savecraft.gg: Skill for Claude Code

.claude/skills/working-on-views/SKILL.md

working-on-views is a skill for Claude Code from joshsymonds/savecraft.gg. It costs 90 tokens per session (2,986 once invoked), scanned A, original, Apache-2.0.

A set of rules for building interactive screens shown inside AI assistants such as Claude or ChatGPT.

In plain words
What is it for?
Use it when changing Svelte view components, view communication, Storybook examples, or the build process for interactive game-state and reference screens.
Why use it?
It prevents the deployed server from using an outdated screen and explains how these embedded views connect to Savecraft tools.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is joshsymonds/savecraft.gg's own configuration. It tells Claude Code how to work on savecraft.gg itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything savecraft.gg configures →

Reuse

Borrowing it

Nothing to install: this file belongs to joshsymonds/savecraft.gg. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/joshsymonds/savecraft.gg/main/.claude/skills/working-on-views/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/joshsymonds/savecraft.gg

Made for: Claude Code.

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 working-on-views

README.md
[![agentmods](https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/working-on-views/github.svg)](https://agentmods.dev/skills/joshsymonds/savecraft.gg/working-on-views)
Your own site
<a href="https://agentmods.dev/skills/joshsymonds/savecraft.gg/working-on-views"><img src="https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/working-on-views/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 working-on-views

Your own site · 80×15
<a href="https://agentmods.dev/skills/joshsymonds/savecraft.gg/working-on-views"><img src="https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/working-on-views.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,986 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.
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 $0.00090 $0.02986
Opus 5 $0.00045 $0.01493
Sonnet 5 $0.00018 $0.00597
Haiku 4.5 $0.00009 $0.00299

Measured 10d ago against content hash 04248ce1711f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

working-on-views 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 10d 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.

.claude/skills/working-on-views/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working on Views

Read docs/views.md for architecture, response format, and constraints. Read docs/view-design.md for when to build a view, interaction patterns, and visual principles.

CRITICAL: Rebuild After Every .svelte Change

worker/src/mcp/views.gen.ts is a committed build artifact — CI does not rebuild it. After modifying ANY .svelte file (in views/, worker/src/mcp/views/, or plugins/*/reference/views/), you MUST:

  1. Run just build-views
  2. Commit the regenerated views.gen.ts alongside your other changes

Forgetting this means production serves stale view HTML even after a successful cloud deploy. The deploy will succeed, the tests will pass, but users see the old view.

Verification

just build-views    # Rebuild views.gen.ts (required after any .svelte change)
just test-worker    # Handler + tool tests
just storybook-views  # Visual verification on port 6007

Two View Types

Game state views — one self-contained HTML per tool. Component + bridge bundled together.

  • Location: worker/src/mcp/views/<slug>.svelte
  • Slug maps to tool name: search-saves.svelte → tool search_saves

Reference views — one bundled HTML for query_reference containing ALL reference module components. Routes on structuredContent.module.

  • Location: plugins/<game>/reference/views/<module-id>.svelte
  • Filename maps to module ID: card-search.svelte → module card_search
  • Auto-discovered by build — adding a .svelte file and rebuilding is sufficient.

Adding a New View

  1. Create <name>.svelte — Svelte 5 component: let { data } = $props()
  2. Create <name>.stories.svelte — Storybook story with fixture data
  3. For game state views: update tool in tools.ts to return viewResult(structuredContent, narrative) instead of textResult()
  4. Run just build-views then just test-worker
  5. Commit views.gen.ts with other changes — CI does not rebuild it

Response Format

// Old (presentation hints — being replaced):
textResult(data, "Display as card gallery...");

// New (structured content for view rendering):
viewResult({ cards, total: cards.length }, "Found 5 cards.");
// For query_reference, handler injects module automatically:
// → { module: "card_search", cards: [...], total: 5 }

Read the full file on GitHub · 245 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. 10d ago First seen · 245 lines · 90 tokens per session scan A 04248ce1711f

Subscribe to this mod's changes

working-on-views is a skill published in the GitHub repository joshsymonds/savecraft.gg (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 2,986 once invoked, about $0.0005 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

shadcn-svelte

Pre-built shadcn-svelte components for json-render Svelte apps. Use when working with @json-render/shadcn-svelte, adding standard UI components to a Svelte catalog, or building Svelte web UIs with shadcn-svelte + Tailwind CSS components.

vercel-labs/json-render · 63 tokens

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

v3-create-crud

A page generator for standard create, read, update, and delete screens, commonly called CRUD screens. It uses Element Plus, a Vue user-interface library, to build tables, searches, pagination, forms, and delete confirmations.

un-pany/v3-admin-vite · 108 tokens

v3-use-composables

Documentation for reusable Vue functions in a project, covering device detection, asynchronous dropdown data, loading screens, pagination, routing, themes, page titles, and watermarks.

un-pany/v3-admin-vite · 137 tokens

moai-domain-uiux

UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.

modu-ai/moai-adk · 49 tokens

frontend-conventions

Frontend convention reference (SvelteKit / Svelte 5). Auto-injected into frontend-aware agents - not user-invocable.

fpindej/netrock · 27 tokens