@monoes/monomindcli 1.10.31 → 1.10.33

package/.claude/skills/monomind/browse.md

@@ -1,6 +1,6 @@
 ---
 name: monomind:browse
-description: State-of-the-art browser automation skill for UI testing, web scraping, and agent-driven navigation using agent-browser (v0.27+). Token-optimized with ref-based element selection, batch execution, KV-cache prompt ordering, on-demand screenshots, and full monomind memory integration.
+description: State-of-the-art browser automation skill for UI testing, web scraping, and agent-driven navigation using monomind browse (built-in TypeScript CDP client). Token-optimized with ref-based element selection, batch execution, KV-cache prompt ordering, on-demand screenshots, and full monomind memory integration.
 version: 2.0.0
 triggers:
   - /browse
@@ -22,12 +22,12 @@ triggers:
 tools:
   - Bash
 requires:
-  - agent-browser >= 0.25.4
+  - monomind >= 1.0.0
 ---
 
 # monomind:browse
 
-State-of-the-art browser automation using agent-browser. Optimized for minimal token consumption, maximum test coverage, and deep monomind integration.
+State-of-the-art browser automation using monomind browse. Optimized for minimal token consumption, maximum test coverage, and deep monomind integration.
 
 ---
 
@@ -35,14 +35,14 @@ State-of-the-art browser automation using agent-browser. Optimized for minimal t
 
 ```bash
 # Install
-npm install -g agent-browser
+# monomind browse is built-in — no install needed
 
 # Download Chrome (first time only)
-agent-browser install
+# no install needed
 
 # Verify
-agent-browser --version   # should be >= 0.25.4
-agent-browser doctor      # check all systems
+npx monomind browse --version   # should be >= 0.25.4
+npx monomind browse doctor      # check all systems
 ```
 
 ---
@@ -51,13 +51,13 @@ agent-browser doctor      # check all systems
 
 These rules are non-negotiable. Violating them wastes tokens and degrades performance.
 
-1. **Batch multi-step flows** — Use `agent-browser batch` to execute sequences in a single process invocation. Eliminates per-command startup overhead.
-2. **Snapshot with `-i` flag** — Interactive-only snapshots are 93% smaller than full trees. Never call `agent-browser snapshot` without `-i` unless you need to understand full page structure.
+1. **Batch multi-step flows** — Use `monomind browse batch` to execute sequences in a single process invocation. Eliminates per-command startup overhead.
+2. **Snapshot with `-i` flag** — Interactive-only snapshots are 93% smaller than full trees. Never call `monomind browse snapshot` without `-i` unless you need to understand full page structure.
 3. **Reuse refs** — After a snapshot, refs (`@e1`, `@e2`) are stable for the current page. Do NOT re-snapshot unless the page changed. One snapshot per page-state.
-4. **On-demand screenshots only** — Screenshots add ~800ms and ~1500 tokens as images. Only call `agent-browser screenshot` when: element not in a11y tree, visual verification is required, or the task explicitly needs visual proof.
-5. **Use batch for read-only chains** — `agent-browser open url && agent-browser snapshot -i` is two process starts. `agent-browser batch "open url" "snapshot -i"` is one.
-6. **Scope snapshots** — When testing a form or component, use `agent-browser snapshot -i -s "#form-id"` to scope to that subtree only.
-7. **Prefer `wait --text` over polling** — Never sleep and re-snapshot. Use `agent-browser wait --text "Expected"` or `wait --url "**pattern"`.
+4. **On-demand screenshots only** — Screenshots add ~800ms and ~1500 tokens as images. Only call `monomind browse screenshot` when: element not in a11y tree, visual verification is required, or the task explicitly needs visual proof.
+5. **Use batch for read-only chains** — `npx monomind browse open url` then `snapshot -i` is two process starts. `monomind browse batch "open url" "snapshot -i"` is one.
+6. **Scope snapshots** — When testing a form or component, use `monomind browse snapshot -i "#form-id"` to scope to that subtree only.
+7. **Prefer `wait --text` over polling** — Never sleep and re-snapshot. Use `monomind browse wait --text "Expected"` or `wait --url "**pattern"`.
 
