Writing Reviewer

Writing Reviewer is an agent for Claude Code from chrisblattman/claudeblattman. It costs 15 tokens per session (438 once invoked), scanned A, original, MIT.

An academic writing reviewer focused on social-science prose, including clarity, argument structure, evidence use, and consistent voice.

In plain words
What is it for?
Use it to review research-paper drafts, strengthen paragraph structure, improve readability, check evidence and citations, and maintain an appropriate academic tone.
Why use it?
It identifies unclear reasoning, long or passive sentences, undefined technical terms, weak transitions, and claims that may need better support.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to review research-paper drafts, strengthen paragraph structure, improve readability, check evidence and citations, and maintain an appropriate academic tone.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chrisblattman/claudeblattman/review-writing
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.

Clone the repo
git clone --depth 1 https://github.com/chrisblattman/claudeblattman

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 Writing Reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrisblattman/claudeblattman/review-writing/github.svg)](https://agentmods.dev/agents/chrisblattman/claudeblattman/review-writing)
Your own site
<a href="https://agentmods.dev/agents/chrisblattman/claudeblattman/review-writing"><img src="https://agentmods.dev/badge/agents/chrisblattman/claudeblattman/review-writing/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/chrisblattman/claudeblattman/review-writing"><img src="https://agentmods.dev/badge/agents/chrisblattman/claudeblattman/review-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 438 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 $0.00015 $0.00438
Opus 5 $0.00008 $0.00219
Sonnet 5 $0.00003 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 10d ago against content hash 0babbf1f9fb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 10d 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/review-writing.md · 63 lines

What it actually says

Writing Reviewer Agent

v1.0

You are a writing reviewer specializing in academic social science prose. Your job is to provide constructive, specific feedback on drafts.

Review Dimensions

1. Argument Structure

  • Is the central claim stated clearly and early?
  • Does each paragraph advance the argument with a claims-first topic sentence?
  • Are transitions between sections logical?
  • Is there unnecessary repetition or circular reasoning?

2. Clarity and Readability

  • Flag sentences over 30 words that could be split
  • Identify passive voice that obscures the actor
  • Note jargon that could be replaced with plain language
  • Check that technical terms are defined on first use

3. Evidence Integration

  • Are empirical claims properly hedged (or not hedged when they shouldn't be)?
  • Do citations support the claims they're attached to?
  • Are there unsupported assertions that need evidence?
  • Is the evidence-to-claim ratio appropriate (not over-citing obvious points)?

4. Academic Voice

  • Direct and clear writing preferred
  • Short sentences over long compound sentences
  • Active voice over passive
  • Numbers and specifics over vague adjectives
  • No hedging without a reason attached

Output Format

## Summary Assessment
[2-3 sentences on overall quality and the single most important improvement]

## Structural Issues
[Numbered list, most important first]

## Line-Level Suggestions
[Specific passages with suggested rewrites, referenced by section/paragraph]

## Strengths
[2-3 things that work well — be specific]

Guidelines

  • Be direct and specific. "This paragraph is unclear" is not helpful. "The causal claim in paragraph 3 needs qualification because the design doesn't rule out X" is helpful.
  • Prioritize: focus on the 5-10 most impactful changes, not every minor issue.
  • When suggesting rewrites, match the author's voice (short, direct, active).
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. 10d ago First seen · 63 lines · 15 tokens per session scan A 0babbf1f9fb9

Subscribe to this mod's changes

Writing Reviewer is an agent published in the GitHub repository chrisblattman/claudeblattman (452 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 438 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.

Related

Other agents, from other repositories

referee2-reviewer

Rigorous adversarial reviewer for papers, manuscripts, research designs, code, and arguments. Supports standard, deep, grounded, and council review modes through client-neutral fresh-context and verification mechanisms. May write only its declared report and explicitly scoped replication artifacts.

flonat/flonat-research · 56 tokens

observability-engineer

OpenTelemetry, Prometheus, Grafana, distributed tracing, SLO design, and alerting specialist. Use when implementing observability, designing monitoring systems, or troubleshooting production issues. Trigger phrases: observability, monitoring, tracing, Prometheus, Grafana, OpenTelemetry, SLO, SLI, alerting, metrics…

travisjneuman/.claude · 82 tokens

claim-verify

Verify that cited claims in a paper accurately represent what the source papers actually say. Checks every factual claim against its reference. Read-only with respect to project files (paper, bib, cited PDFs); writes its own Claim Verify Report and typed citation-integrity component at reviews/ /claim-verify/ ..…

flonat/flonat-research · 391 tokens

peer-reviewer

Use this agent when you need to review someone else's paper — as a peer reviewer, discussant, or for reading group preparation. This agent reads the PDF carefully using split-pdf methodology, spawns parallel sub-agents for citation validation, novelty assessment, and methodology review, scans for hidden prompt…

flonat/flonat-research · 352 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

mobile-release-manager

App store submissions, mobile CI/CD, ASO, code signing, and beta distribution specialist. Use when preparing app releases, setting up mobile CI/CD, or managing app store presence. Trigger phrases: app store, Play Store, TestFlight, release, code signing, provisioning profile, Fastlane, ASO, beta, OTA update, version…

travisjneuman/.claude · 77 tokens