stark-translate

stark-translate is a command for coding agents from f0d010c/stark. It costs 50 tokens per session (472 once invoked), scanned A, original, Apache-2.0.

A command for adapting an interface from one platform to another while keeping its meaning and changing its platform conventions. It supports web, Windows, Apple, and Android as source or target platforms.

In plain words
What is it for?
Use it to turn an iOS settings screen into a Windows settings page, or translate similar product flows between web, Windows, Apple, and Android.
Why use it?
It avoids copying the original layout pixel for pixel when the target platform uses different navigation, controls, spacing, and design guidance.

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-translate
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-translate

README.md
[![agentmods](https://agentmods.dev/badge/commands/f0d010c/stark/stark-translate.svg)](https://agentmods.dev/commands/f0d010c/stark/stark-translate)
Your own site
<a href="https://agentmods.dev/commands/f0d010c/stark/stark-translate"><img src="https://agentmods.dev/badge/commands/f0d010c/stark/stark-translate.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 472 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 $0.00050 $0.00472
Opus 5 $0.00025 $0.00236
Sonnet 5 $0.00010 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured 5d ago against content hash 2fb7b2dbe8f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

stark-translate 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.

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-translate.md · 40 lines

What it actually says

/stark-translate

Legacy Claude Code command. In Codex, ask:

Translate this Apple UI to Windows using stark.

Translate UI from $1 (source platform) to $2 (target platform), preserving product semantics but using the target platform's idiom.

Source/target must each be one of: web, windows, apple, android.

Process

  1. Read the source — file content or description from $ARGUMENTS after the platform args.

  2. Identify the product semantics — what is this UI doing? Settings? List-detail? Onboarding? Tab nav? Modal flow?

  3. Translate idiom, not pixels. Reference the translation rules in skills/cross-platform-design/SKILL.md step 3.

    Example: an iOS grouped Form with switch toggles becomes:

    • On Windows → NavigationView + scrollable stack of SettingsCard over Mica
    • On Android → LargeTopAppBar + LazyColumn with ListItem rows + M3 switches
    • On web → asymmetric layout with sidebar nav and editorial section headers
  4. Apply target platform's anti-slop ban list as you generate. Read the target's SKILL.md step 6.

  5. State the translation choices at the top of the response in 2–3 lines:

    • "iOS grouped Form → Windows NavigationView + SettingsCard stack with Mica backdrop"
    • "iOS Toggle → WinUI ToggleSwitch with ThemeResource brushes"
    • "iOS section headers → Windows muted text headers, no row separators"
  6. Implement working code in the target stack.

Refuse to pixel-clone. If the user insists on identical pixels across platforms, push back once with the rationale: every platform has reference apps that nail their idiom; users notice when a Mac app feels Android.

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 · 40 lines · 50 tokens per session scan A 2fb7b2dbe8f3

Subscribe to this mod's changes

stark-translate is a command published in the GitHub repository f0d010c/stark (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 472 once invoked, about $0.0003 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