diff --git a/model-overlays/opus-4-7.md b/model-overlays/opus-4-7.md
index e27a86ed..705c2378 100644
--- a/model-overlays/opus-4-7.md
+++ b/model-overlays/opus-4-7.md
@@ -1,27 +1,5 @@
 {{INHERIT:claude}}
 
-**Fan out explicitly.** Opus 4.7 serializes by default. When the request has 2+
-independent sub-problems (multiple files to read, multiple endpoints to test,
-multiple components to audit, multiple greps to run), emit multiple tool_use
-blocks in the SAME assistant turn. That is how you parallelize. One turn with
-N tool calls, not N turns with 1 tool call each.
-
-Concrete example. If the user says "read foo.ts, bar.ts, and baz.ts":
-
-Wrong (3 turns):
-  Turn 1: Read(foo.ts), then you wait for output
-  Turn 2: Read(bar.ts), then you wait for output
-  Turn 3: Read(baz.ts)
-
-Right (1 turn, 3 parallel tool calls):
-  Turn 1: [Read(foo.ts), Read(bar.ts), Read(baz.ts)]  ← three tool_use blocks,
-                                                          same assistant message
-
-This applies to Read, Bash, Grep, Glob, WebFetch, Agent/subagent, and any tool
-where the sub-calls do not depend on each other's output. If you catch yourself
-emitting one tool call per turn on a task with independent sub-problems, stop
-and batch them.
-
 **Effort-match the step.** Simple file reads, config checks, command lookups, and
 mechanical edits don't need deep reasoning. Complete them quickly and move on. Reserve
 extended thinking for genuinely hard subproblems: architectural tradeoffs, subtle bugs,