diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
index 6ca35e92..5bb858b5 100644
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -2,7 +2,7 @@
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "humanizer",
   "description": "Rewrite AI-sounding text so it reads naturally without changing what it says.",
-  "version": "2.11.2",
+  "version": "2.12.0",
   "author": {
     "name": "blader",
     "url": "https://github.com/blader"
diff --git a/README.md b/README.md
index aea9a0b4..ffb19aa9 100644
--- a/README.md
+++ b/README.md
@@ -6,7 +6,7 @@ Humanizer rewrites AI-sounding text so it reads like a person wrote it, without
 
 ## How it works
 
-Humanizer uses 35 patterns from Wikipedia's ["Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. It makes a first pass without treating the original structure as fixed. Then it checks the draft against those patterns and the original claims before rewriting whatever still needs work.
+Humanizer uses 36 patterns from Wikipedia's ["Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. It makes a first pass without treating the original structure as fixed. Then it checks the draft against those patterns and the original claims before rewriting whatever still needs work.
 
 > "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
 
@@ -52,7 +52,7 @@ Now humanize this text:
 
 Humanizer follows the sample's rhythm, word choice, punctuation, and deliberate quirks.
 
-## The 35 patterns
+## The 36 patterns
 
 ### Content patterns
 
@@ -113,6 +113,7 @@ Humanizer follows the sample's rhythm, word choice, punctuation, and deliberate
 | 23 | **Filler phrases** | "In order to", "Due to the fact that" | "To", "Because" |
 | 24 | **Too many qualifiers** | "could potentially possibly" | "may" |
 | 25 | **Generic positive endings** | "The future looks bright" | End with a fact or a sourced plan |
+| 36 | **Hedge then overstate** | "It's worth noting that X is the single most important..." | Make the claim and back it, or make a smaller claim |
 
 ## Full example
 
@@ -154,6 +155,7 @@ Humanizer follows the sample's rhythm, word choice, punctuation, and deliberate
 <details>
 <summary>Show release notes</summary>
 
+- **2.12.0** - Added pattern 36, hedge then overstate: a soft opener paired with a strong claim in one sentence. The hedge hides behind the superlative. Commit to the claim or make the smaller one.
 - **2.11.2** - Removed the plugin symlink and separate Claude Desktop package. Current Claude Code loads the root `SKILL.md` directly, so GitHub's source ZIP now works in Claude Desktop. No change to the 35 patterns.
 - **2.11.1** - Added a Claude Desktop-ready release package with one regular `humanizer/SKILL.md` file. GitHub's source archive still keeps the plugin symlink (fixes #224). No change to the 35 patterns.
 - **2.11.0** - Rewrote all repo guidance, descriptions, checks, and skill instructions in Plain Language. Kept all 35 patterns and their behavior.
diff --git a/SKILL.md b/SKILL.md
index c9c22422..7b8b9320 100644
--- a/SKILL.md
+++ b/SKILL.md
@@ -7,7 +7,7 @@ description: |
   voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing."
 license: MIT
 metadata:
-  version: "2.11.2"
+  version: "2.12.0"
 ---
 
 # Humanizer: remove AI writing patterns
@@ -390,6 +390,15 @@ Remove only the unsupported defense. If it contains a real claim, state that cla
 
 One rejected option may be valid. Several short, unrelated rejections are a stronger sign. Ask what new information each sentence adds. If it only records an earlier edit, rewrite the paragraph around its main point.
 
+### 36. Hedge then overstate
+
+**Phrases to watch:** "It's worth noting that... [strong claim]", "arguably... [absolute claim]", "in some sense... [definite statement]", "to some extent... critically", "broadly speaking... fundamentally"
+**Problem:** A soft opener paired with a strong claim in the same sentence. The hedge gives the writer room to retreat while the superlative does the real asserting, so the reader has to guess how much the writer means. Strip the hedge and the sentence becomes a plain claim; strip the superlative and it says nothing. Pick one: make the claim and back it, or make the smaller claim and own it.
+**Before:**
+> It's worth noting that caching is the single most important optimization here. Arguably, it changes everything about how the service scales.
+**After:**
+> Caching is the main optimization here. It roughly halves the median response time under load.
+
 ## Check for false positives
 
 ### What not to flag