PrimeIntellect-ai/verifiers

31.5

Adjusted Score

31.5

Raw Score

100%

Time Factor

2026-08-29

Last Push

4.6K

Stars

Python

Language

107.9K

Lines of Code

583

Files

2.5K

Pattern Hits

2026-08-29

Scan Date

0.20

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 117MEDIUM 186LOW 2210

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 2513 distinct pattern matches across 21 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers912 hits · 893 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_gepa_utils.py	15	def test_save_gepa_results_writes_best_system_prompt_verbatim(tmp_path):	CODE
LOW	tests/test_gepa_utils.py	29	def test_save_gepa_results_handles_none_best_score(tmp_path):	CODE
LOW	tests/test_gepa_utils.py	46	def test_save_gepa_results_writes_upload_schema_without_task_fields(tmp_path):	CODE
LOW	tests/test_gepa_utils.py	101	def test_save_gepa_results_writes_candidate_diffs_and_frontier(tmp_path):	CODE
LOW	tests/test_eval_utils.py	13	def test_print_results_rollout_indexing(capsys, make_metadata, make_state, make_input):	CODE
LOW	tests/test_eval_utils.py	62	def test_print_results_single_rollout(capsys, make_metadata, make_state, make_input):	CODE
LOW	tests/test_eval_utils.py	90	def test_print_results_includes_eval_name(capsys, make_metadata, make_output):	CODE
LOW	tests/test_eval_utils.py	106	def test_print_results_three_rollouts(capsys, make_metadata, make_state, make_input):	CODE
LOW	tests/test_eval_utils.py	139	def test_print_results_includes_usage(capsys, make_metadata, make_output):	CODE
LOW	tests/test_eval_utils.py	159	def test_attach_metadata_cost_uses_total_output_usage(make_metadata, make_output):	CODE
LOW	tests/test_eval_utils.py	188	def test_print_results_labels_cost_as_all(capsys, make_metadata, make_output):	CODE
LOW	tests/test_eval_utils.py	208	def test_print_results_handles_heterogeneous_metrics(	CODE
LOW⚡	tests/test_parser.py	9	def test_parser_initialization(self, basic_parser):	CODE
LOW⚡	tests/test_parser.py	14	def test_parse_returns_text_as_is(self, basic_parser):	CODE
LOW⚡	tests/test_parser.py	20	def test_get_assistant_messages(self, basic_parser):	CODE
LOW⚡	tests/test_parser.py	33	def test_parse_answer_with_string(self, basic_parser):	CODE
LOW⚡	tests/test_parser.py	39	def test_parse_answer_with_completion(self, basic_parser):	CODE
LOW⚡	tests/test_parser.py	48	def test_parse_answer_with_empty_completion(self, basic_parser):	CODE
LOW⚡	tests/test_parser.py	53	def test_parse_answer_with_no_assistant_messages(self, basic_parser):	CODE
LOW⚡	tests/test_parser.py	59	def test_get_format_reward_func(self, basic_parser):	CODE
LOW	tests/test_per_turn_timing.py	11	async def test_single_turn_records_one_model_span(self, mock_client, make_input):	CODE
LOW	tests/test_per_turn_timing.py	36	async def test_multi_turn_records_model_and_env_spans(	CODE
LOW⚡	tests/test_composable_env.py	149	def test_task_repr_no_sandbox():	CODE
LOW⚡	tests/test_composable_env.py	220	def test_composable_mini_swe_agent_install_script_uses_pip_requirement():	CODE
LOW⚡	tests/test_composable_env.py	227	def test_composable_opencode_install_script_owns_release_download():	CODE
LOW⚡	tests/test_composable_env.py	237	async def test_composable_env_exports_task_workdir():	CODE
LOW⚡	tests/test_composable_env.py	316	async def test_composable_env_install_env_passes_to_execute():	CODE
LOW⚡	tests/test_composable_env.py	558	def test_discover_sibling_dir_finds_skills(tmp_path, monkeypatch):	CODE
LOW⚡	tests/test_composable_env.py	565	def test_discover_sibling_dir_returns_none_without_skills(tmp_path, monkeypatch):	CODE
LOW⚡	tests/test_composable_env.py	575	def test_get_skills_dir_auto_discovers(tmp_path, monkeypatch):	CODE
LOW⚡	tests/test_composable_env.py	582	def test_get_skills_dir_returns_none_without_skills(tmp_path, monkeypatch):	CODE
LOW⚡	tests/test_composable_env.py	589	def test_get_upload_dirs_includes_skills_automatically(tmp_path, monkeypatch):	CODE
LOW⚡	tests/test_composable_env.py	597	def test_get_upload_dirs_empty_without_skills(tmp_path, monkeypatch):	CODE
LOW⚡	tests/test_composable_env.py	608	async def test_composable_env_collects_harness_metrics():	CODE
LOW	tests/test_composable_env.py	97	def test_sandbox_spec_defaults():	CODE
LOW	tests/test_composable_env.py	192	def test_composable_env_eval_inputs_can_shuffle_taskset_dataset():	CODE
LOW	tests/test_composable_env.py	256	async def test_composable_env_quotes_paths_in_mkdir_command():	CODE
LOW	tests/test_composable_env.py	284	async def test_composable_env_quotes_log_path_when_collecting_logs():	CODE
LOW	tests/test_composable_env.py	345	async def test_composable_env_install_env_none_by_default():	CODE
LOW	tests/test_composable_env.py	373	def _make_temp_taskset_package(tmp_path, monkeypatch, *, with_skills: bool):	CODE
LOW	tests/test_composable_env.py	411	async def test_composable_env_uploads_task_dirs(tmp_path, monkeypatch):	CODE
LOW	tests/test_composable_env.py	451	async def test_composable_env_no_upload_when_no_dirs(tmp_path, monkeypatch):	CODE
LOW	tests/test_composable_env.py	479	async def test_composable_env_uploads_harness_dirs(tmp_path):	CODE
LOW	tests/test_composable_env.py	520	async def test_composable_env_rejects_duplicate_task_and_harness_upload_names(	CODE
LOW	tests/test_composable_env.py	657	async def test_composable_env_metrics_with_key_whitelist():	CODE
LOW	tests/test_composable_env.py	694	async def test_composable_env_no_metrics_when_path_not_set():	CODE
LOW⚡	tests/test_opencode_rlm_env.py	50	def test_default_plugin_branch(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	54	def test_default_plugin_install_path(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	62	def test_default_sub_llm_max_turns(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	66	def test_default_sub_timeout_ms(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	95	def test_config_includes_plugin_reference(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	102	def test_config_custom_install_path(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	107	def test_config_has_schema_and_provider(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	114	def test_config_renders_valid_json_after_shell_expansion(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	156	def test_run_command_installs_jq(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	163	def test_run_command_installs_bun(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	167	def test_run_command_clones_plugin(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	174	def test_run_command_custom_branch(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	178	def test_run_command_bun_install(self):	CODE
LOW⚡	tests/test_opencode_rlm_env.py	182	def test_run_command_runs_opencode(self):	CODE
852 more matches not shown…

