Measure startup configuration loading

docs/roadmap/startup.md

@@ -1,6 +1,7 @@
 # Startup Loading Performance Roadmap
 
-Status: Approach accepted; execution has not started.
+Status: Stages 1–3 complete; optimization has not started. Findings and
+reproduction commands are in [startup-benchmark.md](startup-benchmark.md).
 
 Audience: ConfigKit maintainers implementing and reviewing this work.
 
@@ -39,7 +40,9 @@ throughout execution.
 
 ### 1. Establish the downstream and current-code baselines
 
-Status: Not started.
+Status: Complete. The recorded PromptKit revision was measured with v0.5.0 and
+current ConfigKit; allocation costs were reproduced. See the
+[downstream results](startup-benchmark.md#stage-1-downstream-reproduction).
 
 1. Inspect PromptKit's recorded benchmark and configuration adapter at the
    revision identified in its request. Identify which work is timed, including
@@ -63,7 +66,9 @@ evidence. Do not attribute all adapter costs to ConfigKit.
 
 ### 2. Add a representative ConfigKit construction benchmark
 
-Status: Not started.
+Status: Complete. A maintained root-API benchmark measures 32, 128, and 512
+profile/prompt pairs, with complementary existing benchmarks. See the
+[local results](startup-benchmark.md#stage-2-maintained-public-api-benchmark).
 
 1. Add a maintained benchmark through the root public API, using a synthetic
    configuration shape representative of PromptKit's profiles and versioned
@@ -89,7 +94,9 @@ measurements, not machine-specific pass/fail assertions.
 
 ### 3. Profile and choose the first optimization
 
-Status: Not started.
+Status: Complete. CPU/allocation profiles and the source trace identify
+`Path.String` buffer sizing as the first experiment. See the
+[profile evidence and proposal](startup-benchmark.md#stage-3-profiles-and-implementation-trace).
 
 1. Collect CPU and allocation profiles for the representative local fixture.
    Compare them with the downstream profile where available, distinguishing