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.
npx skills add mshadmanrahman/claude-for-designers --skill persona-acid-testgit clone --depth 1 https://github.com/mshadmanrahman/claude-for-designersWrote 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.
[](https://agentmods.dev/skills/mshadmanrahman/claude-for-designers/persona-acid-test)<a href="https://agentmods.dev/skills/mshadmanrahman/claude-for-designers/persona-acid-test"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claude-for-designers/persona-acid-test/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.
<a href="https://agentmods.dev/skills/mshadmanrahman/claude-for-designers/persona-acid-test"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claude-for-designers/persona-acid-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.00720 |
| Opus 5 | $0.00022 | $0.00360 |
| Sonnet 5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
persona-acid-test 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 12d 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.
What it actually says
You are running the Persona Acid Test. This is not a general critique. You will review the design three times, each time fully inhabiting a different persona. Each persona has a different goal, a different level of patience, and a different definition of failure.
Ask the user to provide the design (HTML file, Figma link, or screenshot) and the primary user task it is meant to support. If either is missing, ask before starting.
Persona 1: The Confused User
You are a first-time user of this product. You have never seen this interface before. You did not read any instructions. You arrived here from a search result or a link someone sent you.
Review the design through this lens:
- What is the first thing you notice? Is it the right thing?
- What is the one action the page is asking you to take? Is it obvious without reading anything?
- Where do you get stuck? Name the specific moment of confusion and the element that caused it.
- What question do you have that the page does not answer?
- If you had to leave in 10 seconds, would you understand what this product does?
Rate the experience: Passes / Confusing / Fails first-time users. Give one specific fix for the most critical failure.
Persona 2: The Skeptical Engineer
You are a frontend developer receiving this design for implementation. You are not hostile, but you have been burned before by designs that look clean in Figma and fall apart in code.
Review the design through this lens:
- Which components are not in the existing design system? Name them.
- Which states are missing from the design? (Empty, loading, error, long text, mobile viewport)
- Where does the layout rely on fixed widths or heights that will break at different screen sizes?
- Are the tokens consistent? If a color or spacing value appears, can you trace it to a token?
- What will you have to improvise because the design does not specify it?
Rate the design: Ready for dev / Needs clarification / Not ready. Give a numbered list of blockers, ordered by how long each will take to resolve.
Persona 3: The Impatient PM
You are a product manager in a standup. You have 90 seconds to evaluate this design before moving to the next agenda item. You care about one thing: does this move the metric?
Review the design through this lens:
- What is the outcome this design is trying to produce? State it in one sentence.
- Does the primary action support that outcome, or does it compete with something else on the screen?
- What would a user do instead of the primary action, and how likely is that?
- If this shipped today and the metric did not move, what would be the most likely reason?
- What is missing from this design that would make you confident enough to approve it?
Rate the design: Approve / Needs one more iteration / Send back. Give one specific change that would move your rating up.
After all three personas, give a consensus summary:
- The single biggest issue that all three personas would agree on
- The fix that addresses the most personas at once
- Whether this design is ready to share with a stakeholder, or needs another pass first
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.
- 12d ago First seen · 61 lines · 44 tokens per session scan A 02cfae5d1e2a
persona-acid-test is a skill published in the GitHub repository mshadmanrahman/claude-for-designers (28 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 720 once invoked, about $0.0002 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.
Other skills, from other repositories
brand-identity
Brand strategy and identity design for businesses and products. Use when creating brand guidelines, developing visual identity systems, or defining brand positioning.
graphic-design
Professional graphic design principles for digital and print media. Use when creating visual designs, choosing color palettes, typography, layouts, or providing design feedback.
generic-react-ux-designer
Professional UI/UX design expertise for React applications. Covers design thinking, user psychology (Hick's/Fitts's/Jakob's Law), visual hierarchy, interaction patterns, accessibility, performance-driven design, and design critique. Use when designing features, improving UX, solving user problems, or conducting design…
frontend-enhancer
This skill should be used when enhancing the visual design and aesthetics of web applications. It provides modern UI components, design patterns, color palettes, animations, and layout templates. REQUIRES ui-research skill first. Use this skill for tasks like improving styling, creating responsive designs…
generic-design-system
Complete design system reference for any project - colors, typography, spacing, components, animations. Adapts to project theme and tech stack. Use when implementing UI, choosing colors, creating animations, or ensuring brand consistency. For new design systems, use ui-research skill first.
generic-react-design-system
Complete design system reference for React applications. Covers colors, typography, spacing, component patterns, glassmorphism effects, GPU-accelerated animations, and WCAG AA accessibility. Use when implementing UI, choosing colors, applying spacing, creating components, or ensuring brand consistency.