agentmods.dev

TinyAssets: Skill for Claude Code

.agents/skills/website-editing/SKILL.md

website-editing is a skill for Claude Code, Codex from Jonnyton/TinyAssets. It costs 83 tokens per session (1,868 once invoked), scanned A, original, MIT.

A set of project-specific rules for editing and deploying the TinyAssets website, which has a current React/Next version and a retained Svelte version.

In plain words
What is it for?
It guides edits to website text, components, pages, styles, and routes, as well as local previews, chatbot conversation captures, builds, and deployments.
Why use it?
It helps an agent make website changes consistently while keeping both versions aligned and following the project's preview and deployment process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; mentions Codex.

This is Jonnyton/TinyAssets's own configuration. It tells Claude Code and Codex how to work on TinyAssets 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 TinyAssets configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../site-react && npm test # contract + boundary + preview validators.

not rated 1repo changed 2mo ago A scan 83 tokens original MIT
View source ↗ Jonnyton/TinyAssets tinyassets.io
Reuse

Borrowing it

Nothing to install: this file belongs to Jonnyton/TinyAssets. 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/Jonnyton/TinyAssets/main/.agents/skills/website-editing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Jonnyton/TinyAssets

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 website-editing

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jonnyton/tinyassets/website-editing"><img src="https://agentmods.dev/badge/skills/jonnyton/tinyassets/website-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,868 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 $0.00083 $0.01868
Opus 5.5 $0.00033 $0.00747
Sonnet 5.5 $0.00017 $0.00374
Haiku 4.5 $0.00008 $0.00187

Measured 2mo ago against content hash 472c2706a4bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

website-editing 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 2mo 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.

.agents/skills/website-editing/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Website editing

WebSite/site-react/ is the only source for tinyassets.io. It is a Next.js 14 App Router static export that consumes @tiny/design-system (WebSite/design-system/, tokens + base styles + components). It deploys manually through deploy-site-react.yml. The Svelte rollback tree was retired on 2026-09-02; do not recreate a second tree or a parity step.

These are project-level website rules for every provider; AGENTS.md only points here.

Before you edit anything

  1. Read WebSite/PREVIEW.md (the preview loop) and, if you might ship, WebSite/DEPLOY.md.
  2. Know what the site is for. One sentence the whole site serves: your own AI universe: a cloud agent that runs on your subscription, builds any automation to any platform from primitives, learns you continuously, and runs 24/7 under your control. Every page has one job; the map is in openspec/specs/public-website-surface/spec.md.
  3. Tokens live in the design system. Colour, type, spacing, and the vocabulary classes (.sheet, .rule, .ledger, .receipt, .ev, .eyebrow) come from WebSite/design-system/src/styles/. Edit tokens.css (canonical), run npm run build there, and the site picks it up. DESIGN.md there is the rules layer.
  4. The mark has one source. tinyassets/desktop/icon_gen.py owns the geometry and palette; python WebSite/brand/render_marks.py exports it to every surface (site icons, assets/, desktop, Android, tray, Play listing) and python WebSite/brand/render_og.py renders the OG card. Never hand-edit an exported PNG or ICO.

The iteration loop

cd WebSite/site-react && npm run dev     # http://localhost:3000, live /mcp proxied

Edit, the tab updates (HMR). If a tab ever needs F5, investigate; do not normalise the workaround. Copy and tokens are reviewed in the browser, not in the diff.

Copy rules

  • Sell outcomes, not mechanisms. Never open with "AI-powered workflow engine". Lead with what a universe finishes: a merged PR, a ledger, a watched feed. The proof on the home page is a real receipt (PR #2728).
  • Naming. TinyAssets is the platform, site, and brand. Tiny is the universe the person talks to; it speaks first person. A chatbot relays to the universe; it never "embodies" it.
  • Honest availability. No platform model; Claude is a setup-token deposit, not an OAuth button; ChatGPT/Codex is one tap. Android is a pre-release APK; desktop builds are unsigned and from source. Say so in words.
  • Plans in one place. /fine-print#plans is the only page that describes free versus premium ($20 a month, higher daily limits on outside-world actions, compute and storage). No numbers until enforcement is live, no upgrade control until the app has one. /start may carry one sentence linking there.
  • Do not advertise the paid market, crypto or tokens, hardware, host-run fleets, per-channel integration lists, the retired Workflow name, or "powered by ". No engagement metrics anywhere.
  • Hero = ritual label + H1 + one lead paragraph + one primary action. Secondary links are quiet text.
  • Forms are never fake. If there is no backend, use mailto: with real fields.
  • Affordance contract. If it looks clickable it is clickable; prefer <a>/<button> over clickable <div>s.
  • Refresh labels are fixed: Refresh MCP and Refresh GitHub.
  • No phone numbers.

Read the full file on GitHub · 150 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. 2mo ago Changed · -3 lines · +10 tokens per session scan C → A 472c2706a4bc
  2. 2mo ago First seen · 153 lines · 73 tokens per session scan C 9eb13b61a51d

Subscribe to this mod's changes

website-editing is a skill published in the GitHub repository Jonnyton/TinyAssets (1 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,868 once invoked, about $0.0003 per session on Opus 5.5. 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.

Design and UXFrontend
Related

website-editing compared with skills from other repositories

website-editing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
website-editingJonnyton/TinyAssetsSkill11mo agoMITA83Claude Code, Codex
webgl-holographic-foilnexu-io/open-designSkill106kyesterdayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106kyesterdayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106kyesterdayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34k3d agoMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6kyesterdayMITA47Claude Code