agent-browser 0.11.0 → 0.11.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +17 -0
- package/bin/agent-browser-darwin-arm64 +0 -0
- package/bin/agent-browser-darwin-x64 +0 -0
- package/bin/agent-browser-linux-arm64 +0 -0
- package/bin/agent-browser-linux-x64 +0 -0
- package/bin/agent-browser-win32-x64.exe +0 -0
- package/package.json +1 -1
- package/skills/agent-browser/SKILL.md +17 -0
package/README.md
CHANGED
|
@@ -543,6 +543,23 @@ agent-browser fill @e3 "input text"
|
|
|
543
543
|
agent-browser snapshot -i --json
|
|
544
544
|
```
|
|
545
545
|
|
|
546
|
+
### Command Chaining
|
|
547
|
+
|
|
548
|
+
Commands can be chained with `&&` in a single shell invocation. The browser persists via a background daemon, so chaining is safe and more efficient:
|
|
549
|
+
|
|
550
|
+
```bash
|
|
551
|
+
# Open, wait for load, and snapshot in one call
|
|
552
|
+
agent-browser open example.com && agent-browser wait --load networkidle && agent-browser snapshot -i
|
|
553
|
+
|
|
554
|
+
# Chain multiple interactions
|
|
555
|
+
agent-browser fill @e1 "user@example.com" && agent-browser fill @e2 "pass" && agent-browser click @e3
|
|
556
|
+
|
|
557
|
+
# Navigate and screenshot
|
|
558
|
+
agent-browser open example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png
|
|
559
|
+
```
|
|
560
|
+
|
|
561
|
+
Use `&&` when you don't need intermediate output. Run commands separately when you need to parse output first (e.g., snapshot to discover refs before interacting).
|
|
562
|
+
|
|
546
563
|
## Headed Mode
|
|
547
564
|
|
|
548
565
|
Show the browser window for debugging:
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
package/package.json
CHANGED
|
@@ -27,6 +27,23 @@ agent-browser wait --load networkidle
|
|
|
27
27
|
agent-browser snapshot -i # Check result
|
|
28
28
|
```
|
|
29
29
|
|
|
30
|
+
## Command Chaining
|
|
31
|
+
|
|
32
|
+
Commands can be chained with `&&` in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.
|
|
33
|
+
|
|
34
|
+
```bash
|
|
35
|
+
# Chain open + wait + snapshot in one call
|
|
36
|
+
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i
|
|
37
|
+
|
|
38
|
+
# Chain multiple interactions
|
|
39
|
+
agent-browser fill @e1 "user@example.com" && agent-browser fill @e2 "password123" && agent-browser click @e3
|
|
40
|
+
|
|
41
|
+
# Navigate and capture
|
|
42
|
+
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
**When to chain:** Use `&&` when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).
|
|
46
|
+
|
|
30
47
|
## Essential Commands
|
|
31
48
|
|
|
32
49
|
```bash
|