Cross-Language Confusion92 hits · 555 pts

Severity	File	Line	Snippet	Context
HIGH	…onments/bash_interception/bash_interception/taskset.py	8	REWRITE_COMMAND = f"git --version && touch {REWRITE_SENTINEL}"	CODE
HIGH⚡	tests/test_composable_env.py	306	"cat '/tmp/log dir/agent.log' 2>/dev/null \|\| echo '<no logs>'",	CODE
HIGH	tests/test_composable_env.py	445	"mkdir -p /task && tar -xzf /tmp/_upload_task_skills.tar.gz -C / && rm -f /tmp/_upload_task_skills.tar.gz",	CODE
HIGH	tests/test_composable_env.py	514	"mkdir -p /tmp && tar -xzf /tmp/_upload_tmp_agent-src.tar.gz -C / && rm -f /tmp/_upload_tmp_agent-src.tar.gz",	CODE
HIGH⚡	tests/test_opencode_rlm_env.py	180	assert "cd /tmp/opencode-rlm && bun install" in env.run_command	CODE
HIGH⚡	tests/test_harbor_env_mcp.py	245	env = _DummyEnv(mcp_launch_commands={"svc": "cd /opt && python server.py"})	CODE
HIGH⚡	tests/test_harbor_env_mcp.py	255	assert "'cd /opt && python server.py'" in start_cmd	CODE
HIGH	tests/test_rlm_composable_env.py	534	"mkdir -p /task && tar -xzf /tmp/_upload_task_rlm-skills.tar.gz -C / && rm -f /tmp/_upload_task_rlm-skills.tar.g	CODE
HIGH	tests/test_rlm_composable_env.py	703	"cat '/tmp/log dir/agent.log' 2>/dev/null \|\| echo '<no logs>'",	CODE
HIGH	verifiers/v1/agent.py	355	"one (e.g. bash or null)."	CODE
HIGH⚡	verifiers/v1/harnesses/node.py	12	node_ok() { "$node/bin/node" -e 'const [a,b]=process.versions.node.split(".").map(Number); process.exit(a>22 \|\| a===22 &	CODE
HIGH⚡	verifiers/v1/harnesses/node.py	12	node_ok() { "$node/bin/node" -e 'const [a,b]=process.versions.node.split(".").map(Number); process.exit(a>22 \|\| a===22 &	CODE
HIGH⚡	verifiers/v1/harnesses/node.py	16	if ! node -e 'const [a,b]=process.versions.node.split(".").map(Number); process.exit(a>22 \|\| a===22 && b>=19 ? 0 : 1	CODE
HIGH⚡	verifiers/v1/harnesses/node.py	16	if ! node -e 'const [a,b]=process.versions.node.split(".").map(Number); process.exit(a>22 \|\| a===22 && b>=19 ? 0 : 1	CODE
HIGH⚡	verifiers/v1/harnesses/node.py	26	\|\| { apt-get update -qq && apt-get install -y -qq curl ca-certificates >/dev/null; }	CODE
HIGH⚡	verifiers/v1/harnesses/node.py	26	\|\| { apt-get update -qq && apt-get install -y -qq curl ca-certificates >/dev/null; }	CODE
HIGH⚡	verifiers/v1/harnesses/node.py	28	if [ ! -x "$node/bin/node" ] \|\| [ "$("$node/bin/node" --version 2>/dev/null)" != "v$VF_NODE_VERSION" ]; then	CODE
HIGH	verifiers/v1/harnesses/node.py	44	f'until ln -s "$$" {lock} 2>/dev/null; do '	CODE
HIGH	verifiers/v1/harnesses/node.py	46	f'if ! kill -0 "$owner" 2>/dev/null; then '	CODE
HIGH	verifiers/v1/harnesses/prime_agent/harness.py	78	fs.writeFileSync(manifestPath, `${JSON.stringify(manifest, null, 2)}\n`);	CODE
