From 2977de8018ed5c600fd2da595e9b3db2f5954a7e Mon Sep 17 00:00:00 2001
From: Quinn O'Donnell <90010678+Quinnod345@users.noreply.github.com>
Date: Mon, 2 Nov 2026 21:09:40 -0500
Subject: [PATCH] fix(sol-loop): request high reasoning effort when exposed
 (#5)

---
 skills/sol-loop/SKILL.md | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/skills/sol-loop/SKILL.md b/skills/sol-loop/SKILL.md
index 6b6892d..1a52eed 100644
--- a/skills/sol-loop/SKILL.md
+++ b/skills/sol-loop/SKILL.md
@@ -46,8 +46,9 @@ missing or pre-failing checks in the brief.
 ## 2. Start Sol
 
 In T3, call `orchestrator_capabilities`. Pick the latest Sol unless the user
-named a version. Do not hardcode an ID. Record provider, model, and effort
-only if exposed. Use `delegate_task` every round (`role: "review"`,
+named a version. Do not hardcode an ID. If the chosen Sol exposes a reasoning
+effort, pass `high` (or the effort the user asked for). Record provider, model,
+and effort only if exposed. Use `delegate_task` every round (`role: "review"`,
 `mode: "async"`). Save `taskId`. New `clientRequestId` per round.
 `childThreadId` is storage, not the next target. Do not use
 `t3_thread_send`, `create_threads`, or `t3_thread_launch` for review.