Clarify PyPI usage

README.md

@@ -25,7 +25,7 @@ count is, and how many characters each tokenizer buys per token.
 | | |
 |---|---|
 | **Source** | [github.com/sanderland/ctok](https://github.com/sanderland/ctok) |
-| **Python package** | [`pip install ctok`](https://pypi.org/project/ctok/) — counts Claude tokens offline, no API call |
+| **Python package** | [`ctok` on PyPI](https://pypi.org/project/ctok/) — count any string yourself with `uvx ctok "your text"`, offline, no API call |
 | **The research** | [On the biology of Claude's tokenizer](https://tokencontributions.substack.com/p/on-the-biology-of-claudes-tokenizer) |
 
 ## What is compared

app.py

@@ -488,7 +488,7 @@ from **ctok**, a 99.9%+ accurate offline reconstruction — text only, no per-me
 LINKS = f"""
 <div class='links'>
   <a href='{REPO_URL}' target='_blank' rel='noopener'>◆ Source</a>
-  <a href='{PYPI_URL}' target='_blank' rel='noopener'>▼ <code>pip install ctok</code></a>
+  <a href='{PYPI_URL}' target='_blank' rel='noopener'>▼ <code>ctok</code> on PyPI</a>
   <a href='{POST_URL}' target='_blank' rel='noopener'>✎ The research behind it</a>
 </div>
 """