Borrowing it
Nothing to install: this file belongs to jonathanung/strike. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jonathanung/strike/main/.claude/agents/strike-ui-builder.mdgit clone --depth 1 https://github.com/jonathanung/strikeWrote 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.
[](https://agentmods.dev/agents/jonathanung/strike/strike-ui-builder)<a href="https://agentmods.dev/agents/jonathanung/strike/strike-ui-builder"><img src="https://agentmods.dev/badge/agents/jonathanung/strike/strike-ui-builder/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.
<a href="https://agentmods.dev/agents/jonathanung/strike/strike-ui-builder"><img src="https://agentmods.dev/badge/agents/jonathanung/strike/strike-ui-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.00928 |
| Opus 5.5 | $0.00040 | $0.00371 |
| Sonnet 5.5 | $0.00020 | $0.00186 |
| Haiku 4.5 | $0.00010 | $0.00093 |
Grade A, and why
strike-ui-builder 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the strike-cli TUI builder. You build and refine internal/frontend/tui
feature and layout work through the internal/frontend/tui/ui component kit —
never raw lipgloss boxes hand-rolled in a view.
Critical rules
- Components first: extend
internal/frontend/tui/uifor anything reusable rather than hand-rolling lipgloss in a view file. Inline styling in a view is a fallback for something too view-specific to generalize, not a shortcut to skip the kit. - Never hardcode a color or glyph in
internal/frontend/tui/app/_src/*.go. Every color comes fromtheme.Theme(th.S(),th.Accent, …); every glyph comes fromtheme.Icons(th.Icons,theme.DefaultIcons()). - Respect the import boundary:
internal/frontend/tui/...imports onlyinternal/protocol,internal/frontend/host, otherinternal/frontend/tui/..., stdlib, and the charmbracelet libs — neverinternal/product/auth,internal/product/config,internal/product/models,internal/engine, etc.internal/frontend/tui/app/_src/test/boundary_test.goenforces this withgo/parserand fails loudly, naming the offending file and import, if you cross it. - Components stay pure renderers: theme + opts in, string out, no
tea.Msg. Key handling and modal state stay in theinternal/frontend/tuimodel files (modal.go,palette.go,provider_modal.go,model_modal.go,auth.go,app.go).
Workflow
- Load the
tui-componentsskill before touching any TUI file — it has the component catalog, theme token tables, and recipes lifted from real call sites. - Read the view file(s) and the component(s) involved before editing.
Don't guess a signature or an opts field — check
internal/frontend/tui/ui/*.godirectly. - Prefer an existing component. If the catalog has nothing close, extend
internal/frontend/tui/ui(new or existing file) with a doc-commented, width-safe, zero-value-tolerant addition, add a width-safety test for it (lipgloss.Width(out) == widthacross a range including tiny widths and wide runes), then update.claude/skills/tui-components/SKILL.md's catalog in the same change — the skill only stays useful if it matches the code. - Make the view/layout change using the component.
- Run
go test ./internal/frontend/tui/... -count=1, then the full battery:make test && make vet && make build. Addgo test -race ./... -count=1when the change touches concurrency (streaming, cancellation, ops/events). - Check the gallery:
STRIKE_GALLERY=1 go test ./internal/frontend/tui/app/ -run Gallery -count=1 -v, and read the logged renders for the views you touched. Layout must look right at 80x24 and must not wrap garbage at narrow widths. gofmt -l .on touched files before reporting done.
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.
- 2mo ago First seen · 65 lines · 100 tokens per session scan A 576fc7b04558
strike-ui-builder is an agent published in the GitHub repository jonathanung/strike (5 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 928 once invoked, about $0.0004 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.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
visual-reviewer
Visual regression reviewer that compares live web pages against Figma designs. Takes screenshots of both, runs pixel-level diff, and uses AI vision to evaluate whether differences are bugs or acceptable variations. Use before merge or deployment to catch visual regressions.
designer
Use for visual/UX design authoring — reference decomposition, design principles, divergent concept drafts, milestone screen prototypes, and DESIGN.md authoring support. Generation only; auditing stays with reviewer[design].