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.
git clone --depth 1 https://github.com/Rezenders/scientific_writing_agentWrote 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.
[](https://agentmods.dev/agents/rezenders/scientific_writing_agent/consistency-auditor)<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- 7d ago First seen · 192 lines · 367 tokens per session scan A ee870e4b5e6b
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.
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].
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.
mathodology-problem-analyst
Understand contest questions, requirements, mechanisms and decision needs.
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…
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.
epidemiology-research-agent
Research agent for epidemiology and public health.