normies

normies is a skill for Claude Code from 2389-research/review-squad. It costs 50 tokens per session (1,756 once invoked), scanned A, original, MIT.

A panel of simulated first-time visitors with different levels of technical knowledge who try to understand a website from scratch.

In plain words
What is it for?
Use it to test a website before launch, after a redesign, or whenever you need to understand how experts, beginners, and other visitors experience it.
Why use it?
It reveals confusing language, unclear purpose, frustrating steps, and places where newcomers give up. The focus is on whether real people understand the site, not on code quality or technical compliance.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the review-squad plugin — 4 skills shipped together

Good fit Use it to test a website before launch, after a redesign, or whenever you need to understand how experts, beginners, and other visitors experience it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/2389-research/review-squad/normies
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.

Any agent
npx skills add 2389-research/review-squad --skill normies
Clone the repo
git clone --depth 1 https://github.com/2389-research/review-squad

Made for: Claude Code.

Or install review-squad, the plugin that ships this one along with the rest of its 4 skills.

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 normies

README.md
[![agentmods](https://agentmods.dev/badge/skills/2389-research/review-squad/normies/github.svg)](https://agentmods.dev/skills/2389-research/review-squad/normies)
Your own site
<a href="https://agentmods.dev/skills/2389-research/review-squad/normies"><img src="https://agentmods.dev/badge/skills/2389-research/review-squad/normies/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 normies

Your own site · 80×15
<a href="https://agentmods.dev/skills/2389-research/review-squad/normies"><img src="https://agentmods.dev/badge/skills/2389-research/review-squad/normies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,756 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 $0.00050 $0.01756
Opus 5 $0.00025 $0.00878
Sonnet 5 $0.00010 $0.00351
Haiku 4.5 $0.00005 $0.00176

Measured 10d ago against content hash bd5c60c92b21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

normies 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.

skills/normies/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Normies

Overview

Dispatch a panel of subagents, each role-playing a person with a different level of tech sophistication, who land on a site with zero context. They report what they understand, what confuses them, and where they give up. The organizing principle is the sophistication spectrum — from expert to novice.

This is NOT a technical review. The review-squad:experts skill handles code quality, SEO, accessibility compliance, etc. This skill answers: "Do real people understand my site?"

When to Use

  • Before launch: "Will visitors understand what this is?"
  • After redesign: "Did we make things clearer or more confusing?"
  • New landing page: "Does this page communicate what we want?"
  • Periodic check: "Have we lost sight of the newcomer experience?"

Workflow

digraph normies {
  rankdir=TB;
  "User requests first-time review" -> "Present default persona panel";
  "Present default persona panel" -> "Ask: add, remove, or adjust?";
  "Ask: add, remove, or adjust?" -> "Finalize panel";
  "Finalize panel" -> "Ensure dev server is running";
  "Ensure dev server is running" -> "Dispatch agents sequentially";
  "Dispatch agents sequentially" -> "After each: report key impression";
  "After each: report key impression" -> "All done?";
  "All done?" -> "After each: report key impression" [label="no"];
  "All done?" -> "Compile confusion matrix + recommendations" [label="yes"];
}

Sequential dispatch required. Browser MCP tools share a single browser instance. Agents must run one at a time, not in parallel.

The Default Panel (6 Personas)

Present this spectrum to the user before dispatching. They may adjust.

# Persona Sophistication Patience Gives up after
1 Senior Developer Expert Low — notices every flaw 30 seconds of confusion
2 Product Manager High Medium — goal-oriented, wants to "get it" fast 45 seconds without clarity
3 College Student Medium — digital native, low effort Very low — scrolls fast, judges visually 10 seconds of boredom
4 Small Business Owner Medium — uses web daily, not technical Low — busy, needs answers NOW 60 seconds without finding what they need
5 Retired Teacher Low — reads carefully, confused by jargon High — will try, but gives up when lost 2 minutes of confusion
6 Someone's Grandparent Minimal — icons are meaningless, jargon is alien Very high — wants to understand, easily defeated First moment of real confusion

Read the full file on GitHub · 153 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. 10d ago First seen · 153 lines · 50 tokens per session scan A bd5c60c92b21

Subscribe to this mod's changes

normies is a skill published in the GitHub repository 2389-research/review-squad (12 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 1,756 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

design-integrity-guard

A design review guide for words users or players can see, such as interface labels, system messages, errors, stories, and dialogue. It checks those words against a project's design principles and forbidden patterns.

shihchengwei-lab/separation-and-audit-claude-code · 111 tokens

open-design-landing-deck

OpenDesign's brand-story deck for partners and press: why it exists, what it believes, and where design is going. Built as a decision-grade marketing & GTM deck for partners, press, community.

nexu-io/open-design · 49 tokens

fs-emerald-editorial

OpenDesign's 'design on your desk' brand-launch narrative: the market moment, the story, and the proof that converts. Built as a decision-grade marketing & GTM deck for marketing team, press.

nexu-io/open-design · 49 tokens

huashu-pentagram-grid

OpenDesign's positioning & messaging system: the one-line promise, the pillars, and the proof — the source of truth for all copy. Built as a decision-grade marketing & GTM deck for brand & marketing team.

nexu-io/open-design · 52 tokens

plan

Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request…

jeremylongshore/tons-of-skills-marketplace · 144 tokens

design

Use when the user wants the visual/experiential design of a product done systematically — a design system, a screen, a landing page, or a visual identity — grounded in researched real-world prior art and free of AI slop. Establishes/extends the design system, invokes the matching local taste skill, dispatches the…

jeremylongshore/tons-of-skills-marketplace · 126 tokens