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 agentmods add commands/datathings/marketplace/frontendgit clone --depth 1 https://github.com/datathings/marketplaceWrote 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/commands/datathings/marketplace/frontend)<a href="https://agentmods.dev/commands/datathings/marketplace/frontend"><img src="https://agentmods.dev/badge/commands/datathings/marketplace/frontend.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.05149 |
| Opus 5 | $0.00022 | $0.02575 |
| Sonnet 5 | $0.00009 | $0.01030 |
| Haiku 4.5 | $0.00004 | $0.00515 |
Grade A, and why
frontend 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Review
Purpose: The single hub for GreyCat web-UI quality — correctness, the one prescribed stack, TypeScript/Lit type safety, Lighthouse performance, LLM-friendly SEO, testing, and common pitfalls. (It absorbs the frontend phases that used to live in the separate typecheck / optimize / coverage commands.)
Companion: for GCL backend quality use /greycat:backend.
Scope — arguments: $ARGUMENTS
Default = everything. No upfront questions — resolve the scope from the arguments above and go.
- Empty → run every lens (the full checklist below).
help→ print the lens table below (keyword + what it covers) and stop — do not run the review.- One or more lens keywords → run only those checklist sections.
- Unknown keyword → print the lens table, point out the bad keyword, and stop.
| Keyword | Lens (checklist §) |
|---|---|
layout |
§1 Layout & config + prescribed-stack presence |
ts |
§2–2c TypeScript quality, codegen freshness, SDK-derived strings |
components |
§3–3e Lit patterns, Web Awesome, theming, icons, dependencies |
init |
§4 Init / login gate |
perf |
§5 Performance |
lighthouse |
§6 Lighthouse audit (auto-skips if prerequisites are missing — see §6) |
seo |
§7 SEO + LLM discoverability |
testing |
§8 Type-check / Vitest / coverage gates |
Example: /greycat:frontend lighthouse seo audits only §6 + §7.
Any lens not run — out of scope or unmet prerequisites — must appear in the Output as SKIPPED: <reason>, never silently omitted (a silent skip reads as "passed").
Read reference/webapp.md for the full prescribed toolchain, layout, and integration contract — this review checks against exactly that, with one deviation: the frontend source dir is frontend/, not app/ (the ~ alias maps to frontend/).
How to run this review — ultrathink + ultracode
Ultrathink (always). Reason deeply about why each rule exists (why shadow DOM, why the init gate, why per-component Web Awesome imports) before flagging — a violation you can't tie to a broken render, a blank page, a 422, or a Lighthouse regression is not a finding.
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.
- 4d ago First seen · 231 lines · 43 tokens per session scan A 0f3f42449bc9
frontend is a command published in the GitHub repository datathings/marketplace (11 stars, last pushed 7d ago), licensed Apache-2.0. It adds 43 tokens to every session and 5,149 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 commands, from other repositories
ux-recommend
The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…
review-css-complexity
Scan codebase for overly complex CSS/styling patterns that should be simplified.
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
polish
Final pre-ship pass — apply all three lenses to fix the target.
colorize
Introduce or rework color strategy.