 ---
 
@@ -71,22 +71,22 @@ OPEN → SNAPSHOT -i → ACT (by ref) → SNAPSHOT -i (if page changed) → VERI
 
 ```bash
 # Batch: open + snapshot in one call
-agent-browser batch "open https://app.example.com/login" "snapshot -i"
+npx monomind browse batch "open https://app.example.com/login" "snapshot -i"
 # → snapshot output: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Sign In" [ref=e3]
 
-agent-browser fill @e1 "user@test.com"
-agent-browser fill @e2 "SecurePass123!"
-agent-browser click @e3
-agent-browser wait --url "**/dashboard" --timeout 8000
+npx monomind browse fill @e1 "user@test.com"
+npx monomind browse fill @e2 "SecurePass123!"
+npx monomind browse click @e3
+npx monomind browse wait --url "**/dashboard" --timeout 8000
 
 # Re-snapshot only because URL changed (new page state)
-agent-browser snapshot -i
+npx monomind browse snapshot -i
 ```
 
 ### Full batch mode (most token-efficient)
 
 ```bash
-agent-browser batch \
+npx monomind browse batch \
   "open https://app.example.com/login" \
   "snapshot -i" \
   "fill @e1 user@test.com" \
@@ -107,7 +107,7 @@ echo '[
   ["click", "@e3"],
   ["wait", "--url", "**/dashboard"],
   ["snapshot", "-i"]
-]' | agent-browser batch --json --bail
+]' | monomind browse batch --json --bail
 ```
 
 ---
@@ -117,27 +117,27 @@ echo '[
 ### Navigation
 
 ```bash
-agent-browser open <url>              # Launch + navigate (aliases: goto, navigate)
-agent-browser open                    # Launch on about:blank (for pre-nav setup)
-agent-browser back                    # Go back
-agent-browser forward                 # Go forward
-agent-browser reload                  # Reload
-agent-browser pushstate <url>         # SPA client-side nav (Next.js, Remix, etc.)
-agent-browser close                   # Close browser
-agent-browser close --all             # Close all sessions
+npx monomind browse open <url>              # Launch + navigate (aliases: goto, navigate)
+npx monomind browse open                    # Launch on about:blank (for pre-nav setup)
+npx monomind browse back                    # Go back
+npx monomind browse forward                 # Go forward
+npx monomind browse reload                  # Reload
+npx monomind browse pushstate <url>         # SPA client-side nav (Next.js, Remix, etc.)
+npx monomind browse close                   # Close browser
+npx monomind browse close --all             # Close all sessions
 ```
 
 ### Snapshot (primary observation tool)
 
 ```bash
-agent-browser snapshot                # Full accessibility tree + refs
-agent-browser snapshot -i             # Interactive elements only (USE THIS BY DEFAULT)
-agent-browser snapshot -i --urls      # Include href URLs for links
-agent-browser snapshot -c             # Compact (strip empty structural nodes)
-agent-browser snapshot -d 3           # Limit depth to 3 levels
-agent-browser snapshot -s "#main"     # Scope to CSS selector
-agent-browser snapshot -i -c -d 5    # Combined: compact interactive, max depth 5
-agent-browser snapshot --json         # JSON output for programmatic use
+npx monomind browse snapshot                # Full accessibility tree + refs
+npx monomind browse snapshot -i             # Interactive elements only (USE THIS BY DEFAULT)
+npx monomind browse snapshot -i --urls      # Include href URLs for links
+npx monomind browse snapshot -c             # Compact (strip empty structural nodes)
+npx monomind browse snapshot -d 3           # Limit depth to 3 levels
+npx monomind browse snapshot -s "#main"     # Scope to CSS selector
+npx monomind browse snapshot -i -c -d 5    # Combined: compact interactive, max depth 5
+npx monomind browse snapshot --json         # JSON output for programmatic use
 ```
 
 **Output example:**
@@ -152,138 +152,138 @@ agent-browser snapshot --json         # JSON output for programmatic use
 
 ```bash
 # Primary: use @ref from snapshot (fastest, no DOM re-query)
-agent-browser click @e3
-agent-browser fill @e1 "value"
-agent-browser dblclick @e5
-agent-browser hover @e6
-agent-browser check @e7               # checkbox
-agent-browser uncheck @e8
-agent-browser select @e9 "Option A"
-agent-browser focus @e2
+npx monomind browse click @e3
+npx monomind browse fill @e1 "value"
+npx monomind browse dblclick @e5
+npx monomind browse hover @e6
+npx monomind browse check @e7               # checkbox
+npx monomind browse uncheck @e8
+npx monomind browse select @e9 "Option A"
+npx monomind browse focus @e2
 
 # Keyboard
-agent-browser press Enter
-agent-browser press Tab
-agent-browser press "Control+a"
-agent-browser keyboard type "hello world"      # real keystrokes
-agent-browser keyboard inserttext "hello"      # insert without key events
-agent-browser keydown Shift
-agent-browser keyup Shift
+npx monomind browse press Enter
+npx monomind browse press Tab
+npx monomind browse press "Control+a"
+npx monomind browse keyboard type "hello world"      # real keystrokes
+npx monomind browse keyboard inserttext "hello"      # insert without key events
+npx monomind browse keydown Shift
+npx monomind browse keyup Shift
 
 # Drag & drop
-agent-browser drag @e1 @e2
-agent-browser upload @e3 /path/to/file.pdf
+npx monomind browse drag @e1 @e2
+npx monomind browse upload @e3 /path/to/file.pdf
 
 # Scroll
-agent-browser scroll down 500         # scroll 500px down
-agent-browser scroll up
-agent-browser scrollintoview @e10
-agent-browser scroll down --selector "#feed"
+npx monomind browse scroll down 500         # scroll 500px down
+npx monomind browse scroll up
+npx monomind browse scrollintoview @e10
+npx monomind browse scroll down --selector "#feed"
 ```
 
