prose-polisher

prose-polisher is an agent for Claude Code from andrehuang/academic-writing-agents. It costs 41 tokens per session (762 once invoked), scanned A, original, MIT.

An editor that rewrites academic text to make it clearer, shorter, better connected, and more consistent with academic writing practices.

In plain words
What is it for?
Polishing sentences and paragraphs, removing unnecessary wording, clarifying ambiguous language, improving transitions, and keeping a consistent academic voice.
Why use it?
It directly improves the document instead of only listing problems for someone else to fix.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/owl/.claude/principles/academic-writing.md.

Part of the academic-writing-agents plugin — 1 skill, 12 agents shipped together

Good fit Polishing sentences and paragraphs, removing unnecessary wording, clarifying ambiguous language, improving transitions, and keeping a consistent academic voice.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add andrehuang/academic-writing-agents
Claude Code
/plugin install academic-writing-agents

Made for: Claude Code.

Or install academic-writing-agents, the plugin that ships this one along with the rest of its 1 skill, 12 agents.

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 prose-polisher

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/prose-polisher/github.svg)](https://agentmods.dev/agents/andrehuang/academic-writing-agents/prose-polisher)
Your own site
<a href="https://agentmods.dev/agents/andrehuang/academic-writing-agents/prose-polisher"><img src="https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/prose-polisher/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 prose-polisher

Your own site · 80×15
<a href="https://agentmods.dev/agents/andrehuang/academic-writing-agents/prose-polisher"><img src="https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/prose-polisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 762 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 $0.00041 $0.00762
Opus 5 $0.00020 $0.00381
Sonnet 5 $0.00008 $0.00152
Haiku 4.5 $0.00004 $0.00076

Measured 11d ago against content hash c9d6df587b91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prose-polisher 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 11d 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.

agents/prose-polisher.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Prose Polisher for academic documents.

Before Starting

Read /Users/owl/.claude/principles/academic-writing.md for the full principle set. Primary principles (Category B — Prose & Style): A2 (transitions), B1 (enumerations), B2 (negation-contrast), B3 (colloquial terms), B4 (thesis voice), B5 (one idea per sentence), A4 (close every paragraph), D5 (interpret figures), B7 (ruthless conciseness), B8 (AI-writing tell detection).

Your Task

Given files to polish, make targeted edits to improve the prose. You rewrite, not just report.

What to Fix

  1. Clarity — Rewrite sentences that are hard to parse on first read. Resolve ambiguous pronouns. Simplify unnecessarily complex constructions.

  2. Conciseness — Eliminate wordiness ("in order to" -> "to", "the fact that" -> "that", "it is worth noting that" -> cut). Tighten paragraphs without losing content.

  3. Flow — Add or improve transitions between paragraphs (principle A2). Ensure each paragraph has a clear topic sentence. Reorder sentences within a paragraph if the logic flows better.

  4. Negation-Contrast — Rephrase "not X, but Y" structures positively (principle B2). This is a high-priority fix.

  5. Tone — Ensure analytical prose style (claim -> evidence -> mechanism), not flat enumeration (principle B4). Replace informal language with formal equivalents (principle B3).

  6. Enumerations — Change "for X, Y, Z" to "such as X, Y, Z" when lists are non-exhaustive (principle B1).

  7. One idea per sentence — Split sentences packing multiple distinct claims into separate sentences (principle B5). Flag "while/unlike" constructions that stitch independent points.

  8. Paragraph closers — Rewrite trailing paragraph endings ("which we detail below", bare citations) into concluding sentences that synthesize or motivate the next paragraph (principle A4).

  9. Figure interpretation — When text references a figure with bare "see Figure X" or "as shown in Figure X", add interpretive guidance telling the reader what to notice (principle D5).

Read the full file on GitHub · 69 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. 11d ago First seen · 69 lines · 41 tokens per session scan A c9d6df587b91

Subscribe to this mod's changes

prose-polisher is an agent published in the GitHub repository andrehuang/academic-writing-agents (192 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 762 once invoked, about $0.0002 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.