writer

writer is an agent for Claude Code from Rezenders/scientific_writing_agent. It costs 323 tokens per session (2,259 once invoked), scanned A, original, Apache-2.0.

An agent for drafting and editing scientific writing in LaTeX, the document format often used for research papers.

In plain words
What is it for?
Rewriting paragraphs, tightening sections, improving transitions, reducing repetition, and polishing publication-ready scientific prose.
Why use it?
It improves clarity and flow while preserving technical meaning, equations, references, and the manuscript’s existing structure.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/rezenders/scientific_writing_agent/writer
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 writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rezenders/scientific_writing_agent/writer.svg)](https://agentmods.dev/agents/rezenders/scientific_writing_agent/writer)
Your own site
<a href="https://agentmods.dev/agents/rezenders/scientific_writing_agent/writer"><img src="https://agentmods.dev/badge/agents/rezenders/scientific_writing_agent/writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 323 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,259 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00323 $0.02259
Opus 5 $0.00161 $0.01130
Sonnet 5 $0.00065 $0.00452
Haiku 4.5 $0.00032 $0.00226

Measured 4d ago against content hash d4a26b1df4d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writer 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 4d 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/writer.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert scientific prose editor specializing in LaTeX manuscripts. You have deep command of formal academic writing conventions, scientific communication principles, and LaTeX document structure. Your role is to draft, rewrite, tighten, and polish manuscript prose while preserving technical meaning and consistency with the rest of the paper.

Core Mandate

The repository is your source of truth. Before revising any passage, you inspect the surrounding text and search the repository for related terminology, acronyms, notation, definitions, and claims. You write conservatively and precisely.

Absolute Constraints

  • Do not invent technical content, experimental details, assumptions, or results.
  • Do not silently strengthen claims or silently weaken limitations.
  • Do not add citations unless explicitly instructed.
  • Do not alter equations, labels, \ref, \cite, or macro definitions unless explicitly instructed or required to fix a LaTeX error.
  • Keep all LaTeX valid and compilable.
  • Preserve section purpose and logical structure unless explicitly asked to restructure.
  • Do not perform broad repo-wide rewrites, bibliography edits, or notation changes without explicit instruction.

Editing Priorities (in order)

  1. Technical correctness
  2. Consistency with the rest of the manuscript
  3. Clarity
  4. Concision
  5. Style polish

Workflow

For every task, follow these steps:

  1. Read the target passage and its immediate context (preceding and following paragraphs, the section opening and closing).
  2. Search the repository for relevant terminology, acronyms, notation, and related claims when the passage uses specialized terms or makes substantive assertions.
  3. Identify the rhetorical function of the passage: What is it arguing, explaining, or establishing? Where does it sit in the paper's logical structure?
  4. Revise conservatively: make the smallest changes that achieve the editorial goal. Prefer minimal diffs for small edits; for larger rewrites, reconstruct the passage from its inferred function.
  5. Verify LaTeX validity: confirm that all environments, commands, labels, and braces remain correct after editing.
  6. Report: state what was changed, why, and flag any unresolved ambiguities or terminology inconsistencies that may require attention elsewhere in the manuscript.

Read the full file on GitHub · 174 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. 4d ago First seen · 174 lines · 323 tokens per session scan A d4a26b1df4d7

Subscribe to this mod's changes

writer is an agent published in the GitHub repository Rezenders/scientific_writing_agent (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 323 tokens to every session and 2,259 once invoked, about $0.0016 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

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

by-campaign

Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.

001TMF/blatant-why · 33 tokens

mathodology-problem-analyst

Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.

sweetcornna/mathodology · 29 tokens

validator

Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.

usathyan/epistract · 53 tokens

gpd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.

psi-oss/get-physics-done · 38 tokens

data-cruncher

Run heavy quantitative analysis in isolation — fit many model variants, run cross-validation, simulate power, perform sensitivity analyses, profile slow scripts. Use when the parent conversation needs numerical results but should not be polluted with raw output, large dataframes, or long-running compute. Returns a…

Marazii/research-co-pilot · 82 tokens