 ### Semantic locators (fallback when no ref available)
 
 ```bash
-agent-browser find role button click --name "Submit"
-agent-browser find text "Sign In" click
-agent-browser find label "Email" fill "test@test.com"
-agent-browser find placeholder "Search..." fill "query"
-agent-browser find testid "submit-btn" click
-agent-browser find first ".item" click
-agent-browser find nth 2 "a" text
+npx monomind browse find role button click --name "Submit"
+npx monomind browse find text "Sign In" click
+npx monomind browse find label "Email" fill "test@test.com"
+npx monomind browse find placeholder "Search..." fill "query"
+npx monomind browse find testid "submit-btn" click
+npx monomind browse find first ".item" click
+npx monomind browse find nth 2 "a" text
 ```
 
 ### Wait (never sleep/poll manually)
 
 ```bash
-agent-browser wait 500                         # ms delay (use sparingly)
-agent-browser wait "#spinner" --state hidden   # wait for element to hide
-agent-browser wait --text "Success"            # wait for text to appear
-agent-browser wait --url "**/dashboard"        # wait for URL pattern
-agent-browser wait --load networkidle          # wait for network idle
-agent-browser wait --fn "window.ready === true"  # wait for JS condition
-agent-browser wait --fn "!document.body.innerText.includes('Loading')"
+npx monomind browse wait 500                         # ms delay (use sparingly)
+npx monomind browse wait "#spinner" --state hidden   # wait for element to hide
+npx monomind browse wait --text "Success"            # wait for text to appear
+npx monomind browse wait --url "**/dashboard"        # wait for URL pattern
+npx monomind browse wait --load networkidle          # wait for network idle
+npx monomind browse wait --fn "window.ready === true"  # wait for JS condition
+npx monomind browse wait --fn "!document.body.innerText.includes('Loading')"
 ```
 
 ### Read state
 
 ```bash
-agent-browser get text @e1           # text content
-agent-browser get html @e2           # innerHTML
-agent-browser get value @e3          # input value
-agent-browser get attr @e4 "href"    # attribute
-agent-browser get title              # page title
-agent-browser get url                # current URL
-agent-browser get count ".item"      # count matching elements
-agent-browser get box @e1            # bounding box
-agent-browser get styles @e1         # computed CSS styles
+npx monomind browse get text @e1           # text content
+npx monomind browse get html @e2           # innerHTML
+npx monomind browse get value @e3          # input value
+npx monomind browse get attr @e4 "href"    # attribute
+npx monomind browse get title              # page title
+npx monomind browse get url                # current URL
+npx monomind browse get count ".item"      # count matching elements
+npx monomind browse get box @e1            # bounding box
+npx monomind browse get styles @e1         # computed CSS styles
 
-agent-browser is visible @e1         # boolean check
-agent-browser is enabled @e1
-agent-browser is checked @e1
+npx monomind browse is visible @e1         # boolean check
+npx monomind browse is enabled @e1
+npx monomind browse is checked @e1
 ```
 
 ### Screenshots (use sparingly)
 
 ```bash
-agent-browser screenshot                        # auto-path in /tmp
-agent-browser screenshot page.png              # specific path
-agent-browser screenshot --full full-page.png  # full-page scroll capture
-agent-browser screenshot --annotate            # numbered refs overlaid → use with visual models
-agent-browser pdf report.pdf                   # save as PDF
+npx monomind browse screenshot                        # auto-path in /tmp
+npx monomind browse screenshot page.png              # specific path
+npx monomind browse screenshot --full full-page.png  # full-page scroll capture
+npx monomind browse screenshot --annotate            # numbered refs overlaid → use with visual models
+npx monomind browse pdf report.pdf                   # save as PDF
 ```
 
 **Annotated screenshot pattern** (for visual debugging or multimodal LLMs):
 ```bash
-agent-browser screenshot --annotate
+npx monomind browse screenshot --annotate
 # Output: [1] @e1 button "Submit"  [2] @e2 link "Home"  [3] @e3 textbox "Email"
 # Now refs are cached — interact immediately without re-snapshot
-agent-browser click @e1
+npx monomind browse click @e1
 ```
 
