diff --git a/README.md b/README.md
index 120bec1..1934539 100644
--- a/README.md
+++ b/README.md
@@ -88,7 +88,7 @@ The skill also includes a final "obviously AI generated" audit pass and a second
 
 > "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."
 
-## 29 Patterns Detected (with Before/After Examples)
+## 30 Patterns Detected (with Before/After Examples)
 
 ### Content Patterns
 
@@ -127,6 +127,7 @@ The skill also includes a final "obviously AI generated" audit pass and a second
 | 27 | **Persuasive authority tropes** | "At its core, what matters is..." | State the point directly |
 | 28 | **Signposting announcements** | "Let's dive in", "Here's what you need to know" | Start with the content |
 | 29 | **Fragmented headers** | "## Performance" + "Speed matters." | Let the heading do the work |
+| 30 | **Diff-anchored writing** | "This was added to replace the old approach" | Describe what the code does, not what changed |
 
 ### Communication Patterns
 
@@ -179,6 +180,7 @@ The skill also includes a final "obviously AI generated" audit pass and a second
 
 ## Version History
 
+- **2.5.2** - Added a diff-anchored writing rule, raising the total to 30 patterns
 - **2.5.1** - Added a passive-voice / subjectless-fragment rule, raising the total to 29 patterns
 - **2.5.0** - Added patterns for persuasive framing, signposting, and fragmented headers; expanded negative parallelisms to cover tailing negations; tightened wording around em dash overuse; fixed frontmatter wording to use "filler phrases"
 - **2.4.0** - Added voice calibration: match the user's personal writing style from samples
diff --git a/SKILL.md b/SKILL.md
index 46639f0..518fbd2 100644
--- a/SKILL.md
+++ b/SKILL.md
@@ -461,6 +461,22 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 >
 > When users hit a slow page, they leave.
 
+### 30. Diff-Anchored Writing
+
+**Problem:** Writing that is overly coupled to a specific change or point-in-time diff rather than making statements that stand on their own. Unless the document is inherently version-scoped (release notes, changelogs, migration guides), documentation and comments should read coherently without knowing what changed in the last commit.
+
+**Before:**
+> This function was added to replace the previous approach of iterating through all items. The old method caused O(n²) performance, so we now use a hash map instead.
+
+**After:**
+> This function uses a hash map for O(1) lookups per item, avoiding the O(n²) cost of naive iteration.
+
+**Before:**
+> We removed the `legacy_auth` middleware because legal flagged it for storing session tokens in a non-compliant way. The new implementation uses encrypted cookies.
+
+**After:**
+> Authentication uses encrypted cookies for session storage, meeting the current compliance requirements for token handling.
+
 ---
 
 ## Process
diff --git a/WARP.md b/WARP.md
index 78a5b4c..fd0e015 100644
--- a/WARP.md
+++ b/WARP.md
@@ -16,7 +16,7 @@ The “runtime” artifact is `SKILL.md`: Claude Code reads the YAML frontmatter
   - After the frontmatter is the editor prompt: the canonical, detailed pattern list with examples.
 - `README.md`
   - Installation and usage instructions.
-  - Contains a summarized “25 patterns” table and a short version history.
+  - Contains a summarized “30 patterns” table and a short version history.
 
 When changing behavior/content, treat `SKILL.md` as the source of truth, and update `README.md` to stay consistent.