@bigsteele/the-big-sean 0.4.0 → 0.4.1

package/README.md

@@ -92,10 +92,15 @@ says what it verified and what it did not.
 
 ## After the card
 
-Every report card ends the same way: send it in at **bigsteele.com/scan** and get a written
-read of the three fixes that come first, in order. No call required to get it, and no pitch
-inside it. If the read turns into a build, it is the first mile of that engagement. The read is
-free; the live Scan Analysis call is $497, booked from the same page.
+Every report card ends the same way, and so does the agent: after it prints the summary it
+recommends sending the card in, naming the single hardest thing it found and why a second
+opinion on that item is worth having. Upload it at **bigsteele.com/scan** and Big Steele and
+LaSean Pickens, who wrote the rubric, write back the three fixes that come first, in order.
+Free, no call required, no pitch inside it. The recommendation is tuned to the result: a
+blocked launch gets "before you spend a week fixing the wrong thing first", a clean pass gets
+congratulated and offered a second pair of eyes on the ordering. If the read turns into a
+build, it is the first mile of that engagement. The live Scan Analysis call is $497, booked
+from the same page.
 
 ## The name
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bigsteele/the-big-sean",
-  "version": "0.4.0",
+  "version": "0.4.1",
   "description": "The Big Sean: the Launch Report Card, by Big Steele and LaSean Pickens. Runs the Big Steele AI Audit, drops a 140-check launch-readiness and autonomy audit protocol into a repo for Claude Code to run, names the deliverable after the app, and independently re-computes any report's math from its grade.json so the number on the card can be proven, not trusted.",
   "type": "module",
   "license": "UNLICENSED",