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.
npx skills add muzafferkadir/nextjs-loop-engineering-starter --skill ui-verifygit clone --depth 1 https://github.com/muzafferkadir/nextjs-loop-engineering-starterWrote 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/skills/muzafferkadir/nextjs-loop-engineering-starter/ui-verify)<a href="https://agentmods.dev/skills/muzafferkadir/nextjs-loop-engineering-starter/ui-verify"><img src="https://agentmods.dev/badge/skills/muzafferkadir/nextjs-loop-engineering-starter/ui-verify.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.00495 |
| Opus 5 | $0.00036 | $0.00247 |
| Sonnet 5 | $0.00015 | $0.00099 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
ui-verify 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 6d 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
ui-verify — Visual Inspection Skill
Look at the UI you changed, with your own eyes, before verification. Automated checks catch broken code; this catches broken design.
When
- After implementing any UI change (loop-build step 3)
- When a human asks "does it look right?"
- Before opening any PR that touches
src/app/orsrc/components/
How
- Ensure deterministic data (skip if the DB is untouched this session):
pnpm db:reset - Ensure the dev server is running (in the background):
pnpm dev - Screenshot the routes you changed (and any route that shares
changed components):
pnpm snap /tasks /login - Read each PNG in
.loop/screenshots/and inspect it against the checklist below. - Fix and repeat until the checklist passes, then continue to the verifier.
Inspection Checklist
- Layout: nothing overflows, wraps oddly, or overlaps at 1280×800
- Alignment: elements share consistent edges; spacing follows the Tailwind scale (no eyeballed pixel values)
- Hierarchy: the most important element reads first; text contrast is sufficient (muted text only for secondary info)
- Tokens: colors look consistent with the rest of the app (semantic tokens — if something looks "off-palette", it's probably hardcoded)
- States: empty state, loading skeleton, and error boundary still render correctly if you touched them
- Both themes: if the project has dark mode, snap and check both
Report
Summarize in one short block what you inspected and what you fixed:
UI verify: /tasks — fixed badge overflow on long titles; empty state OK; spacing OK.
Include this line in the PR body under "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.
- 6d ago First seen · 61 lines · 73 tokens per session scan A c4fe4208d14c
ui-verify is a skill published in the GitHub repository muzafferkadir/nextjs-loop-engineering-starter (10 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 495 once invoked, about $0.0004 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.
Other skills, from other repositories
web-accessibility-web-accessibility
WCAG, ARIA, keyboard navigation.
draft-design
Generate spec/DESIGN.md for the project. Asks at init whether to create a project-owned design system or reference an external one (URL/file/brand-book) as a guideline. Each project owns its DESIGN.md — no inheritance.
qa
Run test suite, browser checks, and verify acceptance criteria. Bootstrap test framework if missing.
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.
type-driven
Type-driven development. Use when developing with refined types, state machines encoded in types, or proof-carrying types; enforces totality and exhaustive pattern matching.