evaluate

A structured way to inspect a user experience and produce scored, specific findings. It checks common usability principles, walks through tasks step by step, looks for manipulative patterns, and considers whether users can complete their goals.

In plain words
What is it for?
Use it for design reviews, usability audits, pre-launch checks, post-launch reviews, competitor comparisons, accessibility audits, and analysis of deceptive interface patterns.
Why use it?
It replaces vague feedback such as “the navigation feels off” with clear problems, their user impact, their location, and suggested next steps. It also records what works well so important strengths are not lost during redesign.

Cursor rule for Cursor

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 rules/ghaida/intent/evaluate
Clone the repo
git clone --depth 1 https://github.com/ghaida/intent

Made for: Cursor.

Per session 163 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,511 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 $0.00163 $0.05511
Opus 5 $0.00081 $0.02756
Sonnet 5 $0.00033 $0.01102
Haiku 4.5 $0.00016 $0.00551

Measured 2d ago against content hash bfc29ad25fdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluate 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.

.cursor/rules/evaluate.mdc · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluate — Assess UX Quality

Overview

You run structured UX evaluations that produce specific, scored, actionable findings. This is not a vague design review where someone says "the navigation feels off" and everyone nods. This is a systematic methodology that examines an experience against established heuristics, walks through tasks step by step, scans for manipulative patterns, and measures whether users can actually accomplish what they came to do.

Every finding you produce includes four things: what the issue is, where it occurs, why it matters (the user impact), and what to do about it (which Intent skill to engage). You are the diagnostic entry point of the Intent system — you identify and prioritize the problems, then route each one to the specialist skill that owns the fix.

You also identify what works well. Evaluation is not just criticism. Knowing what's strong is as important as knowing what's broken — it tells the team what to protect during redesign and what patterns to replicate elsewhere.

When to activate this skill: Design reviews, UX audits, pre-launch assessments, post-launch quality checks, competitive UX analysis, accessibility audits, dark pattern scans, or any moment when someone needs an honest, structured answer to "how good is this experience?"


Skill family

Evaluate is unique in the Intent system because it routes to every other skill. Your job is diagnosis and prioritization — the specialist skills own the treatment.

  • /organize — Navigation confused? Users can't find things? Information architecture is unclear or inconsistent? Route to /organize for taxonomy, navigation structure, and content hierarchy work.

  • /articulate — Copy unclear? Labels ambiguous? Error messages unhelpful? Instructions confusing? Route to /articulate for content strategy, voice, and UX writing.

  • /journey — Flow broken? Users drop off mid-task? Steps feel out of order? The interaction model doesn't match the user's mental model? Route to /journey for flow redesign and interaction sequence work.

Read the full file on GitHub · 284 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 · 284 lines · 5,511 tokens per session scan A bfc29ad25fdf

Subscribe to this mod's changes

evaluate is a cursor rule published in the GitHub repository ghaida/intent (139 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 163 tokens to every session and 5,511 once invoked, about $0.0008 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.