Skills

agent-browser

agent-browser is a skill in mvschwarz/openrig, last changed 26 Oct 2026. It can run shell commands, reach the network, name web addresses and pre-approve tools — read the findings before installing. Our pattern check found 1 item to review at commit 6957751 on 27 Oct 2026.

Pattern check: 1 item to review · commit 6957751 · 27 Oct 2026

Install
From the author
Browser 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.
Licence
Apache 2.0
Repo stars
8.3k
Folder last changed
26 Oct 2026 (opens in a new tab)
Publisher
mvschwarz
Files
4 files
Checked
6957751 (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit 6957751, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit 6957751, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/mvschwarz/openrig.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 6957751f5e39af15a3ccf04a579a8477d2744d88 &&
  git -C "$tmp" sparse-checkout set -- skills/_canonical/process/agent-browser &&
  git -C "$tmp" checkout -q 6957751f5e39af15a3ccf04a579a8477d2744d88 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/agent-browser &&
  cp -R "$tmp"/skills/_canonical/process/agent-browser/. .claude/skills/agent-browser/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit 6957751. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Reaches the network

    It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

    LOCAL-INSIGHTS.md:87

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

  • Pre-approves tools

    Its allowed-tools field lists tools the agent may use without asking you first, in agents that honour it.

    SKILL.md:4

Pattern check

Pattern check: 1 item to review · commit 6957751 · 27 Oct 2026

We checked every text file in this skill, at commit 6957751 on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Outside links we did not follow

  • https://github.com/vercel-labs/agent-browser
  • https://site-a.com
  • https://site-b.com
  • http://www.apache.org/licenses/
  • http://www.apache.org/licenses/LICENSE-2.0
  • https://www.google-analytics.com/
  • https://raw.githubusercontent.com/vercel-labs/agent-browser/main/skills/agent-browser/SKILL.md

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses with warnings

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Warning

      metadata values should be text; openrig (a map) is not. The spec's validator turns them into text; other readers may not. O4

      Fix: Quote each value, for example version: "1.0".

    • Warning

      Links to files that aren't in the skill folder: line 403: references/commands.md, line 404: references/snapshot-refs.md, line 405: references/session-management.md, line 406: references/authentication.md, line 407: references/video-recording.md and 5 more. B3

      Fix: Add the missing files or correct the paths, relative to SKILL.md.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

    • Note

      Reference files that SKILL.md doesn't link: OPENRIG.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: LOCAL-INSIGHTS.md (161 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude CodePasses with warnings

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Warning

      Links to files that aren't in the skill folder: line 403: references/commands.md, line 404: references/snapshot-refs.md, line 405: references/session-management.md, line 406: references/authentication.md, line 407: references/video-recording.md and 5 more. B3

      Fix: Add the missing files or correct the paths, relative to SKILL.md.

    • Note

      Reference files that SKILL.md doesn't link: OPENRIG.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: LOCAL-INSIGHTS.md (161 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude apps & API uploadPasses with warnings

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Warning

      Links to files that aren't in the skill folder: line 403: references/commands.md, line 404: references/snapshot-refs.md, line 405: references/session-management.md, line 406: references/authentication.md, line 407: references/video-recording.md and 5 more. B3

      Fix: Add the missing files or correct the paths, relative to SKILL.md.

    • Note

      The description is 488 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

    • Note

      metadata values should be text; openrig (a map) is not. The spec defines metadata as text to text. O4

      Fix: Quote each value, for example version: "1.0".

    • Note

      Reference files that SKILL.md doesn't link: OPENRIG.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: LOCAL-INSIGHTS.md (161 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • OpenAI (Codex & API)Passes with warnings

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Warning

      metadata values should be text; openrig (a map) is not. OpenAI's upload follows the spec's text-to-text rule. O4

      Fix: Quote each value, for example version: "1.0".

    • Warning

      Links to files that aren't in the skill folder: line 403: references/commands.md, line 404: references/snapshot-refs.md, line 405: references/session-management.md, line 406: references/authentication.md, line 407: references/video-recording.md and 5 more. B3

      Fix: Add the missing files or correct the paths, relative to SKILL.md.

  • VS Code & CopilotPasses with warnings

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Warning

      Links to files that aren't in the skill folder: line 403: references/commands.md, line 404: references/snapshot-refs.md, line 405: references/session-management.md, line 406: references/authentication.md, line 407: references/video-recording.md and 5 more. B3

      Fix: Add the missing files or correct the paths, relative to SKILL.md.

SKILL.md

Files

4 files

PathSize
LICENSE.txt (opens in a new tab)10.7 KB
LOCAL-INSIGHTS.md (opens in a new tab)6.5 KB
OPENRIG.md (opens in a new tab)1 KB
SKILL.md (opens in a new tab)16.3 KB

Copies

These share its SKILL.md or its name and description but not all its files, so we list them separately.

More from mvschwarz/openrig

  • agent-operated-software

    mvschwarz/openrig

    Use when designing, building, operating, or diagnosing an ongoing application whose live backend or control loop includes OpenRig agents, including applications with a Markdown, YAML, or JSON agent control plane or a thin surface over specialist agent roles.

    • Instructions only
    Pattern check: Nothing flagged

    Apache 2.0 · 8.3k repo stars · Updated 8 Sept 2026

  • agent-operated-workflows

    mvschwarz/openrig

    Use when a bounded real-world procedure has a deterministic happy path but brownfield, variable, or partially knowable state; when an operation must resume from verified evidence; or when deciding whether agent judgment or ordinary code should own a procedure's control loop.

    • Instructions only
    Pattern check: Nothing flagged

    Apache 2.0 · 8.3k repo stars · Updated 7 Sept 2026

  • agent-starters

    mvschwarz/openrig

    Use when creating, refreshing, packaging, inspecting, promoting, or deprecating a named per-seat starting point — Agent Starter manifest authoring, the 6-state lifecycle (captured → named → inspectable → used → promoted → deprecated), provenance honesty, and refusal rules. NOT a VM image; a managed starting point composed from agent role + startup context + optional native session source + provenance.

    • Instructions only
    Pattern check: Nothing flagged

    Apache 2.0 · 8.3k repo stars · Updated 4 Oct 2026

  • agent-startup-and-context-ingestion

    mvschwarz/openrig

    Use when designing or auditing how an agent becomes useful after launch — AGENTS.md overlays, role files, skills, rig specs, workflow specs, startup checklists, refocus messages, "rig context" surface. Covers the 4 failure modes that make startup context fail (old rig spec misses current operating mode; current agents never told about new guidance; startup file as dumping ground; orchestrator transmits implementation without preserving product intent).

    • Runs shell commands
    Pattern check: Nothing flagged

    Apache 2.0 · 8.3k repo stars · Updated 4 Oct 2026

  • applying-a-permission-policy

    mvschwarz/openrig

    Use before launching a team during agent-guided setup, or when a user asks to configure OpenRig command permissions, reduce repeated native approval prompts, or apply a selected rig/seat permission policy.

    • Runs shell commands
    • Names web addresses
    Pattern check: Nothing flagged

    Apache 2.0 · 8.3k repo stars · Updated 6 Oct 2026

  • backlog-capture

    mvschwarz/openrig

    Quickly capture product ideas, feature requests, or insights from meetings and conversations. Rapid documentation with smart categorization and deduplication.

    • Instructions only
    Pattern check: Nothing flagged

    Apache 2.0 · 8.3k repo stars · Updated 7 Aug 2026

All skills in mvschwarz/openrig