[ai] Remove mention of ultrathink for Claude.

.claude/commands/planner.md

@@ -37,16 +37,8 @@ ls .ai/
 
 Suggest a name to the user or let them specify one directly via $ARGUMENTS.
 
-### 3. Use /ultrathink for Planning
 
-Before writing the prompt, use `/ultrathink` to carefully plan:
+### 3. Create the Folder and Files
-- The structure of the prompt
-- What context the autonomous agent needs
-- How tasks should be broken down
-- What patterns/examples to include
-- Edge cases and error handling
-
-### 4. Create the Folder and Files
 
 Create `.ai/<featurename>/`:
 
@@ -91,7 +83,7 @@ IMPORTANT: Never try to commit files in .ai/
 }
 ```
 
-### 5. Iterate with the User
+### 4. Iterate with the User
 
 After creating initial files, the user may want to:
 - Add more tasks to tasks.json

.claude/commands/task.md

@@ -203,7 +203,7 @@ Read these files:
 - .ai/<project-name>/<letter>/context.md - Contains all gathered context for this task
 - Then read the specific source files referenced in context.md to understand the code deeply.
 
-Use /ultrathink to reason carefully about the implementation approach.
+Think carefully about the implementation approach.
 
 Create a detailed plan in: .ai/<project-name>/<letter>/plan.md
 
@@ -264,7 +264,7 @@ Read these files:
 - .ai/<project-name>/<letter>/plan.md
 - Then read the actual source files referenced to verify the plan makes sense.
 
-Use /ultrathink to assess the plan:
+Carefully assess the plan:
 
 1. **Correctness**: Are the file paths and line references accurate? Does the plan reference real functions and types?
 2. **Completeness**: Are there missing steps? Edge cases not handled?
@@ -393,7 +393,7 @@ Then run `git diff` to see all uncommitted changes made by the implementation. I
 
 Then read the modified source files in full to understand changes in context.
 
-Use /ultrathink to perform a thorough code review.
+Perform a thorough code review.
 
 REVIEW CRITERIA (in order of importance):
 

.claude/commands/withtest.md

@@ -100,7 +100,7 @@ YOUR JOB:
    - [ ] Testing
    Assessed: yes
 
-Use /ultrathink to reason carefully. The follow-up plan should be self-contained enough that an implementation agent can execute it by reading context.md and the updated plan.md.
+Reason carefully. The follow-up plan should be self-contained enough that an implementation agent can execute it by reading context.md and the updated plan.md.
 ```
 
 After this agent completes, read `plan.md` to verify the follow-up plan was written. Then proceed to Phase 4 (Implementation), using the follow-up phases (F1, F2, etc.) instead of the original phases. After implementation and build verification, proceed to Stage 2 (Testing Loop) as normal.
@@ -163,7 +163,7 @@ Read these files:
 - .ai/<feature-name>/context.md - Contains all gathered context
 - Then read the specific source files referenced in context.md to understand the code deeply.
 
-Use /ultrathink to reason carefully about the implementation approach.
+Think carefully about the implementation approach.
 
 Create a detailed plan in: .ai/<feature-name>/plan.md
 
@@ -224,7 +224,7 @@ Read these files:
 - .ai/<feature-name>/plan.md
 - Then read the actual source files referenced to verify the plan makes sense.
 
-Use /ultrathink to assess the plan:
+Carefully assess the plan:
 
 1. **Correctness**: Are the file paths and line references accurate? Does the plan reference real functions and types?
 2. **Completeness**: Are there missing steps? Edge cases not handled?
@@ -367,7 +367,7 @@ YOUR TASKS:
    - Decide: reuse/modify existing test code or start fresh.
 
 3. **Plan the test code.**
-   Use /ultrathink to design test code that will verify the implementation works correctly.
+   Carefully design test code that will verify the implementation works correctly.
 
    The test code must:
    - Be wrapped in `#ifdef _DEBUG` blocks so it only runs in Debug builds
@@ -530,7 +530,7 @@ Read these files:
 - .ai/<feature-name>/result<N>.md
 <if N > 1, also read previous test/result pairs for history>
 
-Use /ultrathink to carefully analyze the test results.
+Carefully analyze the test results.
 
 DECIDE one of three outcomes:
 

.claude/iterate.ps1

@@ -173,7 +173,7 @@ Do exactly ONE task per iteration.
 ## Steps
 
 1. Read tasks.json and find the most suitable task to implement (it can be first uncompleted task or it can be some task in the middle, if it is better suited to be implemented right now, respecting dependencies)
-2. Use /ultrathink to plan the implementation carefully
+2. Plan the implementation carefully
 3. Implement that ONE task only
 4. After successful implementation:
 $AfterImplementation