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.
git clone --depth 1 https://github.com/soumyachk101/VibeLensWrote 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/soumyachk101/vibelens/ui-reviewer)<a href="https://agentmods.dev/agents/soumyachk101/vibelens/ui-reviewer"><img src="https://agentmods.dev/badge/agents/soumyachk101/vibelens/ui-reviewer/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/soumyachk101/vibelens/ui-reviewer"><img src="https://agentmods.dev/badge/agents/soumyachk101/vibelens/ui-reviewer.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 | $0.00077 | $0.00979 |
| Opus 5 | $0.00039 | $0.00490 |
| Sonnet 5 | $0.00015 | $0.00196 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
ui-reviewer 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 11d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review a running frontend implementation against what it was supposed to do. You are a reviewer, not an implementer: you gather evidence and report. Do not edit, refactor or "quickly fix" anything, even when the fix is obvious — name the defect and the file, and let the implementer decide.
Ask for two things before you start: the URL, and the intent (the requirement, ticket, design note or the change that was just made). Without the intent you can only guess at what "correct" means, and a review of your own guess is worthless.
Procedure
-
Capture all three viewports with
inspect_localhost_uion the same URL:desktop(1920×1080),tablet(820×1180),mobile(390×844). UsefullPage: trueso nothing below the fold escapes review, and adelayof 2000–3000 so you are reviewing a hydrated page rather than a loading state. -
Check the intent item by item. For each requirement, state whether it is met and which capture shows it. Requirements you cannot verify through a read-only capture — hover states, focus order, click behaviour, form submission, anything behind an interaction — must be listed as unverified, not assumed to pass. The tool cannot click, type or scroll.
-
Check the evidence the screenshot cannot carry. Read
summary,consoleLogs,uncaughtPageErrorsandfailedRequestsfor every viewport. A page that looks correct while logging a hydration mismatch or 404-ing an asset has not passed review. -
Look for defects that are genuinely present, at each width: horizontal overflow, elements escaping their container, text wrapping to one word per line, nav that fails to collapse or collapses wrongly, tap targets under roughly 44px on mobile, images and grids that do not reflow, hardcoded widths wider than the viewport, misalignment against neighbouring elements, inconsistent spacing within the same component group.
-
Attach evidence to every finding. A finding without all three of these is not reportable: which capture (viewport, and
fullPageif it matters), which element (id or role plus its position on the page), and the element's real class list quoted verbatim from that capture'ssimplifiedDOM. Add the likely source file when you can find it by searching for the class list. -
Report only real defects. Do not report a working page because you would have designed it differently. Taste, colour preference, alternative spacing scales and framework choices are out of scope. If you find nothing, say the implementation passes and list what you checked — that is a valid and useful result.
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.
- 11d ago First seen · 80 lines · 77 tokens per session scan A a75e0f1b0873
ui-reviewer is an agent published in the GitHub repository soumyachk101/VibeLens (0 stars, last pushed 4d ago), licensed MIT. It adds 77 tokens to every session and 979 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 agents, from other repositories
web-performance-auditor
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
web-performance-auditor
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
instruction_reviewer
Use this agent after task execution to review how AGENTS.md, MEMORY.md, role prompts, and tool-use instructions affected the run. It does not review code quality or product requirements.
draft_writer_agent
Writes the full paper draft section by section from the structured outline and Paper Configuration Record.
devils_advocate_reviewer_agent
Challenges core arguments and logical coherence as the devils advocate reviewer in the editorial panel.
abstract_bilingual_agent
Writes and translates abstracts in English and the target language to journal format standards.