diff --git a/apps/todos/muse/todo.md b/apps/todos/muse/todo.md
index 2d5fc0066..9771a1013 100644
--- a/apps/todos/muse/todo.md
+++ b/apps/todos/muse/todo.md
@@ -38,13 +38,11 @@ Use the Activity Context and Activity State Per Segment sections above to unders
 - `sol call todos upcoming` – view upcoming todos to avoid duplicates
 
 ### Transcript Commands
-- `sol call transcripts read --segment SEGMENT_KEY --transcripts` – read audio transcript for a segment
-- `sol call transcripts read --segment SEGMENT_KEY --agents` – read agent outputs (screen summaries) for a segment
-- `sol call transcripts read --segment SEGMENT_KEY --full` – read everything for a segment
+- `sol call transcripts read --segments $activity_segments --transcripts` – read audio transcripts for this activity
+- `sol call transcripts read --segments $activity_segments --agents` – read agent outputs (screen summaries) for this activity
+- `sol call transcripts read --segment SEGMENT_KEY --full` – read everything for a single segment
 - `sol call journal search QUERY` – cross-reference journal content
 
-Activity segments: $activity_segments
-
 **Query syntax**: Terms are AND'd by default; use `OR` for alternatives, quote phrases for exact matches, append `*` for prefix matching.
 
 ## Process
@@ -53,10 +51,8 @@ Activity segments: $activity_segments
 
 Read the activity's transcript and current todo state before making any changes.
 
-1. For each segment in this activity ($activity_segments), load the transcript:
-   `sol call transcripts read --segment SEGMENT_KEY --transcripts`
-   Also load screen agent output for context:
-   `sol call transcripts read --segment SEGMENT_KEY --agents`
+1. Load the activity's transcript and screen agent context:
+   `sol call transcripts read --segments $activity_segments --transcripts --agents --max 0`
 2. Call `sol call todos list` to see the current checklist
 3. Call `sol call todos upcoming -l 50` to check what's already scheduled
 
diff --git a/apps/transcripts/call.py b/apps/transcripts/call.py
index 3f9ae26d5..6e6dd2e66 100644
--- a/apps/transcripts/call.py
+++ b/apps/transcripts/call.py
@@ -17,6 +17,7 @@ from think.cluster import (
     cluster_range,
     cluster_scan,
     cluster_segments,
+    cluster_span,
 )
 from think.utils import (
     day_dirs,
@@ -85,6 +86,9 @@ def read(
     segment: str | None = typer.Option(
         None, "--segment", help="Segment key (HHMMSS_LEN, default: SOL_SEGMENT env)."
     ),
+    segments: str | None = typer.Option(
+        None, "--segments", help="Comma-separated segment keys for a span."
+    ),
     stream: str | None = typer.Option(
         None, "--stream", help="Stream name (default: SOL_STREAM env)."
     ),
@@ -140,8 +144,17 @@ def read(
     else:
         sources = {"transcripts": True, "percepts": False, "agents": True}
 
-    if segment and (start or length is not None):
-        typer.echo("Error: Cannot mix --segment with --start/--length.", err=True)
+    # Validate mutually exclusive selection modes
+    mode_count = sum([
+        segment is not None,
+        segments is not None,
+        start is not None or length is not None,
+    ])
+    if mode_count > 1:
+        typer.echo(
+            "Error: Cannot mix --segment, --segments, and --start/--length.",
+            err=True,
+        )
         raise typer.Exit(1)
 
     if (start is not None) != (length is not None):
@@ -154,6 +167,9 @@ def read(
         start_dt = datetime.strptime(start, "%H%M%S")
         end_dt = start_dt + timedelta(minutes=length)
         markdown = cluster_range(day, start, end_dt.strftime("%H%M%S"), sources)
+    elif segments is not None:
+        span = [s.strip() for s in segments.split(",") if s.strip()]
+        markdown, _counts = cluster_span(day, span, sources, stream=stream)
     elif segment is not None:
         markdown, _counts = cluster_period(day, segment, sources, stream=stream)
     else:
diff --git a/apps/transcripts/muse/transcripts/SKILL.md b/apps/transcripts/muse/transcripts/SKILL.md
index 4a9cd14e2..e865e5e22 100644
--- a/apps/transcripts/muse/transcripts/SKILL.md
+++ b/apps/transcripts/muse/transcripts/SKILL.md
@@ -68,18 +68,19 @@ sol call transcripts segments 20260115
 ## read
 
 ```bash
-sol call transcripts read [DAY] [--start HHMMSS --length MINUTES] [--segment KEY] [--stream NAME] [--full] [--raw] [--audio] [--screen] [--agents]
+sol call transcripts read [DAY] [--start HHMMSS --length MINUTES] [--segment KEY] [--segments KEYS] [--stream NAME] [--full] [--raw] [--audio] [--screen] [--agents]
 ```
 
-Read transcript content for a day, time range, or segment.
+Read transcript content for a day, time range, segment, or span.
 
 - `DAY`: day in `YYYYMMDD` (default: `SOL_DAY` env).
 
 Read modes (mutually exclusive):
 
 1. `--start HHMMSS --length MINUTES`: range mode. Both flags are required together; end time is auto-computed.
-2. `--segment KEY`: segment mode using key from `segments`.
-3. No time flags: whole-day mode.
+2. `--segment KEY`: single segment mode using key from `segments`.
+3. `--segments KEY1,KEY2,...`: span mode — comma-separated segment keys, merged in time order.
+4. No time flags: whole-day mode.
 
 Source flags:
 
@@ -92,7 +93,7 @@ Source flags:
 
 Rules:
 
-- Do not combine `--segment` with `--start/--length`.
+- Do not combine `--segment`, `--segments`, or `--start/--length` with each other.
 - Do not combine `--full` or `--raw` with individual source flags.
 
 Source type meanings:
@@ -107,6 +108,7 @@ Examples:
 sol call transcripts read 20260115
 sol call transcripts read 20260115 --start 090000 --length 30 --raw
 sol call transcripts read 20260115 --segment 091500_300 --full
+sol call transcripts read 20260115 --segments 091500_300,092000_300,092500_300 --transcripts --agents
 sol call transcripts read 20260115 --audio
 ```