diff --git a/src/test_dictionary.py b/src/test_dictionary.py
index 35e19fa..5bcacf1 100644
--- a/src/test_dictionary.py
+++ b/src/test_dictionary.py
@@ -1,6 +1,8 @@
 from ex2_dictionary import calculate_price
-from util import eidp_test, has_annotations, imported_modules_of, has_no_annotations
+from util import *
 import pytest
+import sys
+import argparse
 from enum import Enum
 from copy import deepcopy
 
@@ -72,7 +74,7 @@ def test_typeannotation_by_amount():
 
 @pytest.mark.dependency(depends=[Task.A])
 @pytest.mark.timeout(10)
-@eidp_test("es wird nicht geschaut ob ein ein Produkt in `articles` ist", -2)
+@eidp_test("nicht überprüft ob Produkte in `articles` enthalten", -2)
 def test_article_not_in_articles():
     articles = {'Coke': 200}
     basket = {'Vitamine R': 1}
@@ -98,11 +100,16 @@ def test_price_calc():
     articles = {'Coke': 200, 'Eis': 350}
     basket = {'Coke': 2, 'Eis': 3}
     assert abs(calculate_price(articles, basket) - 14.5) < EPS
+    articles_dict = {"apples": 100, "oranges": 100,
+                     "lemons": 200, "avocado": 500}
+    cart_dict = {"apples": 2, "oranges": 2, "lemons": 1, "bananas": 5}
+
+    assert abs(calculate_price(articles_dict, cart_dict) - 6) < EPS
 
 
 @pytest.mark.dependency(depends=[Task.A])
 @pytest.mark.timeout(10)
-@eidp_test("`articles`/`cart` wird veraendert", -2)
+@eidp_test("`articles`/`cart` wird verwendet", -2)
 def test_sideeffectss():
     a = {'Coke': 200, 'Eis': 350}
     b = {'Coke': 2, 'Eis': 3}
@@ -110,5 +117,74 @@ def test_sideeffectss():
     assert a == a2 and b2 == b
 
 
+@pytest.mark.dependency(depends=[Task.B])
+@pytest.mark.timeout(10)
+@eidp_test("nicht überprüft ob Produkte in `articles` enthalten", -2)
+def test_article_not_in_articles_by_amount():
+    from ex2_dictionary import by_amount
+    articles_dict = {"apples_ex": 100, "oranges_ex": 100,
+                     "lemons": 200, "avocado_ex": 500}
+    cart_dict = {"apples": 2, "oranges": 2, "lemons": 1, "bananas": 5}
+
+    assert by_amount(articles_dict, cart_dict) == {1: ['lemons']}
+
+
+@pytest.mark.dependency(depends=[Task.B])
+@pytest.mark.timeout(10)
+@eidp_test("`by_amount` wird nicht korrekt berechnet", -2)
+def test_by_amount():
+    from ex2_dictionary import by_amount
+    articles_dict = {"apples": 100, "oranges": 100,
+                     "lemons": 200, "avocado": 500}
+    cart_dict = {"apples": 2, "oranges": 2, "lemons": 1, "bananas": 5}
+
+    assert by_amount(articles_dict, cart_dict) == {
+        2: ['apples', 'oranges'], 1: ['lemons']}
+
+
+@pytest.mark.dependency(depends=[Task.B])
+@pytest.mark.timeout(10)
+@eidp_test("es wird kein neues Dictionary erstellt", -4)
+def test_sideeffects_by_amount():
+    from ex2_dictionary import by_amount
+    a = {"apples": 100, "oranges": 100,
+         "lemons": 200, "avocado": 500}
+    b = {"apples": 2, "oranges": 2, "lemons": 1, "bananas": 5}
+
+    r = by_amount(a2 := deepcopy(a), b2 := deepcopy(b)) == {
+        2: ['apples', 'oranges'], 1: ['lemons']}
+    assert a2 == a and b2 == b and r is not a and r is not b
+
+
 if __name__ == '__main__':
-    pass
+    verbose, testing, force = tuple(parse_args(sys.argv).values())
+    parser = argparse.ArgumentParser(
+        prog='ex2_dictionary.py test',
+        description='testing for eidp 2023 ex2 dictionaries',
+    )
+    parser.add_argument('-v', '--verbose',
+                        help="don't print out test output", action="store_true")
+    parser.add_argument(
+        '-t', '--test_only', help='only test without writing readme', action="store_true")
+    args = parser.parse_args()
+
+    # print(options)
+    # print(f'verbose := {verbose}, backup := {backup}')
+
+    collector = ResultsCollector()
+    pytest.main(['test_dictionary.py', '-vv', '-s'], plugins=[collector])
+
+    readme_template = []
+    passed, failed, skipped = collector.get_results()
+
+    if args.verbose:
+        print(f"passed := {passed}")
+        print(f"failed := {failed}")
+        print(f"skipped := {skipped}")
+
+    if not args.test_only:
+        tests = dict([(name, f) for name, f in vars() if callable(
+            f) and hasattr(f, "is_test")])
+        passed_tests = list(map(lambda m: m[1], filter(
+            lambda m: m[0] in passed, tests)))
+        print(passed_tests)
diff --git a/src/util.py b/src/util.py
index d79b579..ff018db 100644
--- a/src/util.py
+++ b/src/util.py
@@ -1,6 +1,8 @@
 from typing import Callable, Any, TypeAliasType, Iterator
 from types import ModuleType
 import inspect
+import pytest
+import time
 
