Agent Skill

Verify skill

verifyzenbu-labs/terminal-browser.claude/skills/verify/SKILL.md

Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.

4.1kMIT

always on

37 tokname + description

once used

1,010 tokSKILL.md body

bundled files

repo stars

4.1kGitHub

Install the Verify skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/zenbu-labs/terminal-browser --skill verify

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/zenbu-labs/terminal-browser.git /tmp/terminal-browser
mkdir -p ~/.claude/skills
cp -R /tmp/terminal-browser/.claude/skills/verify ~/.claude/skills/verify

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

When	What loads	Cost
Every session	Name and description	37 tok
When the agent uses it	The SKILL.md instructions	1,010 tok
Only if opened	No bundled files	—

Until it is used, verify costs about 37× less than the median MCP server we measured (1,363 tokens on every turn). Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

Writing a verification
Ending a verification (required)
Gotchas