HIGH	verifiers/v1/harnesses/prime_agent/harness.py	164	f'"$(command -v flock \|\| command -v lockf)" {lock} '	CODE
HIGH⚡	verifiers/v1/harnesses/openclaw/harness.py	25	command -v curl >/dev/null \|\| (apt-get update -qq && apt-get install -y -qq curl ca-certificates >/dev/null)	CODE
HIGH⚡	verifiers/v1/harnesses/openclaw/harness.py	25	command -v curl >/dev/null \|\| (apt-get update -qq && apt-get install -y -qq curl ca-certificates >/dev/null)	CODE
HIGH⚡	verifiers/v1/harnesses/openclaw/harness.py	39	[ -z "$acp_pid" ] \|\| kill -TERM -"$acp_pid" 2>/dev/null \|\| true	CODE
HIGH⚡	verifiers/v1/harnesses/openclaw/harness.py	40	[ -z "$gateway_pid" ] \|\| kill -TERM -"$gateway_pid" 2>/dev/null \|\| true	CODE
HIGH⚡	verifiers/v1/harnesses/openclaw/harness.py	42	[ -z "$acp_pid" ] \|\| kill -KILL -"$acp_pid" 2>/dev/null \|\| true	CODE
HIGH⚡	verifiers/v1/harnesses/openclaw/harness.py	43	[ -z "$gateway_pid" ] \|\| kill -KILL -"$gateway_pid" 2>/dev/null \|\| true	CODE
HIGH⚡	verifiers/v1/harnesses/openclaw/harness.py	44	[ -z "$acp_pid" ] \|\| wait "$acp_pid" 2>/dev/null \|\| true	CODE
HIGH⚡	verifiers/v1/harnesses/openclaw/harness.py	45	[ -z "$gateway_pid" ] \|\| wait "$gateway_pid" 2>/dev/null \|\| true	CODE
HIGH	verifiers/v1/harnesses/openclaw/harness.py	59	if ! kill -0 "$gateway_pid" 2>/dev/null; then	CODE
HIGH	verifiers/v1/harnesses/openclaw/harness.py	60	wait "$gateway_pid" 2>/dev/null \|\| true	CODE
HIGH	verifiers/v1/harnesses/openclaw/harness.py	126	f'"$(command -v flock \|\| command -v lockf)" {directory}/install.lock '	CODE
HIGH⚡	verifiers/v1/harnesses/kimi_code/harness.py	27	if [ -x "$bin" ] && [ "$("$bin" --version 2>/dev/null)" = "{version}" ]; then	CODE
HIGH⚡	verifiers/v1/harnesses/kimi_code/harness.py	30	command -v curl >/dev/null \|\| { apt-get update -qq && apt-get install -y -qq curl ca-certificates >/dev/null; }	CODE
HIGH⚡	verifiers/v1/harnesses/kimi_code/harness.py	30	command -v curl >/dev/null \|\| { apt-get update -qq && apt-get install -y -qq curl ca-certificates >/dev/null; }	CODE
HIGH	verifiers/v1/harnesses/kimi_code/harness.py	63	'"$(command -v flock \|\| command -v lockf)" '	CODE
HIGH	verifiers/v1/harnesses/codex/harness.py	72	f'"$(command -v flock \|\| command -v lockf)" {directory}/install.lock '	CODE
HIGH	verifiers/v1/harnesses/claude_code/harness.py	59	f'"$(command -v flock \|\| command -v lockf)" {directory}/install.lock '	CODE
HIGH	verifiers/v1/harnesses/pi/harness.py	38	if [ "$(cat "$packages/.versions" 2>/dev/null)" != "$versions" ]; then	CODE
HIGH	verifiers/v1/harnesses/pi/harness.py	75	f'until ln -s "$$" {lock} 2>/dev/null; do '	CODE
HIGH	verifiers/v1/harnesses/pi/harness.py	77	f'if ! kill -0 "$owner" 2>/dev/null; then '	CODE
HIGH	verifiers/v1/harnesses/rlm/harness.py	83	"{ apt-get update -qq && apt-get install -y -qq git; } && "	CODE
HIGH	verifiers/v1/harnesses/rlm/harness.py	84	f"rm -rf /tmp/rlm && git clone https://{RLM_REPO} /tmp/rlm && "	CODE
HIGH⚡	verifiers/v1/harnesses/pool/harness.py	19	command -v curl >/dev/null \|\| (apt-get update -qq && apt-get install -y -qq curl ca-certificates >/dev/null)	CODE
HIGH⚡	verifiers/v1/harnesses/pool/harness.py	19	command -v curl >/dev/null \|\| (apt-get update -qq && apt-get install -y -qq curl ca-certificates >/dev/null)	CODE
HIGH⚡	verifiers/v1/harnesses/pool/harness.py	20	command -v tar >/dev/null \|\| (apt-get update -qq && apt-get install -y -qq tar >/dev/null)	CODE
HIGH⚡	verifiers/v1/harnesses/pool/harness.py	20	command -v tar >/dev/null \|\| (apt-get update -qq && apt-get install -y -qq tar >/dev/null)	CODE
HIGH	verifiers/v1/harnesses/pool/harness.py	51	f'"$(command -v flock \|\| command -v lockf)" {directory}/install.lock '	CODE
HIGH	verifiers/v1/harnesses/terminus_2/harness.py	71	'tmux kill-server >/dev/null 2>&1 \|\| true; rm -rf "$TMUX_TMPDIR"',	CODE
HIGH⚡	verifiers/v1/runtimes/base.py	32	"{ command -v curl >/dev/null 2>&1 \|\| command -v wget >/dev/null 2>&1; } "	CODE
HIGH⚡	verifiers/v1/runtimes/base.py	33	"\|\| { apt-get update -qq && apt-get install -y -qq curl ca-certificates; } "	CODE
HIGH⚡	verifiers/v1/runtimes/base.py	37	"{ command -v curl >/dev/null 2>&1 && curl -LsSf https://astral.sh/uv/install.sh \| sh; } "	CODE
HIGH⚡	verifiers/v1/runtimes/base.py	38	"\|\| { command -v wget >/dev/null 2>&1 && wget -qO- https://astral.sh/uv/install.sh \| sh; }"	CODE
HIGH	verifiers/v1/runtimes/docker/__init__.py	97	'kill -"$1" "-$2" 2>/dev/null \|\| kill -"$1" "$2"',	CODE
HIGH	verifiers/v1/runtimes/docker/__init__.py	139	'kill -KILL "-$pid" 2>/dev/null \|\| kill -KILL "$pid" 2>/dev/null \|\| true; '	CODE
HIGH	verifiers/v1/runtimes/docker/__init__.py	364	'if [ -n "$HOST" ]; then apk add --no-cache iptables >/dev/null; fi; '	CODE
HIGH	verifiers/v1/tasksets/harbor/taskset.py	179	"tar --no-same-owner -xzf /tmp/environment.tgz && rm /tmp/environment.tgz",	CODE
HIGH	verifiers/v1/tasksets/harbor/taskset.py	277	"mkdir -p /logs/verifier /tests && tar -xzf /tmp/tests.tgz -C /tests"	CODE
HIGH	verifiers/legacy/envs/experimental/opencode_rlm_env.py	106	apt-get -o Acquire::Retries=3 update && apt-get -o Acquire::Retries=3 install -y curl git unzip jq	CODE
HIGH	verifiers/legacy/envs/experimental/opencode_env.py	61	apt-get -o Acquire::Retries=3 update && apt-get -o Acquire::Retries=3 install -y curl	CODE
32 more matches not shown…

