Updating agents file to reflect current usage

.claude/commands/verify.md

@@ -0,0 +1,11 @@
+Verify that a code change works correctly without hitting live APIs.
+
+IMPORTANT: Never run `generate.py`, `judge.py`, or `run_pipeline.py` directly — these make live LLM API calls. Verification must use the test suite only.
+
+Steps:
+1. Identify what changed (git diff --stat) to understand the scope
+2. Run the relevant tests with `uv run pytest -m "not live" -v` targeting changed modules where possible
+3. Run the full non-live suite to check for regressions: `uv run pytest -m "not live"`
+4. Report: which tests passed/failed, coverage delta if relevant, and whether the change behaves as expected based on test output
+
+If the change cannot be verified without a live API call, say so explicitly and suggest what a targeted live test would look like (but do not run it).

.gitignore

@@ -28,6 +28,10 @@ coverage.json
 htmlcov/
 !tests/fixtures/conversations/
 
+# IDEs
+.cursor/
+.vscode/
+
 # Claude Code - personal settings and local files only
 .claude/settings.local.json
 .claude/hooks/local/

.pre-commit-config.yaml

@@ -6,11 +6,3 @@ repos:
         args: [--fix]
       - id: ruff-format
 
-  - repo: local
-    hooks:
-      - id: sync-claude-to-agents
-        name: Sync CLAUDE.md to AGENTS.md
-        entry: .pre-commit-scripts/sync-claude-to-agents.sh
-        language: script
-        files: ^CLAUDE\.md$
-        pass_filenames: false