Browser automation CLI for AI agents; use for web tasks - navigate, click, fill forms, screenshot, scrape, test web/Electron apps.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# agent-browser
Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with
accessibility-tree snapshots and compact `@eN` element refs.
Install: `npm i -g agent-browser && agent-browser install`
## Start here
This file is a discovery stub, not the usage guide. Before running any
`agent-browser` command, load the actual workflow content from the CLI:
```bash
agent-browser skills get core # start here — workflows, common patterns, troubleshooting
agent-browser skills get core --full # include full command reference and templates
```
The CLI serves skill content that always matches the installed version,
so instructions never go stale. The content in this stub cannot change
between releases, which is why it just points at `skills get core`.
## Specialized skills
Load a specialized skill when the task falls outside browser web pages:
```bash
agent-browser skills get electron # Electron desktop apps (VS Code, Slack, Discord, Figma, ...)
agent-browser skills get slack # Slack workspace automation
agent-browser skills get dogfood # Exploratory testing / QA / bug hunts
…
The line at the top of this page pins the label git:20261020.7a1f356, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (2356 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
higoralves/orc · 7 stars · license MIT · pushed 2026-10-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6rkytjsxtcytizam
GET https://markdownregistry.com/api/v1/resolve?ref=higoralves/orc/agent-browser
GET https://markdownregistry.com/api/v1/blob/4dd3828e0f46083260e69b8158675aa64ff77331f27bfd8c10d32775ed6ce452
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
higoralves/orc · orc/skills/adr-writing/SKILL.md · Author and update Architecture Decision Records (ADRs) — the durable record of a decision and its trade-offs, in…
higoralves/orc · orc/skills/callouts/SKILL.md · The orc callout palette — emoji-header blockquotes in conversation, GitHub-flavored [!TYPE] form for GitHub-bound output
higoralves/orc · orc/skills/ci-routing/SKILL.md · The canonical route-on-verdict protocol for a red CI diagnosis — fixable/flake/infra/needs-debug handling, the…
higoralves/orc · orc/skills/code-discovery/SKILL.md · Use when discovering or navigating a codebase before planning, implementing, debugging, or refactoring — prefer a…
higoralves/orc · orc/skills/codebase-design/SKILL.md · Shared vocabulary for designing deep modules — seam, adapter, depth, leverage, locality. Use when designing or…
paperclipai/paperclip · packages/skills-catalog/catalog/optional/browser/agent-browser/SKILL.md · Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and…
shanraisshan/claude-code-best-practice · .claude/skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
vercel-labs/agent-browser · skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
nanocoai/nanoclaw · container/skills/agent-browser/SKILL.md · Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots…
mvschwarz/openrig · skills/_canonical/process/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
mvschwarz/openrig · packages/daemon/specs/agents/shared/skills/process/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
maxmiksa/auto-company · .claude/skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
fcakyon/claude-codex-settings · plugins/agent-browser/skills/agent-browser/SKILL.md · Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow…