From c596a2d6400df47654b80b13e01a78571fec16bd Mon Sep 17 00:00:00 2001
From: Lakshya77089 <169168095+Lakshya77089@users.noreply.github.com>
Date: Tue, 16 Jun 2026 21:33:52 +0530
Subject: [PATCH] docs: clarify benchmark numbers are per-task, not plan quota
 (#115)

Adds a caveat under the headline numbers: they are per-task code/latency/cost on the Claude API, not a plan quota promise. Prevents the misread in #111.
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 58a9c2e..d003bfa 100644
--- a/README.md
+++ b/README.md
@@ -20,7 +20,7 @@
 
 <p align="center">
   <strong>80-94% less code &middot; 3-6&times; faster &middot; 47-77% cheaper</strong><br>
-  <sub>Median of 10 runs across Haiku, Sonnet, and Opus. <a href="benchmarks/">Reproduce it yourself.</a></sub>
+  <sub>Per-task code, latency, and cost on the Claude API, not your plan's quota. The ruleset re-injects each turn, so on one short prompt that overhead can outweigh the savings. Median of 10 runs across Haiku, Sonnet, and Opus. <a href="benchmarks/">Reproduce it yourself.</a></sub>
 </p>
 
 ---