feat(text): 'get text' (no selector) defaults to cross-frame whole-page read

So an agent never silently misses iframed content (listing descriptions etc.)
without having to know the --all-frames flag. Single-frame pages are unchanged
(identical to the old body read); multi-frame pages now include child frames —
a strict superset. Skill + help updated to make the default and 'frames'/--main
discoverable.

cli/src/commands.rs

@@ -2463,16 +2463,16 @@ fn parse_get(rest: &[&str], id: &str) -> Result<Value, ParseError> {
             if main {
                 return Ok(json!({ "id": id, "action": "gettext", "main": true }));
             }
-            // `get text` with no selector returns the whole page's text (body) —
+            // `get text` with no selector reads the WHOLE PAGE and now defaults
-            // a common convenience; previously it errored without a selector
+            // to cross-frame aggregation, so an agent gets a page's iframed
-            // (issue #24-D).
+            // content (listing descriptions etc.) without having to know about
-            let sel = rest
+            // `--all-frames` (#27). On a single-frame page this is identical to
-                .iter()
+            // the old body read; multi-frame pages get the child frames too —
-                .skip(1)
+            // a strict superset. An explicit selector stays element-scoped.
-                .find(|a| !a.starts_with("--"))
+            match rest.iter().skip(1).find(|a| !a.starts_with("--")).copied() {
-                .copied()
+                Some(sel) => Ok(json!({ "id": id, "action": "gettext", "selector": sel })),
-                .unwrap_or("body");
+                None => Ok(json!({ "id": id, "action": "gettext", "allFrames": true })),
-            Ok(json!({ "id": id, "action": "gettext", "selector": sel }))
+            }
         }
         Some("html") => {
             let sel = rest.get(1).ok_or_else(|| ParseError::MissingArguments {
@@ -4830,15 +4830,21 @@ mod tests {
     }
 
     #[test]
-    fn test_get_text_defaults_to_body() {
+    fn test_get_text_defaults_to_all_frames() {
-        // `get text` with no selector now returns the whole page (body) instead
+        // `get text` with no selector now reads the whole page across ALL frames
-        // of erroring (issue #24-D).
+        // by default (#27), so iframed content isn't silently missed. (Was: a
+        // top-frame `body` read, #24-D.)
         let cmd = parse_command(&args("get text"), &default_flags()).unwrap();
         assert_eq!(cmd["action"], "gettext");
-        assert_eq!(cmd["selector"], "body");
+        assert_eq!(cmd["allFrames"], true);
-        // An explicit selector still wins.
+        assert!(cmd.get("selector").is_none());
+        // An explicit selector still wins and stays element-scoped.
         let cmd2 = parse_command(&args("get text h1"), &default_flags()).unwrap();
         assert_eq!(cmd2["selector"], "h1");
+        assert!(cmd2.get("allFrames").is_none());
+        // `text` top-level shortcut behaves the same.
+        let cmd3 = parse_command(&args("text"), &default_flags()).unwrap();
+        assert_eq!(cmd3["allFrames"], true);
     }
 
     #[test]

cli/src/output.rs

@@ -1959,8 +1959,7 @@ Usage: chrome-use get <subcommand> [args]
 Retrieves various types of information from elements or the page.
 
 Subcommands:
-  text <selector>            Get text content of element
+  text [selector]            Element text; no selector = WHOLE PAGE, all frames
-  text --all-frames          Aggregate text across ALL frames (incl. iframes)
   text --main                Main-content text only (skip nav/header/sidebar)
   html <selector>            Get inner HTML of element
   value <selector>           Get value of input element
@@ -1977,8 +1976,8 @@ Global Options:
   --session <name>     Use specific session
 
 Examples:
-  chrome-use get text @e1
+  chrome-use get text                  # whole page across ALL frames (default)
-  chrome-use get text --all-frames     # read iframed content (listing pages)
+  chrome-use get text @e1              # one element
   chrome-use get text --main           # main content, no nav/sidebar boilerplate
   chrome-use frames                    # list frames + where the text lives
   chrome-use get html "#content"
@@ -3190,7 +3189,7 @@ Navigation:
 
 Get Info:  chrome-use get <what> [selector]
   text, html, value, attr <name>, title, url, count, box, styles, cdp-url
-  text --all-frames (cross-frame), text --main (no boilerplate), frames (list)
+  text (no selector = whole page, all frames), text --main, frames (list)
 
 Check State:  chrome-use is <what> <selector>
   visible, enabled, checked

skill-data/core/SKILL.md

@@ -207,8 +207,8 @@ assigned fresh on every snapshot.
 For unstructured reading (no refs needed):
 
 ```bash
-chrome-use get text @e1                # visible text of an element
+chrome-use get text                    # WHOLE PAGE — all frames by default (see below)
-chrome-use get text --all-frames       # whole page, aggregated across ALL frames
+chrome-use get text @e1                # visible text of one element (or a CSS selector)
 chrome-use get text --main             # main content only — skip nav/header/sidebar
 chrome-use frames                      # list every frame + where the text lives
 chrome-use get html @e1                # innerHTML
@@ -219,13 +219,20 @@ chrome-use get url                     # current URL
 chrome-use get count ".item"           # count matching elements
 ```
 
-On listing/marketplace pages (Yahoo Auctions, Rakuten, Mercari shops) the seller's
+**Whole-page text is cross-frame by default.** `chrome-use get text` with no
-description often lives in a **child frame** or is buried under a "related items"
+selector aggregates visible text across **every** frame — top document plus
-sidebar, so a plain `get text body` returns only header/nav boilerplate. When the
+same-process child frames plus cross-origin iframes — so you never silently miss
-text you expect is missing: run `chrome-use frames` to see where it is, then
+content that lives in an iframe (Yahoo Auctions / Rakuten / Mercari shop
-`get text --all-frames` (reads every reachable frame incl. cross-origin iframes)
+descriptions, embedded checkout/spec frames). Each child frame is delimited with
-or `get text --main` (drops the global chrome). If the content is lazy-loaded,
+a `----- frame [kind] url -----` marker. You do **not** need to remember a flag —
-`scroll` it into view first.
+the default already reads all frames. (`--all-frames` is still accepted as an
+explicit alias.)
+
+So: when text looks missing or wrong, you don't have to guess — just
+`chrome-use get text` reads everything. To **see** the structure (which frame
+holds what), run `chrome-use frames`. To **cut boilerplate** (global nav/header/
+footer, "related items" sidebars), use `chrome-use get text --main`. If content
+is lazy-loaded, `scroll` it into view first, then read.
 
 ## Interacting