Unused Imports616 hits · 518 pts

Severity	File	Line	Context
LOW	…ronments/nemo_gym_weather/nemo_gym_weather/__init__.py	1	CODE
LOW	…ronments/nemo_gym_weather/nemo_gym_weather/__init__.py	2	CODE
LOW	…yscale_interception/grayscale_interception/__init__.py	1	CODE
LOW	environments/deepwiki/deepwiki/__init__.py	1	CODE
LOW	environments/compact/compact/__init__.py	4	CODE
LOW	environments/compact/compact/__init__.py	4	CODE
LOW	…vironments/proposer_solver/proposer_solver/__init__.py	1	CODE
LOW	…vironments/proposer_solver/proposer_solver/__init__.py	1	CODE
LOW	…vironments/proposer_solver/proposer_solver/__init__.py	1	CODE
LOW	environments/kuhn_poker/kuhn_poker/__init__.py	1	CODE
LOW	environments/kuhn_poker/kuhn_poker/__init__.py	1	CODE
LOW	environments/interception/interception/__init__.py	1	CODE
LOW	environments/openenv_wordle/openenv_wordle/taskset.py	6	CODE
LOW	environments/openenv_wordle/openenv_wordle/__init__.py	1	CODE
LOW	environments/openenv_wordle/openenv_wordle/__init__.py	1	CODE
LOW	environments/wiki_search/wiki_search/__init__.py	1	CODE
LOW	environments/wiki_search/wiki_search/__init__.py	2	CODE
LOW	environments/scratchpad/scratchpad/__init__.py	1	CODE
LOW	…earch_interception/web_search_interception/__init__.py	1	CODE
LOW	…earch_interception/web_search_interception/__init__.py	1	CODE
LOW	…earch_interception/web_search_interception/__init__.py	2	CODE
LOW	environments/reverse_text/reverse_text/__init__.py	1	CODE
LOW	environments/wordle/wordle/__init__.py	1	CODE
LOW	environments/wordle/wordle/__init__.py	2	CODE
LOW	environments/alphabet_sort/alphabet_sort/__init__.py	1	CODE
LOW	environments/alphabet_sort/alphabet_sort/__init__.py	1	CODE
LOW	environments/gsm8k/gsm8k/__init__.py	1	CODE
LOW	…nments/bash_interception/bash_interception/__init__.py	1	CODE
LOW	environments/color_codeword/color_codeword/__init__.py	1	CODE
LOW	environments/color_codeword/color_codeword/__init__.py	1	CODE
LOW	environments/glossary/glossary/__init__.py	1	CODE
LOW	environments/code_golf/code_golf/__init__.py	1	CODE
LOW	environments/code_golf/code_golf/__init__.py	1	CODE
LOW	verifiers/__init__.py	152	CODE
LOW	verifiers/v1/trace.py	1	CODE
LOW	verifiers/v1/task.py	10	CODE
LOW	verifiers/v1/harness.py	1	CODE
LOW	verifiers/v1/graph.py	18	CODE
LOW	verifiers/v1/taskset.py	15	CODE
LOW	verifiers/v1/session.py	10	CODE
LOW	verifiers/v1/__init__.py	3	CODE
LOW	verifiers/v1/__init__.py	5	CODE
LOW	verifiers/v1/__init__.py	5	CODE
LOW	verifiers/v1/__init__.py	5	CODE
LOW	verifiers/v1/__init__.py	6	CODE
LOW	verifiers/v1/__init__.py	6	CODE
LOW	verifiers/v1/__init__.py	6	CODE
LOW	verifiers/v1/__init__.py	6	CODE
LOW	verifiers/v1/__init__.py	6	CODE
LOW	verifiers/v1/__init__.py	7	CODE
LOW	verifiers/v1/__init__.py	7	CODE
LOW	verifiers/v1/__init__.py	7	CODE
LOW	verifiers/v1/__init__.py	7	CODE
LOW	verifiers/v1/__init__.py	7	CODE
LOW	verifiers/v1/__init__.py	7	CODE
LOW	verifiers/v1/__init__.py	7	CODE
LOW	verifiers/v1/__init__.py	16	CODE
LOW	verifiers/v1/__init__.py	17	CODE
LOW	verifiers/v1/__init__.py	17	CODE
LOW	verifiers/v1/__init__.py	18	CODE
556 more matches not shown…

