docs: strengthen Claude rules based on eval results

Eval showed docstrings, tmp_path, and .resolve() rules were being
ignored. Made phrasing more explicit and added concrete examples.

.claude/rules/code-style.md

@@ -5,11 +5,11 @@
 - **Package management**: Always use `uv`, never `pip`
 - **Tooling**: Ruff for linting/formatting, mypy strict mode, prek for pre-commit checks
 - **Comments**: Minimal - only explain "why", not "what"
-- **Docstrings**: Do not add unless explicitly requested
+- **Docstrings**: Do not add docstrings to new or changed code unless the user explicitly asks for them — not even one-liners. The codebase intentionally keeps functions self-documenting through clear naming and type annotations
 - **Types**: Match the type annotation style of surrounding code — the codebase uses annotations, so add them in new code
 - **Naming**: NEVER use leading underscores (`_function_name`) - Python has no true private functions, use public names
 - **Paths**: Always use absolute paths
 - **Encoding**: Always pass `encoding="utf-8"` to `open()`, `read_text()`, `write_text()`, etc. in new or changed code — Windows defaults to `cp1252` which breaks on non-ASCII content. Don't flag pre-existing code that lacks it unless you're already modifying that line.
-- **Verification**: Use `uv run prek` to verify code (handles ruff, ty, mypy in one pass) — don't use `python -c "import ..."` for validation
+- **Verification**: Use `uv run prek` to verify code — it handles ruff, ty, mypy in one pass. Don't run `ruff`, `mypy`, or `python -c "import ..."` separately; `prek` is the single verification command
 - **Pre-commit**: Run `uv run prek` before committing — fix any issues before creating the commit
 - **Pre-push**: Before pushing, run `uv run prek run --from-ref origin/<base>` to check all changed files against the PR base — this matches CI behavior and catches issues that per-commit prek misses. To detect the base branch: `gh pr view --json baseRefName -q .baseRefName 2>/dev/null || echo main`

.claude/rules/testing.md

@@ -7,9 +7,8 @@ paths:
 # Testing Conventions
 
 - Code context extraction and replacement tests must always assert for full string equality, no substring matching.
-- Use pytest's `tmp_path` fixture for temp directories (it's a `Path` object).
-- Write temp files inside `tmp_path`, never use `NamedTemporaryFile` (causes Windows file contention).
-- Always call `.resolve()` on Path objects to ensure absolute paths and resolve symlinks.
+- Use pytest's `tmp_path` fixture for temp directories — do not use `tempfile.mkdtemp()`, `tempfile.TemporaryDirectory()`, or `NamedTemporaryFile`. Some existing tests still use `tempfile` but new tests must use `tmp_path`.
+- Always call `.resolve()` on Path objects before passing them to functions under test — this ensures absolute paths and resolves symlinks. Example: `source_file = (tmp_path / "example.py").resolve()`
 - Use `.as_posix()` when converting resolved paths to strings (normalizes to forward slashes).
 - Any new feature or bug fix that can be tested automatically must have test cases.
 - If changes affect existing test expectations, update the tests accordingly. Tests must always pass after changes.