preview

preview is a cursor rule for Cursor from VoTruongDanh/Skills-Agent. It costs 52 tokens per session (728 once invoked), scanned A, original, MIT.

A rule for showing a proposed result, such as an interface, user flow, copy, or generated content, before building it fully. It includes checks for what is being previewed and how detailed the preview should be.

In plain words
What is it for?
Use it for UI mockups, documentation previews, API-response examples, interaction flows, and other sample outputs that should be reviewed before implementation.
Why use it?
It lets people inspect the expected experience early, when changes are easier to request. It also records project memory about the preview, assumptions, feedback, and decisions.

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/votruongdanh/skills-agent/preview
Clone the repo
git clone --depth 1 https://github.com/VoTruongDanh/Skills-Agent

Made for: Cursor.

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 preview

README.md
[![agentmods](https://agentmods.dev/badge/rules/votruongdanh/skills-agent/preview.svg)](https://agentmods.dev/rules/votruongdanh/skills-agent/preview)
Your own site
<a href="https://agentmods.dev/rules/votruongdanh/skills-agent/preview"><img src="https://agentmods.dev/badge/rules/votruongdanh/skills-agent/preview.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 728 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 $0.00052 $0.00728
Opus 5 $0.00026 $0.00364
Sonnet 5 $0.00010 $0.00146
Haiku 4.5 $0.00005 $0.00073

Measured today against content hash b5274d367f82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

preview 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 today.

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/preview.mdc · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Protocol

START: Read .ai-memory.md from project root. Check UI patterns, design decisions, existing previews, brand guidelines, and user flow notes. END: Update .ai-memory.md using Memory Compaction Rules with: what was previewed, assumptions, feedback, and confirmed decisions.

Goal

Show the user what the result will look or feel like before full implementation.

Agent Routing

  • If previewing UI/UX → read .kiro/skills/agents/agents/frontend-specialist.md and apply its knowledge
  • If previewing documentation → read .kiro/skills/agents/agents/documentation-writer.md and apply its knowledge
  • If previewing API response → read .kiro/skills/agents/agents/backend-specialist.md and apply its knowledge

Socratic Gate

Before previewing, verify:

  1. What artifact is being previewed? (UI, API output, document, flow?)
  2. What level of fidelity is expected? (wireframe, mockup, full sample?)
  3. Any specific requirements or constraints? If any answer is unclear, ASK before proceeding.

Workflow

  1. Read Memory — Load .ai-memory.md for project context and design history.
  2. Infer the artifact being previewed: UI, API output, document, message, workflow, or report.
  3. Produce a faithful mock, sample output, walkthrough, or structured preview.
  4. Highlight assumptions behind the preview.
  5. Identify what could change during implementation.
  6. Update Memory — Save preview details and decisions to .ai-memory.md.

Checklist

  • Artifact type identified

  • Preview is realistic and faithful

  • Assumptions clearly labeled

  • Mock data marked as illustrative

  • Implementation differences noted

  • Memory file updated

  • Clean code chuẩn (Standard clean code applied)

  • Cập nhật đầy đủ tất cả các file liên quan (All related files fully updated)

Rules

  • Keep previews realistic and consistent with the current project.
  • Label illustrative content clearly when it is mock data.
  • Avoid implying broad code changes; if the preview would require major refactor, CALL IT OUT and ASK before implementation.
  • Always read and update the memory file.

Read the full file on GitHub · 63 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. today Changed · +3 lines b5274d367f82
  2. 5d ago First seen · 60 lines · 52 tokens per session scan A 1d488adb596e

Subscribe to this mod's changes

preview is a cursor rule published in the GitHub repository VoTruongDanh/Skills-Agent (2 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 728 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.