 ### Diff (regression testing)
 
 ```bash
-agent-browser diff snapshot                           # current vs last snapshot
-agent-browser diff snapshot --baseline ./before.txt   # vs saved file
-agent-browser diff snapshot -s "#main" --compact      # scoped diff
-agent-browser diff screenshot --baseline before.png   # pixel diff
-agent-browser diff screenshot --baseline b.png -t 0.2 # threshold 0–1
-agent-browser diff url https://v1.com https://v2.com  # compare two URLs
-agent-browser diff url https://v1.com https://v2.com --screenshot  # + visual
+npx monomind browse diff snapshot                           # current vs last snapshot
+npx monomind browse diff snapshot --baseline ./before.txt   # vs saved file
+npx monomind browse diff snapshot -s "#main" --compact      # scoped diff
+npx monomind browse diff screenshot --baseline before.png   # pixel diff
+npx monomind browse diff screenshot --baseline b.png -t 0.2 # threshold 0–1
+npx monomind browse diff url https://v1.com https://v2.com  # compare two URLs
+npx monomind browse diff url https://v1.com https://v2.com --screenshot  # + visual
 ```
 
 ### Tabs & multi-tab
 
 ```bash
-agent-browser tab                          # list all tabs
-agent-browser tab new https://example.com  # new tab
-agent-browser tab new --label docs https://docs.example.com  # named tab
-agent-browser tab docs                     # switch by label
-agent-browser tab t2                       # switch by stable id
-agent-browser tab close docs               # close by label
-agent-browser window new                   # new window
-agent-browser frame "#iframe-id"           # switch to iframe
-agent-browser frame main                   # back to main frame
+npx monomind browse tab                          # list all tabs
+npx monomind browse tab new https://example.com  # new tab
+npx monomind browse tab new --label docs https://docs.example.com  # named tab
+npx monomind browse tab docs                     # switch by label
+npx monomind browse tab t2                       # switch by stable id
+npx monomind browse tab close docs               # close by label
+npx monomind browse window new                   # new window
+npx monomind browse frame "#iframe-id"           # switch to iframe
+npx monomind browse frame main                   # back to main frame
 ```
 
 **Multi-tab parallel test pattern:**
 ```bash
-agent-browser tab new --label app https://app.example.com
-agent-browser tab new --label docs https://docs.example.com
-agent-browser tab app
-agent-browser snapshot -i    # refs for app tab
-agent-browser click @e3
-agent-browser tab docs
-agent-browser snapshot -i    # refs for docs tab
+npx monomind browse tab new --label app https://app.example.com
+npx monomind browse tab new --label docs https://docs.example.com
+npx monomind browse tab app
+npx monomind browse snapshot -i    # refs for app tab
+npx monomind browse click @e3
+npx monomind browse tab docs
+npx monomind browse snapshot -i    # refs for docs tab
 ```
 
 ### Dialogs
 
 ```bash
-agent-browser dialog accept "confirmation text"
-agent-browser dialog dismiss
-agent-browser dialog status            # is a dialog currently open?
+npx monomind browse dialog accept "confirmation text"
+npx monomind browse dialog dismiss
+npx monomind browse dialog status            # is a dialog currently open?
 ```
 
 Note: `alert` and `beforeunload` are auto-accepted by default. `confirm` and `prompt` need explicit handling.
@@ -291,23 +291,23 @@ Note: `alert` and `beforeunload` are auto-accepted by default. `confirm` and `pr
 ### Network interception
 
 ```bash
-agent-browser network route "https://api.example.com/*" --abort    # block endpoint
-agent-browser network route "*" --abort --resource-type script      # block all JS
-agent-browser network route "https://api/*" --body '{"data":[]}'   # mock response
-agent-browser network unroute "https://api.example.com/*"
-agent-browser network requests                          # view tracked requests
-agent-browser network requests --filter api             # filter by URL substring
-agent-browser network requests --type xhr,fetch         # filter by type
-agent-browser network requests --method POST
-agent-browser network requests --status 2xx
-agent-browser network request <requestId>               # full request/response
-agent-browser network har start                         # record HAR
-agent-browser network har stop output.har               # stop + save
+npx monomind browse network route "https://api.example.com/*" --abort    # block endpoint
+npx monomind browse network route "*" --abort --resource-type script      # block all JS
+npx monomind browse network route "https://api/*" --body '{"data":[]}'   # mock response
+npx monomind browse network unroute "https://api.example.com/*"
+npx monomind browse network requests                          # view tracked requests
+npx monomind browse network requests --filter api             # filter by URL substring
+npx monomind browse network requests --type xhr,fetch         # filter by type
+npx monomind browse network requests --method POST
+npx monomind browse network requests --status 2xx
+npx monomind browse network request <requestId>               # full request/response
+npx monomind browse network har start                         # record HAR
+npx monomind browse network har stop output.har               # stop + save
 ```
 
 **Pre-nav setup pattern** (set network routes BEFORE navigating):
 ```bash
-agent-browser batch \
+npx monomind browse batch \
   '["open"]' \
   '["network", "route", "*", "--abort", "--resource-type", "script"]' \
   '["cookies", "set", "--curl", "auth.curl", "--domain", "localhost"]' \
@@ -317,46 +317,46 @@ agent-browser batch \
 ### Cookies & storage
 
 ```bash
-agent-browser cookies                              # get all cookies
-agent-browser cookies set name value              # set cookie
-agent-browser cookies set --curl cookies.curl     # import from cURL dump / JSON / header string
-agent-browser cookies clear
+npx monomind browse cookies                              # get all cookies
+npx monomind browse cookies set name value              # set cookie
+npx monomind browse cookies set --curl cookies.curl     # import from cURL dump / JSON / header string
+npx monomind browse cookies clear
 
-agent-browser storage local                        # get localStorage
-agent-browser storage local myKey                  # get specific key
-agent-browser storage local set myKey myValue      # set
-agent-browser storage local clear
-agent-browser storage session                      # sessionStorage (same API)
+npx monomind browse storage local                        # get localStorage
+npx monomind browse storage local myKey                  # get specific key
+npx monomind browse storage local set myKey myValue      # set
+npx monomind browse storage local clear
+npx monomind browse storage session                      # sessionStorage (same API)
 ```
 
 ### Browser settings
 
 ```bash
-agent-browser set viewport 1280 720 2             # width height deviceScaleFactor
-agent-browser set device "iPhone 15 Pro"          # device emulation
-agent-browser set geo 37.7749 -122.4194           # geolocation
-agent-browser set offline on                      # offline mode
-agent-browser set headers '{"Authorization":"Bearer tok"}'  # global headers
-agent-browser set credentials user pass           # HTTP basic auth
-agent-browser set media dark                      # color scheme
+npx monomind browse set viewport 1280 720 2             # width height deviceScaleFactor
+npx monomind browse set device "iPhone 15 Pro"          # device emulation
+npx monomind browse set geo 37.7749 -122.4194           # geolocation
+npx monomind browse set offline on                      # offline mode
+npx monomind browse set headers '{"Authorization":"Bearer tok"}'  # global headers
+npx monomind browse set credentials user pass           # HTTP basic auth
+npx monomind browse set media dark                      # color scheme
 ```
 
 ### Clipboard
 
 ```bash
-agent-browser clipboard read
-agent-browser clipboard write "Hello"
-agent-browser clipboard copy      # Ctrl+C
-agent-browser clipboard paste     # Ctrl+V
+npx monomind browse clipboard read
+npx monomind browse clipboard write "Hello"
+npx monomind browse clipboard copy      # Ctrl+C
+npx monomind browse clipboard paste     # Ctrl+V
 ```
 
 ### Mouse (raw control, use only when refs/semantic locators fail)
 
 ```bash
-agent-browser mouse move 100 200
-agent-browser mouse down left
-agent-browser mouse up left
-agent-browser mouse wheel 100 0   # dy dx
+npx monomind browse mouse move 100 200
+npx monomind browse mouse down left
+npx monomind browse mouse up left
+npx monomind browse mouse wheel 100 0   # dy dx
 ```
 
 ### React DevTools (v0.27+)
@@ -365,86 +365,86 @@ Requires launching with `--enable react-devtools`:
 
 ```bash
 # Launch with hook installed
-agent-browser open --enable react-devtools https://your-react-app.com
+npx monomind browse open --enable react-devtools https://your-react-app.com
 
 # Inspect component tree
-agent-browser react tree                         # full component hierarchy
-agent-browser react inspect 5                    # fiber ID → props, hooks, state, source
-agent-browser react renders start                # begin render profiling
-agent-browser react renders stop                 # print profile (mount/re-render counts)
-agent-browser react renders stop --json          # JSON output
-agent-browser react suspense                     # Suspense boundaries + root-cause classifier
-agent-browser react suspense --only-dynamic      # hide static boundaries
+npx monomind browse react tree                         # full component hierarchy
+npx monomind browse react inspect 5                    # fiber ID → props, hooks, state, source
+npx monomind browse react renders start                # begin render profiling
+npx monomind browse react renders stop                 # print profile (mount/re-render counts)
+npx monomind browse react renders stop --json          # JSON output
+npx monomind browse react suspense                     # Suspense boundaries + root-cause classifier
+npx monomind browse react suspense --only-dynamic      # hide static boundaries
 ```
 
 ### Web Vitals (framework-agnostic)
 
 ```bash
-agent-browser vitals                             # LCP, CLS, TTFB, FCP, INP + React hydration
-agent-browser vitals https://example.com         # test specific URL
-agent-browser vitals --json                      # JSON output
+npx monomind browse vitals                             # LCP, CLS, TTFB, FCP, INP + React hydration
+npx monomind browse vitals https://example.com         # test specific URL
+npx monomind browse vitals --json                      # JSON output
 ```
 
 ### Tracing & profiling
 
