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 agentmods add skills/akakaui/visual-browser-agent/visual-capturenpx skills add Akakaui/visual-browser-agent --skill visual-capturegit clone --depth 1 https://github.com/Akakaui/visual-browser-agentWrote 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/akakaui/visual-browser-agent/visual-capture)<a href="https://agentmods.dev/skills/akakaui/visual-browser-agent/visual-capture"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/visual-capture.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 | $0.00019 | $0.00718 |
| Opus 5 | $0.00010 | $0.00359 |
| Sonnet 5 | $0.00004 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
visual-capture 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 3d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Capture Skill
When to Use
Use this skill for capturing visual evidence:
- Screenshots of page states
- Short video recordings of interactions
- Animation/transition capture
- Before/after comparisons
- Visual regression evidence
Instructions
Automatic Triggers (Config-Driven)
The system automatically captures based on config:
screenshotOnNavigation: After every navigationscreenshotOnStateChange: After clicks, fills, navigationrecordAnimations: "on-demand" (default) / "always" / "never"
Manual Capture
-
Screenshots: Use
capture_screenshotwith:action: Descriptive action namerequirement: What this screenshot provesselector: Optional element to capturefullPage: Capture full scrollable page
-
Recordings: Use
record_interaction:action: "start"+requirementto begin- Perform interactions
action: "stop"to end and save
Rolling Buffer
- Config:
rollingBufferSeconds: 5,clipAfterTriggerSeconds: 8 - Continuously records last 5 seconds
- On trigger, saves 8-second clip (5 before + 3 after)
- Enable with
recordAnimations: "always"
Frame Deduplication
- Config:
deduplicateFrames: true - Compares consecutive frames
- Skips near-identical screenshots
- Reduces storage for static pages
Evidence Manifest
Every capture creates an evidence manifest:
{
"eventId": "event-042",
"action": "open_mobile_menu",
"requirement": "mobile navigation is usable",
"artifacts": ["frames/mobile-menu-open.png", "clips/mobile-menu.webm"],
"review": { "passed": true, "confidence": 0.94, "findings": [] },
"nextDecision": "continue"
}
Best Practices
- Always include
requirement- what question does this evidence answer? - Use descriptive
actionnames for traceability - Capture minimally - only what's needed for the requirement
- Review evidence before deciding next action
- Use
review_visual_evidencefor vision-based analysis
Examples
User: "Capture the mobile menu open state"
Agent:
1. click(selector: ".mobile-menu-button")
2. capture_screenshot(action: "mobile_menu_open", requirement: "mobile navigation is usable")
3. review_visual_evidence(artifacts: [...], requirement: "mobile navigation is usable")
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.
- 3d ago First seen · 99 lines · 19 tokens per session scan A 1e53c96cb581
visual-capture is a skill published in the GitHub repository Akakaui/visual-browser-agent (0 stars, last pushed 9d ago), licensed MIT. It adds 19 tokens to every session and 718 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 2026-08-31.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
shadcn-svelte
Pre-built shadcn-svelte components for json-render Svelte apps. Use when working with @json-render/shadcn-svelte, adding standard UI components to a Svelte catalog, or building Svelte web UIs with shadcn-svelte + Tailwind CSS components.
column-resizing
Wire columnResizingFeature, header.getResizeHandler, resize mode and direction, pointer or touch events, and performant CSS-variable updates. Load when resize state changes but widths do not, or large tables resize slowly.
better-colors
Helps you build a color system and answer anything about color in your project. You can generate palettes, use semantic tokens, convert between formats, check contrast and more.
design-frontend-dev
Clean Impeccable frontend design skill. Use when the user wants to design, redesign, critique, audit, polish, harden, optimize, adapt, clarify, colorize, animate, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, onboarding, empty states…
markstream-svelte
Integrate the beta markstream-svelte package in Svelte 5 or SvelteKit apps. Use when Codex needs Svelte 5 runes, CSS and optional peers, smooth streaming, worker setup, renderer-local or scoped custom components, or SSR-safe boundaries. Svelte 4 is unsupported.