Merge pull request #6 from hermes-labs-ai/codex/intent-verify-v012-final-polish

docs: clarify v0.1.2 release boundary

Author: roli-lpci

CITATION.cff

@@ -10,7 +10,7 @@ authors:
     affiliation: "Hermes Labs"
 license: MIT
 version: "0.1.2"
-date-released: "2026-04-19"
+date-released: "2026-08-04"
 repository-code: "https://github.com/hermes-labs-ai/intent-verify"
 references:
   - type: article

README.md

@@ -105,6 +105,7 @@ The JSON object includes `spec_path`, `repo_path`, `files_scanned`, `average_cov
 
 ## Limitations / what it does NOT do
 
+- **Not runtime agent intent verification.** It does not authorize or monitor AI-agent actions, MCP/tool calls, or permissions; it checks static repository source against a markdown spec.
 - **Lexical, not semantic.** It matches tokens as substrings; it does not understand meaning, control flow, or behavior.
 - **It can over-credit.** A token appearing anywhere in any scanned file counts, even if it is in a comment, a string, or an unrelated context.
 - **It can under-credit.** A correct implementation written with different vocabulary than the spec will score low.