 
 def has_annotations(f: Callable, param_types: list[object], return_type: object = None) -> bool:
@@ -34,6 +36,61 @@ def eidp_test(message: str, minus_points: float) -> Callable[[Callable[..., Any]
     return wrapper
 
 
-def get_tests(module: ModuleType) -> dict[str, Callable[..., Any]]:
-    return dict([(name, f) for name, f in module.__dict__
-                 if callable(f) and hasattr(f, "is_test")])
+class ResultsCollector:
+    def __init__(self):
+        self.reports = []
+        self.collected = 0
+        self.exitcode = 0
+        self.passed = 0
+        self.failed = 0
+        self.xfailed = 0
+        self.skipped = 0
+        self.total_duration = 0
+
+    @pytest.hookimpl(hookwrapper=True)
+    def pytest_runtest_makereport(self, item, call):
+        outcome = yield
+        report = outcome.get_result()
+        if report.when == 'call':
+            self.reports.append(report)
+
+    def pytest_collection_modifyitems(self, items):
+        self.collected = len(items)
+
+    def pytest_terminal_summary(self, terminalreporter, exitstatus):
+        self.passed = len(terminalreporter.stats.get('passed', []))
+        self.failed = len(terminalreporter.stats.get('failed', []))
+        self.xfailed = len(terminalreporter.stats.get('xfailed', []))
+        self.skipped = len(terminalreporter.stats.get('skipped', []))
+        self.total_duration = time.time() - terminalreporter._sessionstarttime
+
+    def get_results(self) -> tuple[list[str], list[str], list[str]]:
+        passed = []
+        failed = []
+        skipped = []
+
+        for report in self.reports:
+            if report.outcome == 'passed':
+                passed.append(report.nodeid.split('::')[-1])
+            elif report.outcome == 'failed':
+                failed.append(report.nodeid.split('::')[-1])
+            elif report.outcome == 'skipped':
+                skipped.append(report.nodeid.split('::')[-1])
+
+        return passed, failed, skipped
+
+
+def parse_args(args: list[str]) -> dict[str, bool]:
+    arguments = args[1:]
+    retval = {'verbose': False, 'test': False, 'force': False}
+    for argument in arguments:
+        _args = argument[1:] if argument[0] == '-' else argument
+        for arg in _args:
+            match arg:
+                case 'v':
+                    retval['verbose'] = True
+                case 't':
+                    retval['test'] = True
+                case 'f':
+                    retval['force'] = True
+    return retval