Clarify Vercel instrumentation prompt

Author: marcusschiesser

AGENTS.md

@@ -38,7 +38,7 @@ This repository uses Changesets to generate package changelogs.
 <!-- gitnexus:start -->
 # GitNexus — Code Intelligence
 
-This project is indexed by GitNexus as **agentpond** (1323 symbols, 3121 relationships, 105 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely.
+This project is indexed by GitNexus as **agentpond** (1333 symbols, 3159 relationships, 106 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely.
 
 > Index stale? Run `node .gitnexus/run.cjs analyze` from the project root — it auto-selects an available runner. No `.gitnexus/run.cjs` yet? `npx gitnexus analyze` (npm 11 crash → `npm i -g gitnexus`; #1939).
 

CLAUDE.md

@@ -1,7 +1,7 @@
 <!-- gitnexus:start -->
 # GitNexus — Code Intelligence
 
-This project is indexed by GitNexus as **agentpond** (1323 symbols, 3121 relationships, 105 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely.
+This project is indexed by GitNexus as **agentpond** (1333 symbols, 3159 relationships, 106 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely.
 
 > Index stale? Run `node .gitnexus/run.cjs analyze` from the project root — it auto-selects an available runner. No `.gitnexus/run.cjs` yet? `npx gitnexus analyze` (npm 11 crash → `npm i -g gitnexus`; #1939).
 

packages/vercel/src/vercel-project.ts

@@ -19,10 +19,10 @@ export type VercelCliProjectConfig = {
 };
 
 export const VERCEL_INSTRUMENTATION_PROMPT = `Use $agentpond-instrumentation to inspect this Vercel project and add
-OpenInference tracing to its trusted Node.js AI application.
+OpenInference tracing to its Node.js AI application.
 
-Use a connected private Vercel Blob store, export spans directly with
-createVercelSpanExporter() from @agentpond/vercel, and do not add an ingestion route.
+Use a connected private Vercel Blob store and export spans directly with
+createVercelSpanExporter() from @agentpond/vercel.
 
 Build the application, exercise one real AI request, then use $agentpond to: