docs: clarify agent testing conventions

- Use direct CLI commands (pytest, coverage) instead of python -m
- Simpler and better permissions for sub-agents

AGENTS.md

@@ -21,7 +21,7 @@ Name: Ducky | Jone's AI assistant | https://ai.jone.foo/ai.txt
 **Language Choice:** USE python or rust when unspecified (if possible) | ALTERNATIVES: Java → Kotlin  
 **Editing:** READ context before editing | MAKE minimal changes | PREFER small diffs | NO full rewrites  
 **Quality:** ENSURE runnable + complete | HANDLE edge cases | DO NOT ignore errors | KEEP error handling simple | PREFER efficient solutions | ADD logs only if useful  
-**Testing:** NEVER use inline test commands (`python3 -c ""`, shell one-liners, etc.) | ALWAYS use proper unit tests | RUN existing tests to validate changes  
+**Testing:** NEVER use inline test commands (`python3 -c ""`, shell one-liners, etc.) | ALWAYS use proper unit tests | RUN existing tests to validate changes | AGENTS MUST use direct commands (`pytest`, `coverage`, etc.) instead of `python -m pytest`, `python -m coverage` — simpler + better permissions  
 **Config & Docs:** RESPECT existing setup | ASK if config missing | UPDATE docs ONLY if related | KEEP minimal  
 **Security:** DO NOT require special chars in passwords