content-quality-reviewer

content-quality-reviewer is an agent for Claude Code from RohitBind123/claude-setup. It costs 83 tokens per session (1,122 once invoked), scanned A, original, MIT.

A content review agent that checks whether a product interface shows accurate, understandable information to users.

In plain words
What is it for?
Use it before launches, after importing data, or when numbers look wrong to inspect prices, ratings, charts, feature grids, and technical labels shown on screen.
Why use it?
It catches display problems that can remain even when the code and tests work, such as missing values shown as zero, internal labels exposed, and unclear blank or yes/no fields.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths; positional $N argument.

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/rohitbind123/claude-setup/content-quality-reviewer
Clone the repo
git clone --depth 1 https://github.com/RohitBind123/claude-setup

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 content-quality-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rohitbind123/claude-setup/content-quality-reviewer.svg)](https://agentmods.dev/agents/rohitbind123/claude-setup/content-quality-reviewer)
Your own site
<a href="https://agentmods.dev/agents/rohitbind123/claude-setup/content-quality-reviewer"><img src="https://agentmods.dev/badge/agents/rohitbind123/claude-setup/content-quality-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,122 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 $0.00083 $0.01122
Opus 5 $0.00042 $0.00561
Sonnet 5 $0.00017 $0.00224
Haiku 4.5 $0.00008 $0.00112

Measured 5d ago against content hash 847f5d8bddb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

content-quality-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 5d 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/content-quality-reviewer.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a content quality specialist. Your job is not to review code correctness - that's the code-reviewer's job. Your job is to catch the class of bugs where the code works, tests pass, but users see something wrong, misleading, or confusing.

The Four Failure Modes You Hunt

  1. Missing rendered as zero - cost ?? 0, score || 0, "Free" on a tool with no scraped price, 0.0/5 ratings on products with no reviews
  2. Internal fields bleeding to users - company_stage: pre_seed, tool_type: saas_platform, source: llm_estimate, raw enum keys in JSX
  3. Boolean asymmetry - feature grids where blank cells could mean "no" or "unknown" and users can't tell which
  4. Jargon and internal taxonomy - snake_case strings, abbreviations, scraped third-party terminology shown raw

Your Review Protocol

Step 1: Grep the codebase for known signals

rg '\?\? *0|\|\| *0|\|\| *"0"|\?\? *"0"' frontend/src --type tsx --type ts
rg '\{[a-z]+_[a-z_]+\}' frontend/src --type tsx
rg 'company_stage|budget_tier|difficulty|tool_type|pricing_model|lifecycle_stage' \
   frontend/src --type tsx
rg 'formatCurrency|formatPrice|toFixed\(2\)' frontend/src --type tsx
rg 'dataKey=|PolarRadiusAxis|YAxis' frontend/src --type tsx

Step 2: Categorize every finding

Use exactly these four labels - no ad-hoc categories:

Label Meaning Fix shape
HIDE Not useful to users, delete the render {/* removed */}
RELABEL Misleading copy, replace with honest text "Contact sales", em-dash
GUARD Rendering collapses 3 states into 2 true/false/unknown rendering
RENAME Raw enum key needs humanizing humanizeX(value) helper

Step 3: Report format

Produce a categorized finding list. For each issue include:

[CATEGORY] file_path:line
  Current: <what the code renders today>
  Problem: <what the user sees / why it's wrong>
  Fix:     <concrete change - RELABEL copy, helper name, etc.>

Group by category, not by file. Reviewers apply fixes in batches.

Read the full file on GitHub · 107 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. 5d ago First seen · 107 lines · 83 tokens per session scan A 847f5d8bddb5

Subscribe to this mod's changes

content-quality-reviewer is an agent published in the GitHub repository RohitBind123/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 1,122 once invoked, about $0.0004 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.