agent-browser
Skill0 starsChanged 5 months agoMITView on GitHub
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.
- Installs packages
195 other projects use a version of this, 139 of them edited; 135 of 136 edited versions we compared changed its rules; 7 new projects in the last 4 weeks, against 16 the 4 before.
How people change it
135 of 136 edited versions changed its rules, and some changes recur.
Of the 136 edited versions we compared: 1 keep every rule, 135 made changes of their own.
Rules people drop
- When refs are unavailable or unreliable, use semantic locators:dropped by 80 of 135
- Interact: Use refs to click, fill, selectdropped by 75 of 135
- Re-snapshot: After navigation or DOM changes, get fresh refsdropped by 75 of 135
- Every browser automation follows this pattern:dropped by 74 of 135
Rules people add
- A rule we can't quote: its licence doesn't allow itadded by 52 of 135
- A rule we can't quote: its licence doesn't allow itadded by 52 of 135
- A rule we can't quote: its licence doesn't allow itadded by 52 of 135
- A rule we can't quote: its licence doesn't allow itadded by 51 of 135
- A rule we can't quote: its licence doesn't allow itadded by 48 of 135
- A rule we can't quote: its licence doesn't allow itadded by 48 of 135
- A rule we can't quote: its licence doesn't allow itadded by 48 of 135
- A rule we can't quote: its licence doesn't allow itadded by 48 of 135
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Cooling: 7 new projects took it in the last 4 weeks, 0.4× the 4 weeks before.
Most recently taken up by
- maxwell2732/claudecode-research-harness-workflowtheir own version, first seen Nov 15, 2026
- FimawLLC/fimaw-skillsedited, first seen Nov 15, 2026
- axiom-desu/ZCodiumedited, first seen Nov 15, 2026
- moi-computer/moitheir own version, first seen Nov 15, 2026
- crbnos/carbonedited, first seen Nov 15, 2026
- kortix-ai/sunaedited, first seen Nov 15, 2026
Used with
Projects with it also use time-skill, dep-refs and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Recepay6358Skilltime-skill
Display the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.
Also in 6 projects that use this
betacatslingSkilldep-refs
Use when needs to inspect TypeScript export references in the z-code workspace, list exports from a file, verify whether an export is unused before deletion, investigate who imports a symbol during refactors, or combine pnpm knip unused-export results with pnpm dep:refs symbol-level reference tracing.
Also in 5 projects that use this
betacatslingSkillfeature-boundary-planner
Map a ZCode behavior change to current UI surfaces, state owners, protocol commands, persistence, and validation. Use for impact analysis, product-boundary planning, or an implementation handoff grounded in the checked-out source.
Also in 5 projects that use this
Recepay6358Skillweather-svg-creator
Creates an SVG weather card showing the current temperature for Dubai. Writes the SVG to orchestration-workflow/weather.svg and updates orchestration-workflow/output.md.
Also in 6 projects that use this
Cartograf666Skillarchitecture-governance
Bootstrap, document, enforce, and review a project's architecture through layer responsibilities, dependency direction, architecture manifests, legacy baselines, Change Envelopes, cross-layer approval policy, and deterministic architecture checks. Use when starting a project, auditing an existing codebase, planning cross-layer work, preventing architecture erosion, reviewing structural changes, or deciding whether implementation may expand into another layer.
Also in 5 projects that use this
Maliot100XSkillsend-user-message
Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp). Use when the agent needs to notify, alert, or send an unsolicited message to a user — especially during heartbeat invocations, scheduled tasks, or when the agent wants to reach out without a prior user message in the current conversation. Triggers: 'send message to user', 'notify user', 'alert user', 'message the user on discord/telegram/whatsapp', or any need to proactively communicate with a paired sender.
Also in 4 projects that use this
Other versions195 projects use a version of this.
