Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add hmj1026/dhpk/plugin install dhpkWrote 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/commands/hmj1026/dhpk/ui-ux-verify)<a href="https://agentmods.dev/commands/hmj1026/dhpk/ui-ux-verify"><img src="https://agentmods.dev/badge/commands/hmj1026/dhpk/ui-ux-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 | $0.00023 | $0.01339 |
| Opus 5 | $0.00012 | $0.00669 |
| Sonnet 5 | $0.00005 | $0.00268 |
| Haiku 4.5 | $0.00002 | $0.00134 |
Grade A, and why
ui-ux-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 yesterday.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ This command delegates to the ui-ux-verifier agent via the Task tool.
Agent body: ${CLAUDE_PLUGIN_ROOT}/agents/ui-ux-verifier.md
Requires the external OpenSpec plugin for the Default Mode flow (which lists
openspec/changes/*/specs/**/spec.mdfiles changed on the current branch). URL Mode and Combined Mode work without OpenSpec installed.
Context
- Current branch: !
git branch --show-current - Base branch: master
- Changed spec files: !
git diff master..HEAD --name-only | grep -E '^openspec/changes/[^/]+/specs/.+/spec\.md$' || true
Arguments
$ARGUMENTS
| Invocation | Behavior |
|---|---|
/ui-ux-verify |
Default Mode: list openspec/changes/*/specs/**/spec.md changed on the current branch relative to master, prompt the user to pick one, then delegate to the agent |
/ui-ux-verify <url> |
URL Mode: pass the URL to the agent; spec is auto-searched by the agent |
/ui-ux-verify <url> spec:<path> |
Combined Mode: URL + explicit spec path delivered to the agent together |
/ui-ux-verify spec:<path> |
Spec-Only Mode: spec only; URL is derived by the agent from spec contents |
URL format must match https://www.<app-host>/<route-prefix>/<controller>/<action> (the actual host and route-prefix are project-specific; the agent has a built-in regex validation that the consuming project can override).
Workflow
-
Parse
$ARGUMENTS- Empty string → Default Mode (step 2)
- Contains
https://→ URL Mode or Combined Mode (jump to step 4) - Starts with
spec:and no URL → Spec-Only Mode (jump to step 3)
-
Default Mode — pick a changed spec
- Read the
Changed spec fileslist injected into the Context block above - Empty list → cross-verify with
Globagainstopenspec/changes/*/specs/**/spec.md; if still empty, report: "the current branch has no spec.md changes relative tomaster; please use/ui-ux-verify <url>to target a page directly." Then stop — do not enter the agent - Single file → use it; proceed to step 3
- Multiple files → list as a numbered table, wait for user reply (e.g.
1). One spec at a time, to avoid context explosion
- Read the
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.
- yesterday First seen · 108 lines · 23 tokens per session scan A e447a1b4073f
ui-ux-verify is a command published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,339 once invoked, about $0.0001 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 2026-09-05.
Other commands, from other repositories
naksha-browse
Browse any URL with browser vision — extract design patterns for research or inspect your own UI, saved to project memory.
design-compare
Capture two websites with Playwright and produce a structured side-by-side design comparison — layout, color, typography, navigation, and 'steal this' recommendations.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
theme
Switch between visual theme skins — OLED Black, Matrix, Claude Anthropic, Surprise Me.
stark-director
Use this command when the user asks Stark to go all out, raise design quality broadly, use libraries well, make a UI feel actually designed, or coordinate research, typography, motion, usability, implementation, and QA in one pass.