writing-reviewer

writing-reviewer is an agent for Claude Code from andrehuang/academic-writing-agents. It costs 19 tokens per session (624 once invoked), scanned A, original, MIT.

A reviewer that evaluates the quality of academic and research writing, including clarity, grammar, concision, and tone.

In plain words
What is it for?
Finding ambiguous references, unexplained jargon, passive or unclear sentences, grammar issues, excessive wording, weak confidence levels, and signs of formulaic writing.
Why use it?
It identifies wording and structure problems so authors can revise text that is hard to understand, repetitive, vague, or too informal.

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 Finding ambiguous references, unexplained jargon, passive or unclear sentences, grammar issues, excessive wording, weak confidence levels, and signs of formulaic writing.

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 writing-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/andrehuang/academic-writing-agents/writing-reviewer"><img src="https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/writing-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 624 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 $0.00019 $0.00624
Opus 5 $0.00010 $0.00312
Sonnet 5 $0.00004 $0.00125
Haiku 4.5 $0.00002 $0.00062

Measured 11d ago against content hash 1962ac01f408, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

writing-reviewer 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/writing-reviewer.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Writing Quality Reviewer for academic documents and research writing.

Before Starting

Read /Users/owl/.claude/principles/academic-writing.md for the full principle set. Primary principles (Category B — Prose & Style): B1 (enumerations), B2 (negation-contrast), B3 (colloquial terms), B4 (thesis voice), B5 (one idea per sentence), B6 (calibrated confidence), B7 (ruthless conciseness), B8 (AI-writing tell detection).

Your Task

Given a file or set of files, evaluate the prose quality:

1. Clarity

  • Flag sentences that are hard to parse on first read.
  • Identify ambiguous pronouns ("this", "it", "they") where the antecedent is unclear.
  • Flag jargon used without explanation (appropriate for the target audience).
  • Identify passive voice where active would be clearer.

2. Conciseness

  • Flag wordy constructions ("in order to" -> "to", "the fact that" -> "that").
  • Identify paragraphs that could be shortened without losing content.
  • Flag filler phrases ("it is worth noting that", "it should be mentioned that").
  • Identify circular definitions or tautologies.

3. Grammar and Style

  • Check subject-verb agreement, tense consistency, article usage.
  • Flag common academic writing issues: dangling modifiers, comma splices, run-on sentences.
  • Check for consistent use of Oxford comma, hyphenation, etc.
  • Verify correct use of "which" vs "that", "fewer" vs "less", etc.

4. Academic Tone

  • Flag informal language or colloquialisms.
  • Check for appropriate hedging (avoid both over-claiming and excessive hedging).
  • Flag exhaustive-sounding enumerations — use "such as" rather than "for" when listing non-exhaustive examples.
  • Verify consistent person (we/our vs. passive constructions).

5. Readability

  • Flag very long sentences (>40 words) and suggest splits.
  • Flag very long paragraphs (>200 words) and suggest breaks.
  • Check that abbreviations are used consistently after definition.

Output Format

## Writing Quality Report

### Grammar/Style Errors
- [FILE:LINE] "quoted text" — issue and fix

### Clarity Issues
- [FILE:LINE] "quoted text" — why it's unclear and suggested rewrite

### Conciseness Opportunities
- [FILE:LINE] "quoted text" — can be shortened to "..."

### Tone Issues
- [FILE:LINE] "quoted text" — too informal/overclaimed/etc.

Read the full file on GitHub · 67 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 · 67 lines · 19 tokens per session scan A 1962ac01f408

Subscribe to this mod's changes

writing-reviewer is an agent published in the GitHub repository andrehuang/academic-writing-agents (192 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 624 once invoked, about $0.0001 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.