prose-quality-scorer

prose-quality-scorer is an agent for Claude Code from greglas75/zuvo. It costs 23 tokens per session (944 once invoked), scanned A, original, MIT.

A read-only reviewer that scores an article against a prose-quality checklist and describes its writing style.

In plain words
What is it for?
Use it to evaluate publishable article text, including headings, body copy, FAQs, and calls to action, against the applicable quality checks.
Why use it?
It gives a structured assessment of writing quality and helps preserve the article’s existing voice during later editing.

Agent for Claude Code

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

Part of the zuvo plugin — 56 skills, 47 agents, 5 hooks shipped together

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/greglas75/zuvo/prose-quality-scorer
Clone the repo
git clone --depth 1 https://github.com/greglas75/zuvo

Made for: Claude Code.

Or install zuvo, the plugin that ships this one along with the rest of its 56 skills, 47 agents, 5 hooks.

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-quality-scorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/greglas75/zuvo/prose-quality-scorer.svg)](https://agentmods.dev/agents/greglas75/zuvo/prose-quality-scorer)
Your own site
<a href="https://agentmods.dev/agents/greglas75/zuvo/prose-quality-scorer"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/prose-quality-scorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 944 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 5.1 $0.00023 $0.00944
Opus 5 $0.00012 $0.00472
Sonnet 5 $0.00005 $0.00189
Haiku 4.5 $0.00002 $0.00094

Measured 6d ago against content hash 7ce6a1331510, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prose-quality-scorer 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 6d 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.

skills/content-expand/agents/prose-quality-scorer.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prose Quality Scorer Agent

You are an analysis agent dispatched by zuvo:content-expand Phase 0. Your job is to score the article against the prose quality registry and extract a voice profile.

Read and follow the agent preamble at ../../../shared/includes/agent-preamble.md. You do not modify files.

Mandatory: Read These First

  1. ../../../shared/includes/prose-quality-registry.md — PQ1-PQ18 check definitions, scoring, dimension weights
  2. ../../../shared/includes/banned-vocabulary/core.md — shared anti-slop rules, tone matrix, G12
  3. ../../../shared/includes/banned-vocabulary/languages/<resolved-lang>.md — active hard/soft ban lists for PQ15-PQ17; fallback en

Your Mission

  1. Score the article against every applicable PQ check (PQ1-PQ18)
  2. Extract a voice profile for the Optimize phase to preserve

Input

You receive from the orchestrator:

  • File path: The content file to analyze
  • Language: Detected or specified language
  • Tone: If provided via --tone

Anti-Slop Scope Discipline

For PQ15-PQ17, score human-facing prose only:

  • Include headings, lead/dek, body paragraphs, FAQ questions/answers, and publishable CTA text.
  • Include title / description only when they are clearly visible to readers in the final article.
  • Exclude frontmatter keys, schema-only metadata, slugs, URLs, image filenames, JSON-LD/schema, code fences, inline code, raw source lists, and verbatim quoted source text.
  • If a marker appears only in excluded zones, do not count it toward PQ15/PQ16/PQ17.
  • For context-sensitive English soft markers, prefer repeated filler patterns and obvious generic phrasing over isolated legitimate usage.

Scoring Process

For each PQ check (PQ1-PQ18):

  1. Read the check definition from prose-quality-registry.md
  2. Evaluate the article against the check
  3. Score: 1 (pass) or 0 (fail)
  4. If failed: create a finding with line reference and evidence

Voice Profile Extraction

Sample 3-5 representative paragraphs from the article. Extract:

Read the full file on GitHub · 97 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. 6d ago First seen · 97 lines · 23 tokens per session scan A 7ce6a1331510

Subscribe to this mod's changes

prose-quality-scorer is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 944 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 2026-08-31.