What is scientific_writing_agent CLAUDE.md?

Developer instructions for writing a scientific paper in LaTeX, a document system commonly used for research papers. They cover clarity, technical accuracy, terminology, and consistency.

Drafting, editing, and reviewing research manuscripts for journals or conferences.

They help an agent edit the paper without changing its scientific meaning or making the writing inconsistent.

How Rezenders/scientific_writing_agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Rezenders/scientific_writing_agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Rezenders/scientific_writing_agent/main/CLAUDE.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/rezenders/scientific_writing_agent/claude-md/github.svg)](https://agentmods.dev/instructions/rezenders/scientific_writing_agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/rezenders/scientific_writing_agent/claude-md"><img src="https://agentmods.dev/badge/instructions/rezenders/scientific_writing_agent/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/rezenders/scientific_writing_agent/claude-md"><img src="https://agentmods.dev/badge/instructions/rezenders/scientific_writing_agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 730 This file is loaded in full into every session.

When invoked 730 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00730	$0.00730
Opus 5.5	$0.00292	$0.00292
Sonnet 5.5	$0.00146	$0.00146
Haiku 4.5	$0.00073	$0.00073

Measured 17d ago against content hash 9d2fe577bbda, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scientific_writing_agent CLAUDE.md 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 17d 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.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working in this repository. The shared, harness-independent workflow source is .agents/.

Canonical Workflow Layer

.agents/agents/ contains shared agent role instructions.
.agents/skills/ contains shared manuscript workflows.
.agents/context/ contains focused project context templates and project-specific guardrails.
.claude/, .codex/, and .pi/ are adapters only. Preserve harness-specific settings and plugin metadata, but avoid divergent workflow copies.

When updating workflows, edit .agents/ first and then regenerate harness adapters if needed. Avoid symlinks in Overleaf-compatible repositories.

Purpose

This repository is a reusable scientific-writing agent template for LaTeX research papers. Downstream projects should replace placeholders such as <PROJECT_NAME>, <MAIN_TEX>, <SECTION_FILE>, <KEY_MACRO>, <IMPLEMENTATION_REFERENCE>, and <EVALUATION_CLAIM> with paper-specific facts.

The goal is to support technically rigorous, internally consistent, publication-ready scientific manuscripts without changing intended technical meaning.

Human-Controlled Writing Workflow

For substantive drafting or rewriting:

establish an explicit passage contract using .agents/context/passage-contract.md;
optionally create an argument plan;
produce one primary draft;
run read-only diagnostic review when needed;
ask the human to accept, reject, or modify findings;
perform at most one targeted revision from accepted findings;
run final diff, consistency, and build checks.

Reviewer and critic agents diagnose only; they do not rewrite. Do not feed unapproved findings to the writer and do not run automatic repeated critique/rewrite loops.

Editing Priorities

technical correctness;
consistency with the manuscript;
clarity and precision;
concise academic style;
grammar and fluency.

Writing Style

Use formal scientific English, precise terminology, and direct declarative sentences. Prefer “This work proposes X to achieve Y” for contributions and “This work uses X” for tool use. Avoid conversational wording, promotional tone, vague intensifiers, and unnecessary variation. Preserve LaTeX macros, labels, references, citations, equations, and established terminology unless a change is necessary and justified.

Read the full file on GitHub · 61 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.

17d ago Changed · +7 tokens per session 9d2fe577bbda
1mo ago Changed · -183 lines · -1,061 tokens per session scan D → A f0e48465fd2a
2mo ago First seen · 244 lines · 1,784 tokens per session scan D a56b36fe3d82

Subscribe to this mod's changes

scientific_writing_agent CLAUDE.md is an instructions file published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 17d ago), licensed Apache-2.0. It adds 730 tokens to every session, about $0.0029 per session on Opus 5.5. 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.

Scientific Writing and docs

scientific_writing_agent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
scientific_writing_agent CLAUDE.mdRezenders/scientific_writing_agent	Instructions file	14	17d ago	Apache-2.0	A	730	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

scientific_writing_agent: Instructions file for Claude Code