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 soumyachk101/VibeLens --skill before-aftergit 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/skills/soumyachk101/vibelens/before-after)<a href="https://agentmods.dev/skills/soumyachk101/vibelens/before-after"><img src="https://agentmods.dev/badge/skills/soumyachk101/vibelens/before-after/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/skills/soumyachk101/vibelens/before-after"><img src="https://agentmods.dev/badge/skills/soumyachk101/vibelens/before-after.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 | $0.00061 | $0.00878 |
| Opus 5 | $0.00030 | $0.00439 |
| Sonnet 5 | $0.00012 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
before-after 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 10d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before and after
Target: $ARGUMENTS — the URL, and the change to make or verify (if either is missing, ask).
An edit is a hypothesis. The only thing that settles it is two captures of the same page taken under the same conditions. Do this whenever you claim something is fixed.
Steps
-
Capture before. Call
inspect_localhost_uiand write down the exact parameter set you used:url,viewport,fullPage,delay. Choose them deliberately now, because you are committed to them for the rest of the task. PreferfullPage: truewhen the change could shift anything below the fold, and adelayhigh enough that the page is fully hydrated — a comparison against a half-rendered baseline is worthless. -
Record the baseline in writing, not just as an image you will forget:
- the four diagnostic counts from
summary(consoleErrors,consoleWarnings,uncaughtPageErrors,failedRequests) summary.pageTitleandsummary.domTruncated- the class list of every element you are about to touch, copied verbatim from
simplifiedDOM - one sentence on the visible defect in the screenshot
- the four diagnostic counts from
-
Make the change. One coherent change at a time. If you edit three unrelated things and the after-capture is still wrong, the comparison tells you nothing about which one failed.
-
Capture after with byte-identical parameters. Same
url, sameviewport, samefullPage, samedelay.A different
viewportchanges layout, so every difference you see is the viewport, not your fix.fullPage: trueversusfalsechanges the image dimensions and which lazy content loaded. A shorterdelaycan catch the page mid-hydration and invent a regression; a longer one can let an async error appear that was always there. If any parameter differs, the comparison is meaningless — discard it and capture again correctly. If you must change a parameter (for example, the baseline delay was too short), re-take both captures under the new settings and say that you did.
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.
- 10d ago First seen · 71 lines · 61 tokens per session scan A d74ac3edddf3
before-after is a skill published in the GitHub repository soumyachk101/VibeLens (0 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 878 once invoked, about $0.0003 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
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
e2e-patterns
Write robust E2E tests with Playwright — page objects, resilient waiting, auth, and CI integration.
test-pyramid
Decide what type of test to write, structure the suite, measure health, and apply test doubles correctly.
mobile-testing
When writing E2E tests for mobile or configuring Detox.
blackbox-testing
Automates end-to-end and system validation tests. Runs services via Docker, feeds inputs, executes scenarios, and verifies outputs.
browser-testing-with-devtools
A guide for testing web pages and browser-based applications in a real Chrome browser through Chrome DevTools. It checks what is actually rendered and how the page behaves at runtime.