agent-browser is a skill in fcakyon/claude-codex-settings, last changed 28 Oct 2026. It can run shell commands, reach the network, name web addresses, bundle scripts and pre-approve tools — read the findings before installing.

From the author
Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

At a glance

Pattern check

1 item to review

Broad tools pre-approved in allowed-tools

R34 · High · SKILL.md:4

Commit c9887bd · 3 Nov 2026

How the check works

Pattern check:1 item to reviewSee it

Install

Each tab says whether it installs commit c9887bd, the one we checked, or the latest version.

Read this before installing: Broad tools pre-approved in allowed-tools — SKILL.md:4

Read SKILL.md first
Apache 2.0
Licence
1.2k
Repo stars
Publisher

What it can touch

From the files and frontmatter at commit c9887bd. This is how much a skill can do, not whether it is risky.

Pattern check

Pattern check: 1 item to review · commit c9887bd · 3 Nov 2026

We checked every text file in this skill, at commit c9887bd on 3 Nov 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

  • https://duckduckgo.com
  • https://docs
  • https://agent-browser.dev/engines/lightpanda
  • https://agent-browser.dev/engines/obscura
  • https://twitter.com
  • https://ui.perfetto.dev/
  • https://internal.company.com
  • https://external.com
  • https://site.com/page1
  • https://site.com/page2
Show 13 more
  • https://site.com/page3
  • http://corpproxy.company.com:8080
  • https://external-vendor.com
  • https://intranet.company.com
  • https://httpbin.org/ip
  • https://site-a.com
  • https://site-b.com
  • https://site1.com
  • https://site2.com
  • https://site3.com
  • https://app.com?variant=a
  • https://app.com?variant=b
  • https://github.com

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 the strictest version of each rule among the agents we check.

    • Warning

      The body is 580 lines; the spec suggests under 500. B1

      Fix: Move detailed sections into reference files and link to them from SKILL.md.

    • Warning

      The body is about 9,585 tokens (approx.); the spec suggests under 5,000. B2

      Fix: Move detail into reference files that the agent reads only when needed.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/commands.md (577 lines) and references/webgpu.md (119 lines). B5

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

  • Claude CodePasses

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

    • Note

      The body is 580 lines; the spec suggests under 500. Claude Code's docs say the same. B1

      Fix: Move detailed sections into reference files and link to them from SKILL.md.

    • Note

      The body is about 9,585 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2

      Fix: Move detail into reference files that the agent reads only when needed.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/commands.md (577 lines) and references/webgpu.md (119 lines). B5

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

  • Claude apps & API uploadPasses

    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.

    • Note

      The description is 558 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

      The body is 580 lines; the spec suggests under 500. Anthropic's guidance says the same. B1

      Fix: Move detailed sections into reference files and link to them from SKILL.md.

    • Note

      The body is about 9,585 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2

      Fix: Move detail into reference files that the agent reads only when needed.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/commands.md (577 lines) and references/webgpu.md (119 lines). B5

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

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

Files

More from fcakyon/claude-codex-settings

SkillWhat it can touchPattern checkLicenceUpdated
  • Instructions only
Pattern check: Nothing flaggedApache 2.020 Jul 2026
  • Names web addresses
Pattern check: Nothing flaggedApache 2.028 Oct 2026
agents-sdkBuild, debug, or review Cloudflare Agents SDK applications using the agents package.
  • Runs shell commands
  • +2 more

Pattern check: Nothing flaggedApache 2.0Updated 28 Oct 2026

  • Runs shell commands
  • Reaches the network
  • +1 more
Pattern check: Nothing flaggedApache 2.028 Oct 2026
  • Instructions only
Pattern check: Nothing flaggedApache 2.08 Sept 2026
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: Nothing flaggedApache 2.029 Oct 2026
  • Names web addresses
Pattern check: Nothing flaggedApache 2.017 Dec 2025
All skills in fcakyon/claude-codex-settings

Other Frontend & design skills

Same category, most repo stars first.

SkillWhat it can touchPattern checkLicenceUpdated
  • Names web addresses
Pattern check: Nothing flaggedMIT27 Sept 2026
  • Instructions only
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Names web addresses
  • Bundles scripts
Pattern check: Nothing flaggedApache 2.020 Apr 2026
  • Names web addresses
Pattern check: Nothing flaggedApache 2.020 Apr 2026
  • Changes agent settings
  • Runs shell commands
  • +3 more
Pattern check: 1 item to reviewMIT2 Nov 2026
design-htmlDesign finalization: generates production-quality Pretext-native HTML/CSS. (gstack)

garrytan/gstack

  • Runs shell commands
  • +4 more

Pattern check: 1 item to reviewMITUpdated 2 Nov 2026

  • Runs shell commands
  • Reaches the network
  • +3 more
Pattern check: 1 item to reviewMIT2 Nov 2026

Repo facts from GitHub on 3 Nov 2026. Files read at commit c9887bd.

QAI did not write these skills and is not affiliated with their authors unless a page says so. Logos and icons belong to their owners and are not a mark of approval. How we check