svelte5

svelte5 is a skill for Claude Code, Codex from joshuadavidthomas/agent-skills. It costs 180 tokens per session (2,438 once invoked), scanned A, original, MIT.

A review guide for Svelte 5 components, a web framework for building interactive user interfaces.

In plain words
What is it for?
Use it when writing, reviewing, or migrating Svelte components, especially when checking reactive state, props, events, accessibility, and Svelte 5 conventions.
Why use it?
It identifies older or borrowed patterns that may work but make state, data flow, and user interactions harder to understand.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when writing, reviewing, or migrating Svelte components, especially when checking reactive state, props, events, accessibility, and Svelte 5 conventions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joshuadavidthomas/agent-skills/svelte5
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.

Any agent
npx skills add joshuadavidthomas/agent-skills --skill svelte5
Clone the repo
git clone --depth 1 https://github.com/joshuadavidthomas/agent-skills

Made for: Claude Code, Codex.

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 svelte5

README.md
[![agentmods](https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/svelte5/github.svg)](https://agentmods.dev/skills/joshuadavidthomas/agent-skills/svelte5)
Your own site
<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/svelte5"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/svelte5/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.

agentmods 80×15 button for svelte5

Your own site · 80×15
<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/svelte5"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/svelte5.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 37
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
How audits are shown
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 5.1 $0.00180 $0.02438
Opus 5 $0.00090 $0.01219
Sonnet 5 $0.00036 $0.00488
Haiku 4.5 $0.00018 $0.00244

Measured 12d ago against content hash cf8ec3b219b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

svelte5 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.

svelte5/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Think in Svelte 5

You already know Svelte syntax. This skill changes your defaults — what you reach for first when designing a component, placing state, modeling reactivity, and reviewing UI code.

The core failure mode is Svelte that compiles but thinks like React, Vue, or Svelte 4 — effects standing in for derived values and events, props mirrored into state, global stores by reflex, two-way binding as the default, clickable divs, Svelte 4 component APIs in new code.

The component is a small reactive program with visible dependencies. Keep dataflow direct, state ownership obvious, and markup semantic; let the compiler and the DOM do the work.

This skill is the general-purpose entry point for Svelte component review; for SvelteKit-level concerns, also use sveltekit (see Cross-References).

Treat these as strong defaults, not rigid laws: when unsure, choose the approach that makes ownership, dependencies, and user semantics more explicit.

How Svelte Thinks

Make reactivity visible

1. Reactivity is read-tracked. A $derived/$effect depends on what it reads while running; if one reruns unexpectedly, inspect its reads, not a dependency array. See references/read-tracked-reactivity.md.

2. Derived state is $derived, not $effect. Pure functions of other state get derived; effects are for side effects, not keeping variables in sync. See references/effect-driven-state.md.

<!-- ❌ effect writing derived state -->
let doubled = $state(0);
$effect(() => { doubled = count * 2; });

<!-- ✅ derive it -->
let doubled = $derived(count * 2);

3. Effects are escape hatches. Before $effect, check for a derived value, an event handler, or a bind: getter/setter. Use it only to touch the outside world — subscriptions, timers, observers, imperative APIs, logging — and return cleanup.

4. Runes are statically analyzable. Compiler syntax, not runtime hooks — reusable state becomes .svelte.ts classes and factories, not custom hooks. See references/static-runes.md.

Read the full file on GitHub · 142 lines

Files

What ships with it

37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 142 lines · 180 tokens per session scan A cf8ec3b219b1

Subscribe to this mod's changes

svelte5 is a skill published in the GitHub repository joshuadavidthomas/agent-skills (49 stars, last pushed 1mo ago), licensed MIT. It adds 180 tokens to every session and 2,438 once invoked, about $0.0009 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.

Related

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.

liuyanghejerry/Clausura · 31 tokens

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.

jiushiwon/wg-skills · 86 tokens

standards-to-tooling

Translates project coding standards into concrete linting and formatting tool configurations. Given human-readable conventions (from AGENTS.md, code review guidelines, or team standards), this skill produces ESLint, Prettier, Biome, TypeScript, and other tool configs that enforce them automatically. Covers discovery…

pantheon-org/tekhne · 76 tokens

Component Test Scaffold (Vue.js)

Generate Vue.js component test skeletons (Vue Test Utils) from specifications.

s977043/river-review · 22 tokens

review-frontend

Performs a strict code review of the Svelte 5 frontend code (files, diffs, or snippets). Trigger whenever the user shares frontend code (Svelte, TypeScript, CSS) and asks for a review, feedback, or says "review this" — including partial snippets.

AndreiBozantan/svelte-axum-template · 62 tokens

fe-framework-coding-standard

Standardized frontend implementation guidance for FE Dev using the SRS-declared Frontend-Framework. Use when coding, refactoring, or reviewing UI work in React Native, ReactJS, Flutter, Vue.js, Angular, or Next.js; FE Dev reads docs/SRS.md Frontend-Framework plus §3.4.2/§3.4.5 for multi-app projects, then selects the…

evolplus/talos · 111 tokens