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 giltotherescue/velocity-agent-skills --skill vl-screenshotgit clone --depth 1 https://github.com/giltotherescue/velocity-agent-skillsWrote 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/giltotherescue/velocity-agent-skills/vl-screenshot)<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.
<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>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 | $0.00957 |
| Opus 5.5 | $0.00031 | $0.00383 |
| Sonnet 5.5 | $0.00015 | $0.00191 |
| Haiku 4.5 | $0.00008 | $0.00096 |
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 2mo 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 — 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
- Identify the review audience and what they need to judge.
- List the states/pages that tell the feature story from start to finish.
- Prepare stable test data so screenshots show realistic content.
- Capture numbered screenshots with the available browser tool: Playwright, Cypress, Puppeteer, Selenium, agent-browser, framework browser tests, or the agent's built-in browser.
- Build
index.htmlwithscripts/build_contact_sheet.py. - Open the folder and
index.html. - Spot-check the most important screenshots visually before handing off.
- 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.
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.
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.
- 2mo ago First seen · 113 lines · 77 tokens per session scan A 35c1b022e477
vl-screenshot is a skill published in the GitHub repository giltotherescue/velocity-agent-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 957 once invoked, about $0.0003 per session on Opus 5.5. 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
webgl-liquid-iridescence
A self-contained WebGL2 hero: a living oil-on-water field brightened into iridescent caustic filaments; move the cursor to bend the flow.
aws-architecture-diagram
Generate validated AWS architecture diagrams as draw.io XML using official AWS4 icon libraries. Use this skill whenever the user wants to create, generate, or design AWS architecture diagrams, cloud infrastructure diagrams, or system design visuals. Also triggers for requests to visualize existing infrastructure from…
gpui-mockup
Explore visual directions for a herdr-gpui UI element as real GPUI code. Write 3–4 variants in one Rust file, show them side by side in a native mockup window in the user's own theme and fonts, capture the window to check your work, and iterate on the picks and notes the user sends back. Use instead of the HTML mockup…
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
architecture-diagram
Generate architecture diagrams as fully editable SVG with native AWS, Azure, and GCP icons for cloud diagrams, or hand-drawn generic icons for everything else. Optionally deliver a self-contained editable draw.io mxGraph companion. Deterministic layout computes zone nesting and orthogonal routing instead of…