Open-Inspect is a hosted system that lets coding agents work on software tasks in background development environments. Teams use it to connect agents with repositories, communication tools, scheduled events, and parallel sandboxes. The catalogue contains add-ons associated with this system.
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/colemurray/background-agents/record-videonpx skills add ColeMurray/background-agents --skill record-videogit clone --depth 1 https://github.com/ColeMurray/background-agentsWrote 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/colemurray/background-agents/record-video)<a href="https://agentmods.dev/skills/colemurray/background-agents/record-video"><img src="https://agentmods.dev/badge/skills/colemurray/background-agents/record-video.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 | $0.00012 | $0.00788 |
| Opus 5 | $0.00006 | $0.00394 |
| Sonnet 5 | $0.00002 | $0.00158 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
record-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
record-video
Use this skill when a UI verification depends on interaction over time: opening menus, clicking through flows, dragging, typing, navigation, loading states, transitions, or animation.
Key Facts
Use agent-browser record as the primary recorder. Record directly to an .mp4 path so
agent-browser encodes the recording as a silent MP4 that can be uploaded with upload-media.
Required Workflow
- Open the target page with
agent-browser open. - Set the viewport explicitly when layout matters.
- Use
agent-browser snapshot -ito inspect accessible names/selectors before recording. - Start recording with
agent-browser record start <path>.mp4. - Perform the interaction being verified.
- Always run
agent-browser record stop. - Use
ffprobeto read actual encoded dimensions and duration before upload. - Report the returned
artifactIdand what interaction was verified.
Command Pattern
set -e
agent-browser open "$URL"
agent-browser set viewport 1512 982
agent-browser snapshot -i
STARTED_AT_MS=$(date +%s%3N)
agent-browser record start /tmp/opencode/demo.mp4
recording_started=1
cleanup_recording() {
if [ "${recording_started:-0}" = "1" ]; then
agent-browser record stop || true
fi
}
trap cleanup_recording EXIT
interaction_exit_code=0
agent-browser click "[data-testid=settings]" || interaction_exit_code=$?
agent-browser wait 1000 || interaction_exit_code=$?
agent-browser record stop
recording_started=0
trap - EXIT
ENDED_AT_MS=$(date +%s%3N)
PROBE_JSON=$(ffprobe -v error -print_format json -show_streams -show_format /tmp/opencode/demo.mp4)
DURATION_MS=$(node -e 'const p=JSON.parse(process.argv[1]); const v=(p.streams||[]).find((s)=>s.codec_type==="video")||{}; const d=Number(v.duration ?? p.format?.duration); console.log(Math.max(1, Math.round(d * 1000)));' "$PROBE_JSON")
DIMENSIONS=$(node -e 'const p=JSON.parse(process.argv[1]); const v=(p.streams||[]).find((s)=>s.codec_type==="video")||{}; console.log(JSON.stringify({width:Number(v.width),height:Number(v.height)}));' "$PROBE_JSON")
upload-media /tmp/opencode/demo.mp4 \
--artifact-type video \
--caption "What this recording verifies" \
--source-url "$URL" \
--duration-ms "$DURATION_MS" \
--recording-started-at "$STARTED_AT_MS" \
--recording-ended-at "$ENDED_AT_MS" \
--dimensions "$DIMENSIONS" \
--truncated false \
--has-audio false
exit "$interaction_exit_code"
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.
- 5d ago First seen · 81 lines · 12 tokens per session scan A 1a3288fefa49
record-video is a skill published in the GitHub repository ColeMurray/background-agents (2,724 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 788 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 2026-08-30.
Other skills, from other repositories
v8-jit
V8 JIT optimization patterns for writing high-performance JavaScript in Next.js server internals. Use when writing or reviewing hot-path code in app-render, stream-utils, routing, caching, or any per-request code path. Covers hidden classes / shapes, monomorphic call sites, inline caches, megamorphic deopt, closure…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
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.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.