vl-screenshot

vl-screenshot is a skill for Claude Code, Codex from giltotherescue/velocity-agent-skills. It costs 77 tokens per session (957 once invoked), scanned A, original, MIT.

A screenshot-review workflow for web interfaces that collects images of a feature across pages and states into a shareable folder.

In plain words
What is it for?
Capturing realistic web-page states, creating a clickable screenshot index, and packaging the images for sharing.
Why use it?
It makes a complete interface flow easier for developers, designers, testers, and other reviewers to inspect without running the application themselves.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Capturing realistic web-page states, creating a clickable screenshot index, and packaging the images for sharing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/giltotherescue/velocity-agent-skills/vl-screenshot
Install

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.

Any agent
npx skills add giltotherescue/velocity-agent-skills --skill vl-screenshot
Clone the repo
git clone --depth 1 https://github.com/giltotherescue/velocity-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for vl-screenshot

README.md
[![agentmods](https://agentmods.dev/badge/skills/giltotherescue/velocity-agent-skills/vl-screenshot/github.svg)](https://agentmods.dev/skills/giltotherescue/velocity-agent-skills/vl-screenshot)
Your own site
<a href="https://agentmods.dev/skills/giltotherescue/velocity-agent-skills/vl-screenshot"><img src="https://agentmods.dev/badge/skills/giltotherescue/velocity-agent-skills/vl-screenshot/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.

agentmods 80×15 button for vl-screenshot

Your own site · 80×15
<a href="https://agentmods.dev/skills/giltotherescue/velocity-agent-skills/vl-screenshot"><img src="https://agentmods.dev/badge/skills/giltotherescue/velocity-agent-skills/vl-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 957 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.00957
Opus 5 $0.00039 $0.00478
Sonnet 5 $0.00015 $0.00191
Haiku 4.5 $0.00008 $0.00096

Measured 12d ago against content hash 35c1b022e477, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vl-screenshot 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/build_contact_sheet.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/vl-screenshot/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Velocity Screenshot

Create a review folder that lets the team see an entire frontend flow at a glance, click through screenshots in-page, and download the screenshots as a zip for sharing.

Output Standard

The folder should contain:

  • Numbered screenshots, using names like 01-start.png, 02-empty-state.png, 03-results.png.
  • index.html, a clickable contact sheet with a two-column desktop grid and in-page previous/next screenshot viewer.
  • screenshots.zip, a downloadable zip of the matched screenshots for sharing in Slack, email, or issue comments.
  • Screenshots large enough to inspect real UI, preferably full-page for long flows.
  • Real loaded content where possible, not loading placeholders, unless the loading state itself is part of the review.

Default folder naming:

~/Desktop/<feature-name>-screenshots

Workflow

  1. Identify the review audience and what they need to judge.
  2. List the states/pages that tell the feature story from start to finish.
  3. Prepare stable test data so screenshots show realistic content.
  4. Capture numbered screenshots with the available browser tool: Playwright, Cypress, Puppeteer, Selenium, agent-browser, framework browser tests, or the agent's built-in browser.
  5. Build index.html with scripts/build_contact_sheet.py.
  6. Open the folder and index.html.
  7. Spot-check the most important screenshots visually before handing off.
  8. If the feature requires staged backend state, document the refresh steps next to the implementation.

Capture Guidance

Prefer full-page screenshots for flows with cards, lists, or long forms.

Example with an agent-browser style CLI:

agent-browser open "$URL"
agent-browser wait 1200
agent-browser screenshot --full "$OUT/01-start.png"

Use a named browser session when auth or cookies matter:

AGENT_BROWSER_SESSION=feature-review agent-browser open "$URL"
AGENT_BROWSER_SESSION=feature-review agent-browser screenshot --full "$OUT/01-start.png"

If the UI depends on queued jobs, external services, or backend states, create a temporary staging helper that:

  • Mutates only local/test data.
  • Can stage each state deterministically.
  • Restores the record to a stable final state after capture.
  • Is referenced in handoff notes if another person needs to refresh screenshots.

Read the full file on GitHub · 113 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 113 lines · 77 tokens per session scan A 35c1b022e477

Subscribe to this mod's changes

vl-screenshot is a skill published in the GitHub repository giltotherescue/velocity-agent-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 957 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.