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 TuahaJawaid/looks-expensive --skill looks-expensive-updategit clone --depth 1 https://github.com/TuahaJawaid/looks-expensiveWrote 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/tuahajawaid/looks-expensive/looks-expensive-update)<a href="https://agentmods.dev/skills/tuahajawaid/looks-expensive/looks-expensive-update"><img src="https://agentmods.dev/badge/skills/tuahajawaid/looks-expensive/looks-expensive-update/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/tuahajawaid/looks-expensive/looks-expensive-update"><img src="https://agentmods.dev/badge/skills/tuahajawaid/looks-expensive/looks-expensive-update.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 | $0.00093 | $0.01069 |
| Opus 5 | $0.00046 | $0.00535 |
| Sonnet 5 | $0.00019 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade C, and why
looks-expensive-update scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/TuahaJawaid/looks-expensive/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/TuahaJawaid/looks-expensive/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update /looks-expensive
This skill updates the /looks-expensive design skill to the latest version published at github.com/TuahaJawaid/looks-expensive.
What it does
Runs the official installer script, which:
- Downloads the latest release from GitHub
- Auto-detects which AI tools the user has (Claude Code, Cursor, Codex)
- Updates the skill in each detected tool
- Shows the old → new version per tool
The installer is idempotent — running it when already on the latest version does a clean reinstall, not an error.
How to run
Step 1 — Show the user what you're about to do
Before running anything, tell the user:
- You're going to run the official installer from
raw.githubusercontent.com/TuahaJawaid/looks-expensive/main/install.sh - It will update
/looks-expensiveAND this/looks-expensive-updateskill in every detected AI tool - They'll need to start a new session of their tool for the update to take effect
Step 2 — Optionally check current version first
If the user wants to know what version they currently have before updating:
grep "^version:" ~/.claude/skills/looks-expensive/SKILL.md 2>/dev/null \
| head -1 \
| sed -E 's/version:[[:space:]]*//; s/[[:space:]]*$//'
(Adjust path to ~/.cursor/skills-cursor/looks-expensive/SKILL.md or ~/.codex/skills/looks-expensive/SKILL.md for Cursor or Codex.)
Step 3 — Run the update
curl -fsSL https://raw.githubusercontent.com/TuahaJawaid/looks-expensive/main/install.sh | bash
Step 4 — Show the output
The installer prints which tools were updated and from which version to which version. Relay this to the user verbatim — they want to see the actual version numbers.
After updating
The user must start a NEW session of their AI tool (Claude Code, Cursor, or Codex) for the updated skill to load. Existing sessions have the old skill loaded in memory. Tell them this explicitly — it's the #1 source of "I updated but nothing changed" confusion.
If the update fails
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 · 116 lines · 93 tokens per session scan C b2cce6e4890a
looks-expensive-update is a skill published in the GitHub repository TuahaJawaid/looks-expensive (20 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 1,069 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ui-ux-design-pro
Senior-level UI/UX design expert for building data-driven, premium production interfaces. Use when you need to: 1. Design complex applications (dashboards, SaaS, AI tools) from scratch 2. Generate comprehensive design systems (tokens, palettes, typography) 3. Audit existing UI for quality, accessibility, and "craft"…
user-research-cookiy
End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design, usability studies, participant recruitment…
ban-pattern
A design-system rule for recording interface patterns that should not be used because they make a UI look generic or AI-generated.
reimagine-it-lock
Design DNA capture — extracts palette, type stack, motifs, motion, and 3D signatures from a shipped HTML file and saves them as a reusable reference pack. Use when the user says /reimagine-it lock, "lock this design", "save design DNA", "capture this look", or wants to reuse a shipped design on a different target.…
build-screen
A step-by-step procedure for building one interface screen from a project's existing design contracts. It asks a small number of clarifying questions, creates the screen, and reports what it checked.
design-review
A review procedure for checking an HTML file against the melta UI design system, which is a set of rules for how an interface should look and behave.