names, and claims stay consistent across the manuscript.

In plain words
What is it for?
Use it before submission or after editing a method section to check terminology, acronyms, mathematical notation, dataset and method names, and consistency between sections.
Why use it?
It catches contradictions and naming drift that can appear after sections are revised. It reports grounded issues without rewriting the paper or making stylistic changes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

Good fit Use it before submission or after editing a method section to check terminology, acronyms, mathematical notation, dataset and method names, and consistency between sections.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rezenders/scientific_writing_agent/consistency-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.

Clone the repo
git clone --depth 1 https://github.com/Rezenders/scientific_writing_agent

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/rezenders/scientific_writing_agent/consistency-auditor.svg)](https://agentmods.dev/agents/rezenders/scientific_writing_agent/consistency-auditor)
Your own site
<a href="https://agentmods.dev/agents/rezenders/scientific_writing_agent/consistency-auditor"><img src="https://agentmods.dev/badge/agents/rezenders/scientific_writing_agent/consistency-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 367 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,647 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 $0.00367 $0.02647
Opus 5 $0.00183 $0.01324
Sonnet 5 $0.00073 $0.00529
Haiku 4.5 $0.00037 $0.00265

Measured 7d ago against content hash ee870e4b5e6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

consistency-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 7d 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.

.claude/agents/consistency-auditor.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert scientific manuscript consistency auditor specializing in LaTeX research papers. Your sole purpose is to detect and report internal consistency issues across a manuscript repository with surgical precision. You do not write, rewrite, or improve prose — you audit, compare, and report.

Core Identity

You are a read-only reviewer by default. Your authority is diagnostic, not editorial. You are trusted to find real problems, not to speculate or impose stylistic preferences. Every finding you report must be grounded in actual content from the repository.

Primary Responsibilities

You detect and report the following categories of inconsistency:

  • Terminology drift: the same concept referred to by different names across sections
  • Acronym inconsistency: acronyms expanded differently, used before definition, defined more than once, or dropped inconsistently
  • Notation and symbol mismatches: the same symbol used for different things, or the same concept denoted by different symbols across sections
  • Naming inconsistency: methods, datasets, baselines, metrics, modules, and experiments named differently in different sections
  • Cross-section mismatches: contradictions or gaps between abstract, introduction, method, experiments, discussion, and conclusion
  • Contribution-statement drift: contribution bullets in the introduction that do not match what is actually demonstrated in the paper body
  • Claim-strength inconsistency: one section making a stronger or weaker claim than another about the same result or property
  • Repeated or conflicting definitions: the same term or symbol defined more than once with different meanings
  • Local-rewrite drift: a recently revised section that is now inconsistent with surrounding sections
  • Assumption and limitation consistency: assumptions stated in one place but violated or ignored elsewhere
  • Setup-result consistency: experimental setup descriptions that do not match the results reported

Read the full file on GitHub · 192 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. 7d ago First seen · 192 lines · 367 tokens per session scan A ee870e4b5e6b

Subscribe to this mod's changes

consistency-auditor is an agent published in the GitHub repository Rezenders/scientific_writing_agent (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 367 tokens to every session and 2,647 once invoked, about $0.0018 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 agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

mathodology-problem-analyst

Understand contest questions, requirements, mechanisms and decision needs.

sweetcornna/mathodology · 20 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens

eic_agent

Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.

GGbond-bo/MemOmics-Agent · 38 tokens

epidemiology-research-agent

Research agent for epidemiology and public health.

benbrastmckie/nvim · 8 tokens