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 jleechanorg/agent-orchestrator-ts --skill ui-video-evidencegit clone --depth 1 https://github.com/jleechanorg/agent-orchestrator-tsWrote 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/jleechanorg/agent-orchestrator-ts/ui-video-evidence)<a href="https://agentmods.dev/skills/jleechanorg/agent-orchestrator-ts/ui-video-evidence"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/ui-video-evidence/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/jleechanorg/agent-orchestrator-ts/ui-video-evidence"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/ui-video-evidence.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 | $0.00024 | $0.01233 |
| Opus 5.5 | $0.00010 | $0.00493 |
| Sonnet 5.5 | $0.00005 | $0.00247 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
ui-video-evidence 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 9d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Video Evidence for Visual Verification
Purpose
Prove that UI behavior, visual state, and click flows occurred as claimed. A GIF with visible URL, timestamps, and action context is tamper-evident in a way screenshots alone are not.
When This Is Required
Use UI video evidence (in addition to tmux video) whenever your claim involves:
- A rendered UI component or page
- A click flow, form submission, or navigation
- Visual state change (modal open, error shown, data loaded)
- "Works in browser" or "UI looks correct" claims
- Any test that drives a real browser
Tool Options
Option 1 — Claude-in-Chrome GIF (preferred for agent sessions)
mcp__claude-in-chrome__gif_creator
Built into the harness. Records Chrome tab interactions directly.
Usage pattern:
- Start gif recording
- Navigate to the page under test (URL must be visible in frame)
- Perform the action being claimed
- Capture the resulting state
- Stop and save with a meaningful filename
Option 2 — Kap (preferred for native app / full-screen flows)
brew install --cask kap
Open Kap → select region → record → export as GIF.
Option 3 — ffmpeg (CI / headless environments)
# Record X11 display (Linux CI)
ffmpeg -video_size 1280x720 -framerate 10 -f x11grab -i :99 \
-t 30 /tmp/<work_name>.mp4
# Convert to GIF
ffmpeg -i /tmp/<work_name>.mp4 -vf "fps=10,scale=1280:-1" \
/tmp/<work_name>.gif
Mandatory Evidence Frames
Every UI evidence GIF MUST show these frames in order:
| # | Frame | What must be visible |
|---|---|---|
| 1 | URL + Page Load | Full browser URL bar showing the route being tested |
| 2 | Before State | Initial state before the action (empty form, list count, etc.) |
| 3 | Action | The click, input, or navigation being performed |
| 4 | After State | Result of the action (success message, data change, navigation) |
| 5 | Git Commit Link | Terminal pane or overlay showing git rev-parse HEAD |
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.
- 9d ago First seen · 153 lines · 24 tokens per session scan A 0d4c53f3c28e
ui-video-evidence is a skill published in the GitHub repository jleechanorg/agent-orchestrator-ts (8 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 1,233 once invoked, about $0.0001 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 2026-10-02.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…