ui-iterate

ui-iterate is a command for coding agents from ShipWithAI/shipwithai-plugins. It costs 43 tokens per session (1,424 once invoked), scanned A, original, MIT.

A command that repeatedly checks and improves a Jetpack Compose screen, a Kotlin UI screen built from code, until it passes layout and visual checks.

In plain words
What is it for?
It renders screens at different sizes, text scales, themes, and content states; runs automated checks; records findings; and applies fixes between checks.
Why use it?
It separates editing from evaluation so the agent does not judge its own changes, and escalates to a person after four attempts.

Command

Part of the shipwithai-mobile-ui-harness plugin — 2 skills, 3 commands, 1 agent 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/shipwithai/shipwithai-plugins/ui-iterate
Clone the repo
git clone --depth 1 https://github.com/ShipWithAI/shipwithai-plugins

Or install shipwithai-mobile-ui-harness, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 1 agent.

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 ui-iterate

README.md
[![agentmods](https://agentmods.dev/badge/commands/shipwithai/shipwithai-plugins/ui-iterate.svg)](https://agentmods.dev/commands/shipwithai/shipwithai-plugins/ui-iterate)
Your own site
<a href="https://agentmods.dev/commands/shipwithai/shipwithai-plugins/ui-iterate"><img src="https://agentmods.dev/badge/commands/shipwithai/shipwithai-plugins/ui-iterate.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,424 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 $0.00043 $0.01424
Opus 5 $0.00022 $0.00712
Sonnet 5 $0.00009 $0.00285
Haiku 4.5 $0.00004 $0.00142

Measured 4d ago against content hash 308236b85805, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-iterate 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.

plugins/mobile-ui-harness/commands/ui-iterate.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iterate on $ARGUMENTS until it passes, then stop. Hard cap: 4 iterations, then escalate to the human.

Two lanes, kept apart. You are the executor: you edit the @Composable and run the gates. The evaluator is a separate subagent in a fresh context (step 4) — never grade your own edits, that's the self-review this loop exists to prevent.

Commands below use placeholders (<app-module>, <module>, <your.pkg>) and e.g. examples. Derive the real values from this project in step 0 — never run the example coordinates verbatim.

0. Locate + resolve target

  • Glob for the screen's inspection test: **/*$ARGUMENTS*Inspection.kt (convention: <Screen>Inspection, seeded by the setup skill). From its path derive three things: the Gradle module (e.g. :feature:foo:impl), the test FQN (e.g. com.acme.feature.foo.impl.presentation.<Screen>Inspection), and the PNG dir (<module>/build/outputs/roborazzi/).
  • No inspection test yet? Create one from the template the setup skill installs (assets/substrate/ScreenInspection.kt.tmpl; see INTEGRATION.md) — width {360,411} × fontScale {1.0,1.5,2.0} × {light,dark} × content {default,long,empty,error}, each capturing to _inspect_*.png then calling Tier1Assertions.assertAll.
  • Target: if harness/targets/$ARGUMENTS.png exists → Fidelity mode (evaluator reports deltas vs target). Else → absolute rubric mode.

1. Implement / edit (executor lane)

Edit the @Composable for $ARGUMENTS. Rails (apply whichever your project has):

  • Reuse your design system — check your component catalog before building anything new.
  • Tokens, not literals — use your theme's color/spacing/type/shape tokens (keep raw MaterialTheme.* inside the design-system module).
  • Insets: top-level screens consume WindowInsets (status/nav bars, IME).
  • Boundary gate: if your project enforces a design-system / Material-3 boundary (e.g. via the konsist-architecture-tests skill or a Konsist rule), satisfy it — add or reuse a wrapper rather than importing the gated API directly.

Read the full file on GitHub · 71 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. 4d ago First seen · 71 lines · 43 tokens per session scan A 308236b85805

Subscribe to this mod's changes

ui-iterate is a command published in the GitHub repository ShipWithAI/shipwithai-plugins (10 stars, last pushed 22d ago), licensed MIT. It adds 43 tokens to every session and 1,424 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.