Decorative Section Separators83 hits · 306 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/test_composable_env.py	139	# ── Task from plain TaskSet ────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_composable_env.py	155	# ── TaskSet ─────────────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_composable_env.py	312	# ── install_env ──────────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_composable_env.py	555	# ── discover_sibling_dir ─────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_composable_env.py	572	# ── get_skills_dir / auto-discovery ──────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_composable_env.py	604	# ── Harness metrics collection ───────────────────────────────────────────	COMMENT
MEDIUM	tests/test_composable_env.py	30	# ── Mock Rubrics ──────────────────────────────────────────────────────	COMMENT
MEDIUM	tests/test_composable_env.py	51	# ── Mock TaskSets ───────────────────────────────────────────────────────	COMMENT
MEDIUM	tests/test_composable_env.py	94	# ── SandboxSpec ─────────────────────────────────────────────────────────	COMMENT
MEDIUM	tests/test_composable_env.py	109	# ── Task from SandboxTaskSet ───────────────────────────────────────────	COMMENT
MEDIUM	tests/test_composable_env.py	370	# ── get_upload_dirs ──────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	40	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	42	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	89	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	91	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	150	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	152	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	187	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	189	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	246	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	248	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	282	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	284	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	342	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_opencode_rlm_env.py	344	# =============================================================================	COMMENT
MEDIUM	tests/test_opencode_rlm_env.py	20	# =============================================================================	COMMENT
MEDIUM	tests/test_opencode_rlm_env.py	22	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_renderer_client.py	822	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_renderer_client.py	824	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_renderer_client.py	866	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_renderer_client.py	868	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_renderer_client.py	599	# ── Parity across real renderers: truncated most-recent step ──────────	COMMENT
MEDIUM⚡	tests/test_rlm_composable_env.py	177	# ── RLM harness ──────────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_rlm_composable_env.py	654	# ── RLM metrics via harness fields ──────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_rlm_composable_env.py	806	# ── keep_trajectory_step end-to-end (header-stash ordering) ──────────────	COMMENT
MEDIUM	tests/test_rlm_composable_env.py	450	# ── install_env ──────────────────────────────────────────────────────────	COMMENT
MEDIUM	tests/test_rlm_composable_env.py	497	# ── Skills upload ────────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_browser_env.py	45	# ============================================================================	COMMENT
MEDIUM⚡	tests/test_browser_env.py	47	# ============================================================================	COMMENT
MEDIUM⚡	tests/test_browser_env.py	386	# ============================================================================	COMMENT
MEDIUM⚡	tests/test_browser_env.py	388	# ============================================================================	COMMENT
MEDIUM	tests/test_browser_env.py	18	# ============================================================================	COMMENT
MEDIUM	tests/test_browser_env.py	20	# ============================================================================	COMMENT
MEDIUM	tests/test_browser_env.py	457	# ============================================================================	COMMENT
MEDIUM	tests/test_browser_env.py	459	# ============================================================================	COMMENT
MEDIUM	tests/test_context_token_metrics.py	16	# =========================================================================	COMMENT
MEDIUM	tests/test_context_token_metrics.py	18	# =========================================================================	COMMENT
MEDIUM	tests/test_context_token_metrics.py	63	# =========================================================================	COMMENT
MEDIUM	tests/test_context_token_metrics.py	65	# =========================================================================	COMMENT
MEDIUM	tests/test_context_token_metrics.py	179	# =========================================================================	COMMENT
MEDIUM	tests/test_context_token_metrics.py	181	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_sandbox_mixin.py	79	# ── create_sandbox ───────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_sandbox_mixin.py	180	# ── post_sandbox_setup ───────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_sandbox_mixin.py	188	# ── delete_sandbox ───────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_sandbox_mixin.py	208	# ── bulk_delete_sandboxes ────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_sandbox_mixin.py	231	# ── run_background_job ───────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_sandbox_mixin.py	275	# ── teardown_sandboxes ──────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_sandbox_mixin.py	322	# ── teardown_sandbox_client ──────────────────────────────────────────	COMMENT
MEDIUM	tests/test_sandbox_mixin.py	47	# ── init_sandbox_client ──────────────────────────────────────────────	COMMENT
MEDIUM	tests/test_sandbox_mixin.py	361	# ── SandboxTimeouts ──────────────────────────────────────────────────	COMMENT
23 more matches not shown…

