dryui-init

dryui-init is a skill for Claude Code, Codex from rob-balfre/dryui. It costs 39 tokens per session (3,306 once invoked), scanned A, original, MIT.

A setup workflow for adding DryUI to a SvelteKit project or creating a new SvelteKit project with DryUI. SvelteKit is a framework for building web applications, and DryUI provides the interface components and styling rules.

In plain words
What is it for?
Use it to start a DryUI project, add DryUI to an existing SvelteKit app, or handle an unclear project that might need either approach.
Why use it?
It determines whether the project is new or already uses SvelteKit, then directs the appropriate setup instead of applying the wrong project structure.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

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 skills/rob-balfre/dryui/dryui-init
Any agent
npx skills add rob-balfre/dryui --skill dryui-init
Clone the repo
git clone --depth 1 https://github.com/rob-balfre/dryui

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 dryui-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/rob-balfre/dryui/dryui-init.svg)](https://agentmods.dev/skills/rob-balfre/dryui/dryui-init)
Your own site
<a href="https://agentmods.dev/skills/rob-balfre/dryui/dryui-init"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/dryui-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,306 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 5.1 $0.00039 $0.03306
Opus 5 $0.00019 $0.01653
Sonnet 5 $0.00008 $0.00661
Haiku 4.5 $0.00004 $0.00331

Measured 5d ago against content hash 89267b18a350, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

dryui-init 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 5d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/bare-skeleton.sh, scripts/setup-feedback-agents.sh, templates/src/app.d.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/dryui-init/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dryui:init

Bootstrap DryUI in the current project, or scaffold a new SvelteKit app when the user asks for a new project.

Install Or Refresh This Skill

The durable install path for DryUI skills is:

npx skills add rob-balfre/dryui

Skill Discipline

This is a short, linear flow. Do not create per-step TaskCreate items — the bookkeeping costs more than the work it tracks. One intent line up front and one summary line at the end is enough.

First tool call is always the script. Do not run an explicit pre-triage ls/[ -f X ] call — the script self-triages and routes via exit code:

bash <skill-base-dir>/scripts/bare-skeleton.sh "$PWD"
  • Exit 0 → done. Print one summary line and stop.
  • Exit 2 with route=existing-sveltekit → follow Apply Setup below.
  • Exit 2 with route=ambiguous → ask the user one question (scaffold over / integrate / abort), then act on the answer.
  • Any other non-zero → read the message, fix the specific issue, do not re-run the whole thing manually.

Do not Read any file you just copied from templates/ to verify it — those files are validated by bun run check at the end of the script. Do not run bunx sv@latest create into a temp dir. Do not overwrite package.json with Write — the script uses jq to merge so user-set keys (especially overrides) are preserved.

What The Script Does

scripts/bare-skeleton.sh is the single entry point. It self-triages and either bootstraps a bare skeleton or exits 2 with a routing hint. Steps in order:

  1. Triage — exits 2 with route=existing-sveltekit if svelte.config.* is present, or route=ambiguous if src/ exists without a config.
  2. Removes index.ts / index.js from the bun init skeleton.
  3. Copies every file in templates/ into the project root, including local AGENTS.md / CLAUDE.md instructions that force UI agents through dryui-build.
  4. Merges scripts, lucide-svelte into dependencies, devDependencies, and type: "module" into package.json via jq. Preserves existing overrides and any other dependency keys.
  5. Appends SvelteKit/Vite ignores to .gitignore (idempotent — checks for /.svelte-kit first).
  6. Detects a local dryui workspace at $DRYUI_LOCAL, ../dryui, ~/dryui, ~/src/dryui, or ~/code/dryui. If found, runs bun link in each packages/{ui,lint,primitives,feedback,feedback-server} and writes overrides with link:@dryui/<pkg> so the consumer pulls the local workspace. If not found, falls back to bun add @dryui/ui + bun add -d @dryui/lint @dryui/feedback @dryui/feedback-server against npm.
  7. Runs scripts/setup-feedback-agents.sh "$PWD" to copy project-local DryUI skills, detect installed feedback agents, merge project-local MCP config files where possible, and write dryui.config.json.
  8. Runs bun run check to validate the contract end-to-end.

Read the full file on GitHub · 136 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. 5d ago First seen · 136 lines · 39 tokens per session scan A 89267b18a350

Subscribe to this mod's changes

dryui-init is a skill published in the GitHub repository rob-balfre/dryui (9 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 3,306 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 2026-08-31.