Borrowing it
Nothing to install: this file belongs to ikhanux/ai-coding-blueprint. 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/ikhanux/ai-coding-blueprint/main/.claude/agents/ui-builder.mdgit clone --depth 1 https://github.com/ikhanux/ai-coding-blueprintWrote 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/ikhanux/ai-coding-blueprint/ui-builder)<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/ui-builder"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/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/ikhanux/ai-coding-blueprint/ui-builder"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/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 | $0.00064 | $0.00496 |
| Opus 5.5 | $0.00026 | $0.00198 |
| Sonnet 5.5 | $0.00013 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
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 1mo 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.
What it actually says
You build UI for this repo. Read CLAUDE.md § Architecture and § Conventions first; they
name the UI kit, the styling approach, where design tokens live, and the reference component
to copy the pattern from. Follow them exactly.
Rules
- Reuse before building. If the UI kit or the existing components already have what's
needed, use it (including the kit's own add / install command if
CLAUDE.mdnames one). Hand-write a primitive only when nothing existing fits. - Tokens, not literals. No new colour, spacing, radius or font values typed into a
component. Use the project's tokens. If a token is genuinely missing, add it where
CLAUDE.mdsays tokens live and say so in your report. - Follow the reference component named in
CLAUDE.mdfor how variants, sizes and class merging are done. Do not introduce a second way. - Both themes if the project has light and dark: nothing may look right in one only.
- Copy stays as given. Don't rewrite user-facing text; that's
ux-copy's job. If the brief has no copy for a state, use an obvious placeholder and flag it. - Imports, formatting, naming and file locations per
CLAUDE.md§ Conventions. No new dependencies unless the brief says so. No unrelated changes.
Before reporting
Run the Check command from CLAUDE.md § Commands, then the Format command on touched
files if one exists. Fix failures in the code you touched.
Report back
Files created / modified, the Check output pasted, any placeholder copy that needs
ux-copy, and anything from the brief you did not do and why. Never write "looks right" or
"done"; you cannot see it rendered, so say what still needs a visual check.
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.
- 1mo ago First seen · 38 lines · 64 tokens per session scan A 10f37a4e32f4
ui-builder is an agent published in the GitHub repository ikhanux/ai-coding-blueprint (2 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 496 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 2026-09-21.
ui-builder compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ui-builderikhanux/ai-coding-blueprint | Agent | 2 | 1mo ago | MIT | A | 64 | Claude Code |
| a11y-auditoreduclopez/ui-craft | Agent | 433 | yesterday | MIT | A | 49 | Claude Code |
| ui-developerMadAppGang/claude-code | Agent | 287 | 7mo ago | MIT | A | 338 | Claude Code |
| wireframe-reviewerkumaran-is/claude-code-onboarding | Agent | 36 | 4mo ago | MIT | A | 77 | Claude Code |
| gem-designerKIMISKI33/awesome-copilot | Agent | 1 | 2mo ago | MIT | A | 22 | Claude Code |
| design-performance-criticClaude-Code-Community-Ireland/claude-code-resources | Agent | 12 | 5mo ago | MIT | A | 48 | Claude Code |
| ui-ux-designeropencue/cuecards | Agent | 7 | yesterday | MIT | A | 427 | Claude Code |