ux-case-study

ux-case-study is a command for coding agents from Laith0003/ux-skill. It costs 112 tokens per session (2,791 once invoked), scanned A, original, MIT.

A command for producing a finished project case study in a black-and-white editorial document format. A case study explains a project's problem, solution, and results for readers such as clients or portfolio visitors.

In plain words
What is it for?
Use it after a project or milestone ships to create an HTML, Blade, or Markdown case study.
Why use it?
It turns scattered project facts and retrospective notes into a publishable document with a consistent structure.

Command

Part of the ux-skill plugin — 25 commands, 5 agents 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 commands/laith0003/ux-skill/ux-case-study
Clone the repo
git clone --depth 1 https://github.com/Laith0003/ux-skill

Or install ux-skill, the plugin that ships this one along with the rest of its 25 commands, 5 agents.

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 ux-case-study

README.md
[![agentmods](https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-case-study.svg)](https://agentmods.dev/commands/laith0003/ux-skill/ux-case-study)
Your own site
<a href="https://agentmods.dev/commands/laith0003/ux-skill/ux-case-study"><img src="https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-case-study.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,791 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 $0.00112 $0.02791
Opus 5 $0.00056 $0.01396
Sonnet 5 $0.00022 $0.00558
Haiku 4.5 $0.00011 $0.00279

Measured 5d ago against content hash 4ce0e0568f40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-case-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 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.

commands/ux-case-study.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ux-case-study

You are running the /ux-case-study command from the ux plugin. The job is to produce a project case study as a finished, publishable artifact — pure monochrome editorial typography, hairline separators, numbered section codes, bilingual-safe layout. Not a marketing brochure. A document.

When to use

Triggers: "write a case study", "case study this project", "do the wrap-up doc", "publish this work", "post-launch retrospective", "portfolio piece". Use after a project ships or after a discrete milestone is hit.

Input

Required:

  • Project facts — audience, problem, solution, outcomes, impact, market, target. Pull from .ux/last-frame.json and any other .ux/last-*.json that contain relevant signal. Ask the user for any facts not in state.
  • Output format: HTML / Blade / Markdown. Default: HTML.
  • Output path: default case-studies/<slug>.<ext> in the project root.

Ask once if missing: "Format (HTML / Blade / Markdown) and output path? Or 'defaults' and I'll pick."

Process

1. Gather facts

Walk through state in priority order:

  1. .ux/last-frame.json — audience, problem, brand voice
  2. .ux/last-workshop.json — the Game Plan if a workshop fed this work
  3. .ux/last-research.json — research findings and decisions
  4. .ux/last-design.json / .ux/last-component.json / .ux/last-dashboard.json — what was built
  5. .ux/last-a11y.json / .ux/last-polish.json — quality signals

For anything missing, ask the user in a single round of questions — never piecemeal.

2. Read the style reference

Read references/output/case-study-style.md before writing. Internalize: pure monochrome, numbered section codes A-G, editorial type, hairline separators, two-tone body emphasis, RTL-safe layout.

3. Build the seven sections

Use these exact section codes and headers:

  • (A) About — what is this project, in two sentences. Plain, declarative.
  • (B) Mission — the problem and the position. Why this project exists.
  • (C) Outcomes — what shipped. Specific, dated, with concrete artifacts.
  • (D) Impact — measured change. Numbers if you have them; qualitative observations if not. Never invent metrics.
  • (E) Market — the context. Competitors, adjacent solutions, why the moment is right.
  • (F) Chance — the opportunity that remains. What's next, what's not yet solved.
  • (G) Target Audience — who this is for. Not demographics — behaviors, needs, contexts.

Read the full file on GitHub · 254 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 · 254 lines · 112 tokens per session scan A 4ce0e0568f40

Subscribe to this mod's changes

ux-case-study is a command published in the GitHub repository Laith0003/ux-skill (65 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 2,791 once invoked, about $0.0006 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.