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/agent-browsernpx skills add ColeMurray/background-agents --skill agent-browsergit 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/agent-browser)<a href="https://agentmods.dev/skills/colemurray/background-agents/agent-browser"><img src="https://agentmods.dev/badge/skills/colemurray/background-agents/agent-browser.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 | $0.00000 | $0.00663 |
| Opus 5 | $0.00000 | $0.00331 |
| Sonnet 5 | $0.00000 | $0.00133 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
agent-browser 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 4d 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.
agent-browser
Use agent-browser from bash when you need visual verification in the sandbox.
When To Use It
- Capture screenshots of a UI before or after a change
- Record short interaction videos that upload to the session
- Compare two states with a visual diff
- Inspect accessibility structure or page snapshots
Core Commands
agent-browser screenshot --json /tmp/current.png
agent-browser screenshot --full --json /tmp/full-page.png
agent-browser screenshot --annotate --json /tmp/annotated.png
agent-browser diff screenshot --baseline /tmp/before.png -o /tmp/diff.png
Prefer --json when you need machine-readable output such as a saved path.
Uploading Screenshots
Screenshots only appear in the Open-Inspect session after upload.
upload-media /tmp/current.png --caption "Dashboard after fix"
upload-media /tmp/full-page.png --full-page
upload-media /tmp/annotated.png --annotated
upload-media /tmp/current.png \
--source-url "http://127.0.0.1:3000" \
--viewport '{"width":1440,"height":900}'
Working Pattern
- Capture the current state with
agent-browser screenshot. - Make or verify the UI change.
- Upload the screenshot with
upload-media. - When useful, upload before/after/diff images as separate artifacts.
Recording Videos
Use agent-browser record for browser recordings. Record to an .mp4 path so agent-browser
encodes a silent MP4, then probe actual dimensions/duration with ffprobe and upload with
upload-media.
set -e
agent-browser open "http://127.0.0.1:3000/checkout"
agent-browser set viewport 1440 900
agent-browser snapshot -i
STARTED_AT_MS=$(date +%s%3N)
agent-browser record start /tmp/opencode/checkout-flow.mp4
recording_started=1
trap 'if [ "${recording_started:-0}" = "1" ]; then agent-browser record stop || true; fi' EXIT
interaction_exit_code=0
agent-browser click "[data-testid=continue]" || interaction_exit_code=$?
agent-browser wait 1000 || interaction_exit_code=$?
agent-browser record stop
recording_started=0
trap - EXIT
ENDED_AT_MS=$(date +%s%3N)
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.
- 4d ago First seen · 81 lines · 0 tokens per session scan A e1c74aad623f
agent-browser is a skill published in the GitHub repository ColeMurray/background-agents (2,712 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 663 tokens. 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
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.
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.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.