 ```bash
-agent-browser trace start trace.zip             # start Chrome trace
-agent-browser trace stop trace.zip              # stop and save
-agent-browser profiler start                    # DevTools profiler
-agent-browser profiler stop profile.json        # stop and save
+npx monomind browse trace start trace.zip             # start Chrome trace
+npx monomind browse trace stop trace.zip              # stop and save
+npx monomind browse profiler start                    # DevTools profiler
+npx monomind browse profiler stop profile.json        # stop and save
 
-agent-browser console                           # browser console messages
-agent-browser console --json                    # structured CDP output
-agent-browser console --clear
-agent-browser errors                            # uncaught JS exceptions
-agent-browser errors --clear
+npx monomind browse console                           # browser console messages
+npx monomind browse console --json                    # structured CDP output
+npx monomind browse console --clear
+npx monomind browse errors                            # uncaught JS exceptions
+npx monomind browse errors --clear
 ```
 
 ### Sessions & auth
 
 ```bash
 # Isolated sessions (each has own browser, cookies, history)
-agent-browser --session agent1 open site-a.com
-agent-browser --session agent2 open site-b.com
-agent-browser session list
+npx monomind browse --session agent1 open site-a.com
+npx monomind browse --session agent2 open site-b.com
+npx monomind browse session list
 
 # Persist state across restarts
-agent-browser --session-name myapp open app.example.com
-# → auto-saves to ~/.agent-browser/sessions/myapp
+npx monomind browse --session-name myapp open app.example.com
+# → auto-saves to ~/.monomind/browser-sessions/myapp
 
 # Reuse existing Chrome login
-agent-browser profiles                          # list Chrome profiles
-agent-browser --profile Default open gmail.com
+npx monomind browse profiles                          # list Chrome profiles
+npx monomind browse --profile Default open gmail.com
 
 # Save / load state
-agent-browser state save ./auth.json            # save cookies + localStorage
-agent-browser state load ./auth.json
-agent-browser --state ./auth.json open https://app.example.com/dashboard
+npx monomind browse state save ./auth.json            # save cookies + localStorage
+npx monomind browse state load ./auth.json
+npx monomind browse --state ./auth.json open https://app.example.com/dashboard
 
 # Auth vault (credentials never sent to LLM)
-echo "mypassword" | agent-browser auth save github --url https://github.com/login --username me --password-stdin
-agent-browser auth login github
+echo "mypassword" | monomind browse auth save github --url https://github.com/login --username me --password-stdin
+npx monomind browse auth login github
 
 # Encrypted state at rest
 export AGENT_BROWSER_ENCRYPTION_KEY=<64-char-hex>
-agent-browser --session-name secure open example.com
+npx monomind browse --session-name secure open example.com
 ```
 
 ### Dashboard (observability)
 
 ```bash
-agent-browser dashboard start              # port 4848
-agent-browser dashboard start --port 8080
-agent-browser dashboard stop
+npx monomind browse dashboard start              # port 4848
+npx monomind browse dashboard start --port 8080
+npx monomind browse dashboard stop
 # → open http://localhost:4848 for live viewport + activity feed + AI chat
 ```
 
 ### Init scripts
 
 ```bash
-agent-browser open --init-script ./setup.js https://app.example.com
-agent-browser addinitscript "window.__TEST__ = true"
-agent-browser removeinitscript <identifier>
+npx monomind browse open --init-script ./setup.js https://app.example.com
+npx monomind browse addinitscript "window.__TEST__ = true"
+npx monomind browse removeinitscript <identifier>
 ```
 
 ### iOS / Mobile (real Safari)
@@ -452,14 +452,14 @@ agent-browser removeinitscript <identifier>
 Requires: `npm install -g appium && appium driver install xcuitest`
 
 ```bash
-agent-browser device list
-agent-browser -p ios --device "iPhone 15 Pro" open https://example.com
-agent-browser -p ios snapshot -i
-agent-browser -p ios tap @e1
-agent-browser -p ios fill @e2 "text"
-agent-browser -p ios swipe up
-agent-browser -p ios screenshot mobile.png
-agent-browser -p ios close
+npx monomind browse device list
+npx monomind browse -p ios --device "iPhone 15 Pro" open https://example.com
+npx monomind browse -p ios snapshot -i
+npx monomind browse -p ios tap @e1
+npx monomind browse -p ios fill @e2 "text"
+npx monomind browse -p ios swipe up
+npx monomind browse -p ios screenshot mobile.png
+npx monomind browse -p ios close
 ```
 
 ### Cloud providers
@@ -477,18 +477,18 @@ All commands work identically regardless of provider.
 ### Streaming
 
 ```bash
-agent-browser stream status           # see WebSocket port
-agent-browser stream enable --port 9223
-agent-browser stream disable
+npx monomind browse stream status           # see WebSocket port
+npx monomind browse stream enable --port 9223
+npx monomind browse stream disable
 ```
 
 ### CDP / Electron apps
 
