stark-assets

stark-assets is a command for coding agents from f0d010c/stark. It costs 31 tokens per session (441 once invoked), scanned A, original, Apache-2.0.

A command for planning the visual assets needed before building a website or app. Assets can include icons, fonts, textures, product interface mockups, references, and generated visuals.

In plain words
What is it for?
Use it to plan hero visuals, workflow diagrams, warning states, empty states, icons, typography, and other assets for a Stark-designed project.
Why use it?
It helps decide where each visual comes from, how it will be used, and whether it creates licensing concerns before implementation begins.

Command

Part of the stark plugin — 9 skills, 14 commands shipped together

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 commands/f0d010c/stark/stark-assets
Clone the repo
git clone --depth 1 https://github.com/f0d010c/stark

Or install stark, the plugin that ships this one along with the rest of its 9 skills, 14 commands.

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 stark-assets

README.md
[![agentmods](https://agentmods.dev/badge/commands/f0d010c/stark/stark-assets.svg)](https://agentmods.dev/commands/f0d010c/stark/stark-assets)
Your own site
<a href="https://agentmods.dev/commands/f0d010c/stark/stark-assets"><img src="https://agentmods.dev/badge/commands/f0d010c/stark/stark-assets.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 441 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 $0.00031 $0.00441
Opus 5 $0.00015 $0.00220
Sonnet 5 $0.00006 $0.00088
Haiku 4.5 $0.00003 $0.00044

Measured 4d ago against content hash 15527f60cee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stark-assets 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 4d 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.

commands/stark-assets.md · 46 lines

What it actually says

/stark-assets

Legacy Claude Code command. In Codex, ask:

Use stark assets to plan the visual assets for this app/site before building.

Plan assets for the project described by $ARGUMENTS.

Read:

  • references/ui-patterns/ui-decision-brief.md
  • references/ui-patterns/asset-selection.md
  • references/ui-patterns/asset-realism-matrix.md
  • references/ui-patterns/asset-production-pipeline.md
  • references/ui-patterns/advanced-visual-systems.md when assets become the signature visual system
  • the routed platform or web skill

Then produce an asset plan before implementation:

Asset plan
- Needed assets: product UI mock, icons, texture, typeface, references
- Source: local Stark library, lucide, generated CSS/SVG mock, imagegen, external reference
- Advanced visual system: main mechanic, owner, motif, fallback, rejected spectacle, if relevant
- License risk: none / low / needs attribution / avoid
- Usage: hero product preview, warning states, workflow diagram, empty state
- Reference extraction: structure only, not copied visuals
- Bans: stock hero photos, abstract AI gradients, placeholder images, private screenshots without permission

Rules

  • Do not freely browse and grab assets.
  • Ask whether the project needs icons, real product screenshots, reference UI patterns, typography, brand assets, or generated bitmap visuals.
  • Pull only assets that support the product job and visual direction.
  • If the agent is GPT/Codex and image generation is available, prefer generated bitmap assets for fictional hero imagery, textures, product concept art, or editorial visuals when CSS/SVG would be too weak.
  • Never include private/local screenshots unless the user explicitly allows it.
  • Do not copy copyrighted brand assets into public output.
  • Use real-world references to extract structure and interaction patterns, not visual identity.
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. 4d ago First seen · 46 lines · 31 tokens per session scan A 15527f60cee0

Subscribe to this mod's changes

stark-assets is a command published in the GitHub repository f0d010c/stark (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 441 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 2026-08-30.

Related

Other commands, from other repositories