Word for word · 12
- shanraisshan/claude-code-best-practice★ 69k100% same
- MaxMiksa/Auto-Company★ 3.2k100% same
- MaxMiksa/Autonomous-Company★ 3.2k100% same
- nicepkg/auto-company★ 188100% same
- NikitaDmitrieff/auto-co-meta★ 43100% same
- Recepay6358/claude-code-best-practice★ 4100% same
- noya21th/ClaudeCode-BestPractice★ 2100% same
- sumulige/sumulige-claude★ 2100% same
- DmacMcgreg/psibot★ 1100% same
- PickleBoxer/skills★ 1100% same
2 more not listed
Edited · 139
- vercel-labs/agent-browser★ 51k16% same
- moeru-ai/airi★ 51k16% same
- activepieces/activepieces★ 26k35% same
- slopus/happy★ 25k52% same
- kortix-ai/CompanyOS★ 21k16% same
- kortix-ai/suna★ 21k16% same
- documenso/documenso★ 16k99% same
- elie222/inbox-zero★ 13k26% same
- humanlayer/humanlayer★ 13k27% same
- markmead/hyperui★ 12k16% same
129 more not listed
Wrote their own version · 44
- eosphoros-ai/DB-GPT★ 20ksame name
- emdash-cms/emdash★ 14ksame name
- superagent-ai/grok-cli★ 3.5ksame name
- Chachamaru127/claude-code-harness★ 3.2ksame name
- oxylabs/agent-skills★ 876same name
- EvovexAI/EvoFlow★ 636same name
- InternLM/WildClawBench★ 534same name
- github/replica★ 275same name
- cafe3310/public-agent-skills★ 258same name
- team-mirai-volunteer/mirai-gikai★ 214same name
34 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository70 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- code-review-securitySkill
- cold-email-sequence-generatorSkill
- community-led-growthSkill
- competitive-intelligence-analystSkill
- content-strategySkill
- deep-analysisSkill
- deep-reading-analystSkill
- deep-researchSkill
- devopsSkill
- email-sequenceSkill
- financial-unit-economicsSkill
- find-skillsSkill
- github-explorerSkill
- market-sizing-analysisSkill
- micro-saas-launcherSkill
- ph-community-outreachSkill
- premortemSkill
- pricing-strategySkill
- product-strategistSkill
- scientific-critical-thinkingSkill
- security-auditSkill
- senior-qaSkill
- seo-auditSkill
- seo-content-strategistSkill
- skill-creatorSkill
- startup-business-modelsSkill
- startup-financial-modelingSkill
- tailwind-v4-shadcnSkill
- teamSkill
- user-persona-creationSkill
- user-research-synthesisSkill
- ux-audit-rethinkSkill
- web-scrapingSkill
- webshSkill
- agent-browserSkill
- code-review-securitySkill
- cold-email-sequence-generatorSkill
- community-led-growthSkill
- competitive-intelligence-analystSkill
- content-strategySkill
- deep-analysisSkill
- deep-reading-analystSkill
- deep-researchSkill
- devopsSkill
- email-sequenceSkill
- financial-unit-economicsSkill
- find-skillsSkill
- github-explorerSkill
- market-sizing-analysisSkill
- micro-saas-launcherSkill
- ph-community-outreachSkill
- premortemSkill
- pricing-strategySkill
- product-strategistSkill
- scientific-critical-thinkingSkill
- security-auditSkill
- senior-qaSkill
- seo-auditSkill
- seo-content-strategistSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 168 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Every browser automation follows this pattern:
- Distinctive: line 15
Interact: Use refs to click, fill, select
- Distinctive: line 16
Re-snapshot: After navigation or DOM changes, get fresh refs
- Distinctive: line 184
When refs are unavailable or unreliable, use semantic locators:
“Common” is measured: kept by at least 6 in 10 of the 168 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Browser Automation with agent-browser
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"
agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i # Check resultEssential Commands
# Navigation
agent-browser open <url> # Navigate (aliases: goto, navigate)
agent-browser close # Close browser
# Snapshot
agent-browser snapshot -i # Interactive elements with refs (recommended)
agent-browser snapshot -i -C # Include cursor-interactive elements (divs with onclick, cursor:pointer)
agent-browser snapshot -s "#selector" # Scope to CSS selector
# Interaction (use @refs from snapshot)
agent-browser click @e1 # Click element
agent-browser fill @e2 "text" # Clear and type text
agent-browser type @e2 "text" # Type without clearing
agent-browser select @e1 "option" # Select dropdown option
agent-browser check @e1 # Check checkbox
agent-browser press Enter # Press key
agent-browser scroll down 500 # Scroll page
# Get information
agent-browser get text @e1 # Get element text
