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 AndreiBozantan/svelte-axum-template --skill review-frontendgit clone --depth 1 https://github.com/AndreiBozantan/svelte-axum-templateWrote 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/andreibozantan/svelte-axum-template/review-frontend)<a href="https://agentmods.dev/skills/andreibozantan/svelte-axum-template/review-frontend"><img src="https://agentmods.dev/badge/skills/andreibozantan/svelte-axum-template/review-frontend/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/andreibozantan/svelte-axum-template/review-frontend"><img src="https://agentmods.dev/badge/skills/andreibozantan/svelte-axum-template/review-frontend.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 | $0.00062 | $0.01116 |
| Opus 5 | $0.00031 | $0.00558 |
| Sonnet 5 | $0.00012 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
review-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 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Svelte Frontend Code Review
Review from the perspective of a principal engineer with deep expertise in Svelte 5 (runes), TypeScript, browser security, and SPA architecture. Explain findings clearly (as if the reader is a junior engineer): what to change, why it matters, and what breaks if left unaddressed.
0. Problem-Solution Fit
Ensure the code addresses a real issue or feature, not hypothetical future needs. Flag speculative abstractions, premature generalization, and unneeded indirection. Prefer the simplest design that solves the problem.
1. Project Standards
API Access: All backend calls must go through the generated client (api.<tag>.<operation>(...) from $lib/generated/endpoints.ts). Flag raw fetch() calls outside lib/fetch.ts and hand-written request/response types that duplicate generated ones.
Generated Code: Files under src/lib/generated/ must never be hand-edited. If they changed without a matching openapi.json change, flag it.
State: Shared app state lives in AppState.svelte.ts using rune-based class fields ($state, $derived) with small setter methods. New global state should follow this pattern, not ad-hoc module-level variables or legacy stores.
Formatting & Checks: Code must pass cargo -q xtask check frontend. Flag any casts, @ts-ignore, and disabled lint rules without justification.
2. Svelte 5 Correctness
Runes: Use $state/$derived/$effect (no legacy $: reactive statements or svelte/store for new code). Derived values must use $derived, not manual synchronization in $effect.
Effects: $effect is a last resort — flag effects that merely compute state (use $derived), and effects missing cleanup for timers, subscriptions, or event listeners.
Reactivity Pitfalls: Watch for destructuring that breaks reactivity, stale closures in async callbacks, and mutation of non-reactive objects expected to trigger updates.
Async UI State: Every async operation needs loading and error states. Check for race conditions when a component fires overlapping requests (e.g., stale response overwriting newer state).
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 · 86 lines · 62 tokens per session scan A 175545242d49
review-frontend is a skill published in the GitHub repository AndreiBozantan/svelte-axum-template (2 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,116 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.
Other skills, from other repositories
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.
frontend-code-doctor
A front-end code review procedure for uni-app, Vue 3, React, and TypeScript projects. It checks code for correctness, security, speed, translation support, and accessibility, meaning whether people with disabilities can use it.
wot-ui-v2
A reference guide for using Wot UI v2, a component library for uni-app and Vue 3 applications. It covers components, forms, themes, feedback dialogs, and common usage problems.
nuxt-data-audit
An audit guide for checking how Nuxt projects load data and whether their data-fetching patterns follow the project's performance rules.
nuxt-content
Build typed, content-driven Nuxt applications with @nuxt/content. Use when working with content.config.ts, collections, queryCollection, Markdown or MDC rendering, content databases, hooks, custom sources, search, or Content v2 migrations.
nuxt-modules
Use when creating Nuxt modules: (1) Published npm modules (@nuxtjs/, nuxt-), (2) Local project modules (modules/ directory), (3) Runtime extensions (components, composables, plugins), (4) Server extensions (API routes, middleware), (5) Releasing/publishing modules to npm, (6) Setting up CI/CD workflows for modules.…