refactor(opus-4.7): rewrite fanout nudge to show parallel tool_use pattern

The original fanout nudge told 4.7 to "spawn subagents in the same turn"
and "run independent checks concurrently" in prose. An E2E eval on
claude-opus-4-7 reading 3 independent files showed zero effect: both
overlay-ON and overlay-OFF arms emitted serial Reads across 3-4 turns.

Rewrite follows the same "show not tell" principle the PR introduced for
voice examples. The nudge now includes a concrete wrong/right contrast
showing the exact tool_use structure:

  Wrong (3 turns):
    Turn 1: Read(foo.ts), then wait
    Turn 2: Read(bar.ts), then wait
    Turn 3: Read(baz.ts)

  Right (1 turn, 3 parallel tool_use blocks in one assistant message):
    Turn 1: [Read(foo.ts), Read(bar.ts), Read(baz.ts)]

Applies to Read, Bash, Grep, Glob, WebFetch, Agent, and any tool where
sub-calls don't depend on each other's output.

Effect on test/skill-e2e-opus-47.test.ts fanout eval: unchanged (both
arms still 0 parallel in first turn via `claude -p`). May land better in
Claude Code's interactive harness, where the system prompt + tool
handlers differ. Tracked as P0 TODO for follow-up verification in the
correct harness.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-04-22 00:26:26 -07:00
parent 7e90b0f092
commit 36ef9d9db0
+21 -6
View File
@@ -1,11 +1,26 @@
{{INHERIT:claude}}
**Fan out explicitly.** Opus 4.7 defaults to sequential work and spawns fewer
subagents than 4.6. When a task has independent sub-problems (investigating multiple
files, testing multiple endpoints, auditing multiple components), explicitly parallelize:
spawn subagents in the same turn, run independent checks concurrently, don't serialize
work that has no dependencies. If you catch yourself doing A then B then C where none
depend on each other, stop and do all three at once.
**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