agent-browser get url # Get current URL
agent-browser get title # Get page title
# Wait
agent-browser wait @e1 # Wait for element
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --url "**/page" # Wait for URL pattern
agent-browser wait 2000 # Wait milliseconds
# Capture
agent-browser screenshot # Screenshot to temp dir
agent-browser screenshot --full # Full page screenshot
agent-browser pdf output.pdf # Save as PDFCommon Patterns
Form Submission
agent-browser open https://example.com/signup
agent-browser snapshot -i
agent-browser fill @e1 "Jane Doe"
agent-browser fill @e2 "jane@example.com"
agent-browser select @e3 "California"
agent-browser check @e4
agent-browser click @e5
agent-browser wait --load networkidleAuthentication with State Persistence
# Login once and save state
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "$USERNAME"
agent-browser fill @e2 "$PASSWORD"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json
# Reuse in future sessions
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboardData Extraction
agent-browser open https://example.com/products
agent-browser snapshot -i
agent-browser get text @e5 # Get specific element text
agent-browser get text body > page.txt # Get all page text
# JSON output for parsing
agent-browser snapshot -i --json
agent-browser get text @e1 --jsonParallel Sessions
agent-browser --session site1 open https://site-a.com
agent-browser --session site2 open https://site-b.com
agent-browser --session site1 snapshot -i
agent-browser --session site2 snapshot -i
agent-browser session listVisual Browser (Debugging)
agent-browser --headed open https://example.com
agent-browser highlight @e1 # Highlight element
agent-browser record start demo.webm # Record sessionLocal Files (PDFs, HTML)
# Open local files with file:// URLs
agent-browser --allow-file-access open file:///path/to/document.pdf
agent-browser --allow-file-access open file:///path/to/page.html
agent-browser screenshot output.pngiOS Simulator (Mobile Safari)
# List available iOS simulators
agent-browser device list
# Launch Safari on a specific device
agent-browser -p ios --device "iPhone 16 Pro" open https://example.com
# Same workflow as desktop - snapshot, interact, re-snapshot
agent-browser -p ios snapshot -i
agent-browser -p ios tap @e1 # Tap (alias for click)
agent-browser -p ios fill @e2 "text"
agent-browser -p ios swipe up # Mobile-specific gesture
# Take screenshot
agent-browser -p ios screenshot mobile.png
# Close session (shuts down simulator)
agent-browser -p ios closeRequirements: macOS with Xcode, Appium (npm install -g appium && appium driver install xcuitest)
Real devices: Works with physical iOS devices if pre-configured. Use --device "<UDID>" where UDID is from xcrun xctrace list devices.
Ref Lifecycle (Important)
Refs (@e1, @e2, etc.) are invalidated when the page changes. Always re-snapshot after:
- Clicking links or buttons that navigate
- Form submissions
- Dynamic content loading (dropdowns, modals)
agent-browser click @e5 # Navigates to new page
agent-browser snapshot -i # MUST re-snapshot
agent-browser click @e1 # Use new refsSemantic Locators (Alternative to Refs)
When refs are unavailable or unreliable, use semantic locators:
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" clickDeep-Dive Documentation
| Reference | When to Use |
| references/commands.md | Full command reference with all options |
| references/snapshot-refs.md | Ref lifecycle, invalidation rules, troubleshooting |
| references/session-management.md | Parallel sessions, state persistence, concurrent scraping |
| references/authentication.md | Login flows, OAuth, 2FA handling, state reuse |
| references/video-recording.md | Recording workflows for debugging and documentation |
| references/proxy-support.md | Proxy configuration, geo-testing, rotating proxies |
Ready-to-Use Templates
| Template | Description |
| templates/form-automation.sh | Form filling with validation |
| templates/authenticated-session.sh | Login once, reuse state |
| templates/capture-workflow.sh | Content extraction with screenshots |
./templates/form-automation.sh https://example.com/form
./templates/authenticated-session.sh https://app.example.com/login
./templates/capture-workflow.sh https://example.com ./outputDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

