study

A command for examining a live webpage, screenshot, or reference site and describing its visual design patterns. It produces a report about layout, typography, colors, imagery, and other design choices.

In plain words
What is it for?
Use it to study a client reference, reverse-engineer a competitor’s appearance, or document the design basis for a new project.
Why use it?
It gives a structured way to understand how a site looks before starting a new design or copying a visual direction. It also helps compare several sites and identify their shared design language.

Command for Codex

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 commands/alwkala/tidyfactor-design/study
Clone the repo
git clone --depth 1 https://github.com/alwkala/tidyfactor-design

Made for: Codex.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,027 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 $0.00000 $0.01027
Opus 5 $0.00000 $0.00513
Sonnet 5 $0.00000 $0.00205
Haiku 4.5 $0.00000 $0.00103

Measured 2d ago against content hash fdd088b1e4d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

study 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 2d 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/skills/tidyfactor-design/references/commands/study.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: study — Design DNA Extraction & Competitive Analysis

Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.

When to use

  • Before starting any new design project (run study → then brief → then init)
  • When reverse-engineering a competitor's design language
  • When a client says "make it feel like [reference]"

Dispatch Steps

  1. Load memory/06-quality-bar.md — anti-slop awareness (so the study doesn't praise AI patterns).
  2. Load memory/01-design-schools.md — classify the reference into a design movement.
  3. Execute the DNA extraction protocol below.
  4. Output a diagnosis report — user decides next step.

DNA Extraction Protocol

Input

One of:

  • Live URL → browse the page, capture computed styles, screenshot sections
  • Screenshot / image → visual analysis only (less precise on exact hex values)
  • Multiple URLs → cross-reference to find the shared design language

Extraction Axes (6 Dimensions)

Axis What to extract How to extract
Macrostructure Section rhythm, hero type, scroll behavior Map each viewport-height section, note sticky/parallax/pinned
Color Anchor Primary, surface, text, accent colors Computed styles from getComputedStyle() on buttons, headers, body, backgrounds — NOT visual guesses from screenshots
Type Pairing Heading family, body family, weight usage <link> and @font-face declarations, NOT visual matching
Spacing System Base unit, scale pattern, section gaps Measure actual padding/margin values on key containers
Motion Register Entrance style, scroll interaction, transition timing Observe scroll behavior, hover states, page transitions
Component DNA Card style, button shape, nav pattern, footer pattern Classify against the catalogs in memory/14-nav-footer-catalog.md

Critical Rules

  • Sample computed styles (actual rendered hex values from buttons, headers, body text) — never guess from a screenshot's visual impression.
  • Extract font family names from <link>/@font-face declarations — never from visual matching.
  • Do NOT extract layout structure — the reference site's section order is not a design token; the engine's layout archetypes (memory/13-layout-archetypes.md) own that decision.
  • Do NOT extract literal copy text — voice rules transfer (tone, banned words), literal sentences don't.

Read the full file on GitHub · 99 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. 2d ago First seen · 99 lines · 0 tokens per session scan A fdd088b1e4d5

Subscribe to this mod's changes

study is a command published in the GitHub repository alwkala/tidyfactor-design (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,027 tokens. 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.