 ```bash
-agent-browser connect 9222            # connect to port, persist for session
-agent-browser --cdp 9222 snapshot     # per-command
-agent-browser --cdp wss://remote/cdp snapshot
-agent-browser --auto-connect snapshot  # auto-discover running Chrome
+npx monomind browse connect 9222            # connect to port, persist for session
+npx monomind browse --cdp 9222 snapshot     # per-command
+npx monomind browse --cdp wss://remote/cdp snapshot
+npx monomind browse --auto-connect snapshot  # auto-discover running Chrome
 ```
 
 ---
@@ -498,130 +498,130 @@ agent-browser --auto-connect snapshot  # auto-discover running Chrome
 ### Login / Auth
 
 ```bash
-agent-browser batch \
+npx monomind browse batch \
   "open https://app.example.com/login" \
   "snapshot -i"
 # identify refs from output, then:
-agent-browser fill @e[email] "user@test.com"
-agent-browser fill @e[password] "TestPass123!"
-agent-browser click @e[submit]
-agent-browser wait --url "**/dashboard" --timeout 8000
+npx monomind browse fill @e[email] "user@test.com"
+npx monomind browse fill @e[password] "TestPass123!"
+npx monomind browse click @e[submit]
+npx monomind browse wait --url "**/dashboard" --timeout 8000
 ```
 
 ### Form with validation
 
 ```bash
 # Test happy path
-agent-browser batch "open /form" "snapshot -i"
-agent-browser fill @e1 "John Doe"
-agent-browser fill @e2 "john@test.com"
-agent-browser select @e3 "Option A"
-agent-browser check @e4
-agent-browser click @e5
-agent-browser wait --text "submitted"
-agent-browser screenshot pass-form.png
+npx monomind browse batch "open /form" "snapshot -i"
+npx monomind browse fill @e1 "John Doe"
+npx monomind browse fill @e2 "john@test.com"
+npx monomind browse select @e3 "Option A"
+npx monomind browse check @e4
+npx monomind browse click @e5
+npx monomind browse wait --text "submitted"
+npx monomind browse screenshot pass-form.png
 
 # Test validation (empty submit)
-agent-browser reload
-agent-browser snapshot -i
-agent-browser click @e5                    # submit empty
-agent-browser wait --text "required"
-agent-browser snapshot -i                  # verify error messages
+npx monomind browse reload
+npx monomind browse snapshot -i
+npx monomind browse click @e5                    # submit empty
+npx monomind browse wait --text "required"
+npx monomind browse snapshot -i                  # verify error messages
 
 # Invalid email
-agent-browser fill @e2 "not-an-email"
-agent-browser click @e5
-agent-browser snapshot -i
+npx monomind browse fill @e2 "not-an-email"
+npx monomind browse click @e5
+npx monomind browse snapshot -i
 ```
 
 ### CRUD
 
 ```bash
 # Create
-agent-browser click @e[add]
-agent-browser fill @e[name] "New Item"
-agent-browser click @e[save]
-agent-browser wait --text "New Item"
+npx monomind browse click @e[add]
+npx monomind browse fill @e[name] "New Item"
+npx monomind browse click @e[save]
+npx monomind browse wait --text "New Item"
 
 # Update
-agent-browser click @e[edit]
-agent-browser fill @e[name] "Updated Item"
-agent-browser click @e[save]
-agent-browser wait --text "Updated Item"
+npx monomind browse click @e[edit]
+npx monomind browse fill @e[name] "Updated Item"
+npx monomind browse click @e[save]
+npx monomind browse wait --text "Updated Item"
 
 # Delete
-agent-browser click @e[delete]
-agent-browser wait --text "Are you sure"
-agent-browser click @e[confirm]
-agent-browser wait --fn "!document.body.innerText.includes('Updated Item')"
+npx monomind browse click @e[delete]
+npx monomind browse wait --text "Are you sure"
+npx monomind browse click @e[confirm]
+npx monomind browse wait --fn "!document.body.innerText.includes('Updated Item')"
 ```
 
 ### Multi-step wizard
 
 ```bash
 # Step 1
-agent-browser batch "open /wizard" "snapshot -i"
-agent-browser fill @e1 "value"
-agent-browser click @e[next]
-agent-browser wait --text "Step 2"
+npx monomind browse batch "open /wizard" "snapshot -i"
+npx monomind browse fill @e1 "value"
+npx monomind browse click @e[next]
+npx monomind browse wait --text "Step 2"
 
 # Step 2
-agent-browser snapshot -i
-agent-browser select @e2 "choice"
-agent-browser click @e[next]
+npx monomind browse snapshot -i
+npx monomind browse select @e2 "choice"
+npx monomind browse click @e[next]
 
