docs(research): break the two worst wall paragraphs

The chezmoi overview was one 488-character sentence-block; the git-crypt mechanism and verdict
lines were the same shape. Reflowed to ~100 columns with no wording lost, so the pages read the
same in an editor as they do rendered.

Refs #64

omp-docs/research/secrets-for-agents.md

@@ -42,7 +42,9 @@ The question: for each tool, does a secret ever appear in plaintext where an age
 
 ### How it works
 
-git-crypt uses git clean/merge filters to encrypt specific files at commit time and decrypt them at checkout. The `.gitattributes` file declares which paths to encrypt. Encryption uses AES-256-CTR with a synthetic IV derived from SHA-1 HMAC.
+git-crypt uses git clean/merge filters to encrypt specific files at commit time and decrypt
+them at checkout. The `.gitattributes` file declares which paths to encrypt. Encryption is
+AES-256-CTR with a synthetic IV derived from SHA-1 HMAC.
 
 ### Agent behavior
 
@@ -64,7 +66,10 @@ git-crypt uses git clean/merge filters to encrypt specific files at commit time
 
 ### Agent safety verdict
 
-**Moderate.** Plaintext appears on disk post-checkout but the agent doesn't explicitly decrypt — git does it silently. However, any agent that opens the file sees plaintext. In a shared repo scenario, any collaborator who gets the GPG private key gets full access to all history.
+**Moderate.** Plaintext appears on disk post-checkout, but the agent never decrypts — git does
+it silently inside the filter pipeline. Any agent that opens the file still sees plaintext.
+And in a shared repo, any collaborator who gets the GPG private key gets full access to all
+history.
 
 ---