mvschwarz/openrig / packages/daemon/specs/agents/shared/skills/process/agent-browser
agent-browser
VerifiedBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
| File | Kind | Size |
|---|---|---|
| LICENSE.txt | markdown | 10.7 KB |
| LOCAL-INSIGHTS.md | markdown | 6.5 KB |
| OPENRIG.md | markdown | 1.0 KB |
| SKILL.md | skill md | 16.3 KB |
OPENRIG.md
View on GitHub---
skill: agent-browser
openrig-relationship: vendored-adapted
---
# OpenRig and this skill
## Origin
- **Upstream**: [Vercel Labs agent-browser](https://github.com/vercel-labs/agent-browser).
- **Checked**: 2026-10-25, revision `372ac5ce20fab885dbf45ee0c9d510ec8c3b6fdb`; SKILL.md and license compared, no content sync.
- **License**: upstream Apache-2.0 text is included verbatim in [LICENSE.txt](LICENSE.txt).
## OpenRig's copy
OpenRig retains an adapted browser workflow, with a Local Dev Insights pointer in
`SKILL.md` and the companion `LOCAL-INSIGHTS.md`. It does not track upstream.
At the checked revision, upstream's `skills/agent-browser/SKILL.md` is a discovery
stub that points to content served by the installed agent-browser CLI. This
retained workflow is not that stub and was not refreshed by the provenance check.
The comparison establishes the difference; it does not qualify the retained
commands or companion advice against any installed CLI version. Choosing whether
to retain this workflow or use upstream's served content is a separate change.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |