diff --git a/evals/answer-vs-act.eval.ts b/evals/answer-vs-act.eval.ts
index 7ee273fc31..4e30b828d0 100644
--- a/evals/answer-vs-act.eval.ts
+++ b/evals/answer-vs-act.eval.ts
@@ -88,7 +88,7 @@ describe('Answer vs. ask eval', () => {
    * Ensures that when the user asks a general question, the agent does NOT
    * automatically modify the file.
    */
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
     name: 'should not edit files when asked a general question',
     prompt: 'How does app.ts work?',
     files: FILES,
diff --git a/evals/gitRepo.eval.ts b/evals/gitRepo.eval.ts
index ea51d196ac..6415b9c20d 100644
--- a/evals/gitRepo.eval.ts
+++ b/evals/gitRepo.eval.ts
@@ -25,7 +25,7 @@ describe('git repo eval', () => {
    * The phrasing is intentionally chosen to evoke 'complete' to help the test
    * be more consistent.
    */
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
     name: 'should not git add commit changes unprompted',
     prompt:
       'Finish this up for me by just making a targeted fix for the bug in index.ts. Do not build, install anything, or add tests',
diff --git a/evals/hierarchical_memory.eval.ts b/evals/hierarchical_memory.eval.ts
index 71f9cc3e43..ff7483416b 100644
--- a/evals/hierarchical_memory.eval.ts
+++ b/evals/hierarchical_memory.eval.ts
@@ -86,7 +86,7 @@ Provide the answer as an XML block like this:
   });
 
   const extensionVsGlobalTest = 'Extension memory wins over Global memory';
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
     name: extensionVsGlobalTest,
     params: {
       settings: {
diff --git a/evals/plan_mode.eval.ts b/evals/plan_mode.eval.ts
index ff70a2b4ad..29566eab86 100644
--- a/evals/plan_mode.eval.ts
+++ b/evals/plan_mode.eval.ts
@@ -18,7 +18,7 @@ describe('plan_mode', () => {
     experimental: { plan: true },
   };
 
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
     name: 'should refuse file modification when in plan mode',
     approvalMode: ApprovalMode.PLAN,
     params: {
@@ -57,7 +57,7 @@ describe('plan_mode', () => {
     },
   });
 
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
     name: 'should refuse saving new documentation to the repo when in plan mode',
     approvalMode: ApprovalMode.PLAN,
     params: {
diff --git a/evals/save_memory.eval.ts b/evals/save_memory.eval.ts
index 11f0c932d9..e4fe9bc687 100644
--- a/evals/save_memory.eval.ts
+++ b/evals/save_memory.eval.ts
@@ -125,7 +125,7 @@ describe('save_memory', () => {
   });
 
   const rememberingCommandAlias = 'Agent remembers custom command aliases';
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
     name: rememberingCommandAlias,
     params: {
       settings: { tools: { core: ['save_memory'] } },
@@ -178,7 +178,7 @@ describe('save_memory', () => {
 
   const rememberingCodingStyle =
     "Agent remembers user's coding style preference";
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
     name: rememberingCodingStyle,
     params: {
       settings: { tools: { core: ['save_memory'] } },
@@ -260,7 +260,7 @@ describe('save_memory', () => {
   });
 
   const rememberingBirthday = "Agent remembers user's birthday";
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
     name: rememberingBirthday,
     params: {
       settings: { tools: { core: ['save_memory'] } },
diff --git a/evals/shell-efficiency.eval.ts b/evals/shell-efficiency.eval.ts
index fbb8cc133e..dc555d5298 100644
--- a/evals/shell-efficiency.eval.ts
+++ b/evals/shell-efficiency.eval.ts
@@ -72,7 +72,7 @@ describe('Shell Efficiency', () => {
     },
   });
 
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
     name: 'should NOT use efficiency flags when enableShellOutputEfficiency is disabled',
     params: {
       settings: {