 # Step 3 — verify summary
-agent-browser snapshot -i
-agent-browser get text @e[summary]
-agent-browser click @e[confirm]
-agent-browser wait --text "Complete"
+npx monomind browse snapshot -i
+npx monomind browse get text @e[summary]
+npx monomind browse click @e[confirm]
+npx monomind browse wait --text "Complete"
 ```
 
 ### Regression test (diff baseline)
 
 ```bash
 # Save baseline
-agent-browser open https://app.example.com
-agent-browser snapshot -i > baseline.txt
+npx monomind browse open https://app.example.com
+npx monomind browse snapshot -i > baseline.txt
 
 # After a deploy, compare:
-agent-browser open https://app.example.com
-agent-browser diff snapshot --baseline ./baseline.txt
+npx monomind browse open https://app.example.com
+npx monomind browse diff snapshot --baseline ./baseline.txt
 ```
 
 ### API mocking
 
 ```bash
 # Mock API response, test UI reaction
-agent-browser batch \
+npx monomind browse batch \
   '["open"]' \
   '["network", "route", "https://api.example.com/users", "--body", "{\"data\":[]}"]' \
   '["navigate", "https://app.example.com/users"]'
-agent-browser snapshot -i
+npx monomind browse snapshot -i
 # → verify "No users found" empty state renders correctly
 ```
 
 ### React app deep inspection
 
 ```bash
-agent-browser open --enable react-devtools https://your-react-app.com
-agent-browser react tree
-agent-browser vitals --json
-agent-browser react renders start
+npx monomind browse open --enable react-devtools https://your-react-app.com
+npx monomind browse react tree
+npx monomind browse vitals --json
+npx monomind browse react renders start
 # ... trigger user interactions ...
-agent-browser react renders stop
-agent-browser react suspense --only-dynamic
+npx monomind browse react renders stop
+npx monomind browse react suspense --only-dynamic
 ```
 
 ---
 
-## Configuration (agent-browser.json)
+## Configuration
 
 Create in project root for persistent defaults:
 
 ```json
 {
-  "$schema": "https://agent-browser.dev/schema.json",
+  "$schema": "https://monomind.dev/schema.json",
   "maxOutput": 50000,
   "contentBoundaries": true,
   "idleTimeout": "5m",
@@ -651,7 +651,7 @@ AGENT_BROWSER_IDLE_TIMEOUT_MS=300000  # daemon auto-shutdown after idle
 AGENT_BROWSER_CONTENT_BOUNDARIES=1   # LLM-safe output delimiters
 AGENT_BROWSER_HEADED=1               # visible browser (debugging)
 AGENT_BROWSER_STREAM_PORT=9223       # fixed WebSocket stream port
-AI_GATEWAY_API_KEY=gw_...            # for `agent-browser chat`
+# No API key needed — monomind browse is built-in
 AI_GATEWAY_MODEL=anthropic/claude-sonnet-4-6
 ```
 
@@ -686,10 +686,10 @@ npx monomind task create \
 
 ```bash
 # Once logged in:
-agent-browser state save .monomind/auth/<app>.json
+npx monomind browse state save .monomind/auth/<app>.json
 
 # Future sessions:
-agent-browser --state .monomind/auth/<app>.json open https://app.example.com
+npx monomind browse --state .monomind/auth/<app>.json open https://app.example.com
 ```
 
 ---
@@ -698,8 +698,8 @@ agent-browser --state .monomind/auth/<app>.json open https://app.example.com
 
 | Anti-pattern | Why | Fix |
 |---|---|---|
-| `agent-browser snapshot` (no `-i`) for every step | Full tree = 10–20x tokens | Use `snapshot -i` always |
-| Playwright MCP | 13,700-token schema tax before step 1 | Use agent-browser directly |
+| `monomind browse snapshot` (no `-i`) for every step | Full tree = 10–20x tokens | Use `snapshot -i` always |
+| Playwright MCP | 13,700-token schema tax before step 1 | Use monomind browse directly |
 | Screenshot every step | +800ms +1500 tokens each | Screenshot only on fail/visual-required |
 | Re-snapshot without page change | Wastes tokens | Reuse refs from last snapshot |
 | `sleep N` between actions | Slow, fragile | Use `wait --text`, `wait --url`, `wait --fn` |
@@ -711,8 +711,8 @@ agent-browser --state .monomind/auth/<app>.json open https://app.example.com
 ## Checklist
 
 When this skill is activated:
-- [ ] `agent-browser --version` — confirm >= 0.25.4 (or run `npm install -g agent-browser`)
-- [ ] `agent-browser doctor` — check Chrome + daemon health
+- [ ] `npx monomind browse --version` — confirm monomind is installed
+- [ ] `npx monomind doctor` — check system health
 - [ ] Get target URL from user if not provided
 - [ ] Use `batch "open <url>" "snapshot -i"` to start
 - [ ] Use refs (`@eN`) from snapshot output for all interactions