diff --git a/.github/workflows/evals-periodic.yml b/.github/workflows/evals-periodic.yml
index 318abf9a3..23c6ff126 100644
--- a/.github/workflows/evals-periodic.yml
+++ b/.github/workflows/evals-periodic.yml
@@ -127,7 +127,7 @@ jobs:
           GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           EVALS_CONCURRENCY: "40"
           PLAYWRIGHT_BROWSERS_PATH: /opt/playwright-browsers
-        run: EVALS=1 bun test --retry 2 --concurrent --max-concurrency 40 ${{ matrix.suite.file }}
+        run: EVALS=1 bun test --retry 1 --concurrent --max-concurrency 40 ${{ matrix.suite.file }}
 
       - name: Upload eval results
         if: always()
diff --git a/.github/workflows/evals.yml b/.github/workflows/evals.yml
index 2e61ded5d..16ee6fc4b 100644
--- a/.github/workflows/evals.yml
+++ b/.github/workflows/evals.yml
@@ -283,7 +283,7 @@ jobs:
           GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           EVALS_CONCURRENCY: "40"
           PLAYWRIGHT_BROWSERS_PATH: /opt/playwright-browsers
-        run: EVALS=1 bun test --retry 2 --concurrent --max-concurrency 40 ${{ matrix.suite.file }}
+        run: EVALS=1 bun test --retry 1 --concurrent --max-concurrency 40 ${{ matrix.suite.file }}
 
       - name: Upload eval results
         if: always()
diff --git a/package.json b/package.json
index f65e484c8..4681a8552 100644
--- a/package.json
+++ b/package.json
@@ -21,12 +21,12 @@
     "test": "bun test browse/test/ test/ make-pdf/test/ design/test/ --timeout 30000 --ignore 'test/skill-e2e-*.test.ts' --ignore test/skill-llm-eval.test.ts --ignore test/skill-routing-e2e.test.ts --ignore test/codex-e2e.test.ts --ignore test/gemini-e2e.test.ts && (bun run slop:diff 2>/dev/null || true)",
     "test:free": "bun run scripts/test-free-shards.ts",
     "test:windows": "bun run scripts/test-free-shards.ts --windows-only",
-    "test:evals": "EVALS=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
-    "test:evals:all": "EVALS=1 EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
-    "test:e2e": "EVALS=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
-    "test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
-    "test:gate": "EVALS=1 EVALS_TIER=gate bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
-    "test:periodic": "EVALS=1 EVALS_TIER=periodic EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
+    "test:evals": "EVALS=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
+    "test:evals:all": "EVALS=1 EVALS_ALL=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
+    "test:e2e": "EVALS=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
+    "test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
+    "test:gate": "EVALS=1 EVALS_TIER=gate bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
+    "test:periodic": "EVALS=1 EVALS_TIER=periodic EVALS_ALL=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
     "test:gate:sharded": "bun run scripts/test-paid-shards.ts --tier gate",
     "test:periodic:sharded": "EVALS_ALL=1 bun run scripts/test-paid-shards.ts --tier periodic",
     "test:codex": "EVALS=1 bun test test/codex-e2e.test.ts",
diff --git a/scripts/test-paid-shards.ts b/scripts/test-paid-shards.ts
index fad74e868..8a5e77040 100644
--- a/scripts/test-paid-shards.ts
+++ b/scripts/test-paid-shards.ts
@@ -136,7 +136,7 @@ export function planPaidShards(
 }
 
 export function buildPaidShardArgs(files: string[], timeoutMs: number): string[] {
-  return ['test', ...files, '--retry', '2', `--timeout=${timeoutMs}`];
+  return ['test', ...files, '--retry', '1', `--timeout=${timeoutMs}`];
 }
 
 /**