AI Slop Vocabulary79 hits · 245 pts

Severity	File	Line	Snippet	Context
MEDIUM	…ayscale_interception/grayscale_interception/taskset.py	13	# The last request message is the new user input, before the harness stores it.	COMMENT
MEDIUM	environments/interception/interception/taskset.py	11	# A response stop runs while the response is buffered, before the harness	COMMENT
MEDIUM	…earch_interception/web_search_interception/__init__.py	4	# Exporting Codex beside the taskset makes it this example's default harness, so	COMMENT
MEDIUM⚡	tests/test_rlm_composable_env.py	177	# ── RLM harness ──────────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/test_rlm_composable_env.py	654	# ── RLM metrics via harness fields ──────────────────────────────────────	COMMENT
MEDIUM	tests/v1/conftest.py	22	uv run pytest tests/v1 -n auto -m bash # only the bash harness	STRING
MEDIUM	tests/v1/conftest.py	76	# `compact` (an example harness) and `terminus-2` (drives the host tmux) are excluded from e2e.	COMMENT
MEDIUM⚡	tests/v1/test_e2e.py	96	# harness runtime x tool placement: every axis value once plus the two-container case	COMMENT
MEDIUM⚡	tests/v1/test_e2e.py	97	# (harness and tool in separate docker boxes) and a prime-colocated row (a tool in its	COMMENT
MEDIUM⚡	tests/v1/test_e2e.py	98	# OWN prime sandbox needs port exposure; colocated rides the harness's box).	COMMENT
MEDIUM⚡	tests/v1/test_e2e.py	618	# The tool was advertised to the masked chat, regardless of harness qualification.	COMMENT
MEDIUM	tests/v1/test_e2e.py	18	# harness x harness runtime: every harness once, both local runtimes hit (subprocess	COMMENT
MEDIUM	tests/v1/test_e2e.py	36	# harness x harness runtime for the shell task: every coding agent once (null is a chat	COMMENT
MEDIUM	tests/v1/test_e2e.py	55	# The scripted user runs in the eval process itself (no placement axis); the harness	COMMENT
MEDIUM	tests/v1/test_e2e.py	65	# retain MCP access after resuming. Cover every harness in the local container runtime,	COMMENT
MEDIUM	tests/v1/test_e2e.py	307	# The interception server captured the harness's advertised name and schema. Harnesses	COMMENT
MEDIUM	tests/v1/test_e2e.py	580	# assistant's harness while the task's rewards score off non-prompt fields	COMMENT
MEDIUM⚡	tests/v1/test_e2e.py	629	harness=None, # both seats pin the null harness themselves	CODE
MEDIUM	tests/v1/test_e2e.py	430	harness=None, # both duet seats pin their own harness	CODE
MEDIUM	tests/v1/test_e2e.py	459	harness=None, # a multi-agent env refuses the run-level harness	CODE
MEDIUM	tests/v1/test_e2e.py	661	harness=None, # both duet seats pin their own harness	CODE
MEDIUM	verifiers/v1/env.py	116	# Same harness config -> one loaded object (harnesses are stateless values).	COMMENT
MEDIUM	verifiers/v1/env.py	127	# Warn once per distinct harness; tool-less chat loops are exempt.	COMMENT
MEDIUM	verifiers/v1/env.py	207	# Unpinned fields fall back to the run's ctx / the taskset's harness.	COMMENT
MEDIUM	verifiers/v1/__init__.py	271	# taskset / harness / runtime / environment	COMMENT
MEDIUM	verifiers/v1/rollout.py	221	# Task setup and harness provisioning share one setup-stage deadline.	COMMENT
MEDIUM	verifiers/v1/rollout.py	240	# The harness reaches the model at `{base_url}/v1`; tool servers reach this	COMMENT
MEDIUM	verifiers/v1/rollout.py	367	# Prefer an intercepted model/tool error to the harness exit it caused.	COMMENT
MEDIUM	verifiers/v1/rollout.py	383	# harness's own I/O with no expired deadline stays the raw failure.	COMMENT
MEDIUM	verifiers/v1/rollout.py	394	except Exception as e: # noqa: BLE001 - harness boundary records every rollout failure	CODE
MEDIUM	verifiers/v1/rollout.py	412	# A harness that completes cleanly after a failed model call handled it (e.g. it	COMMENT
MEDIUM	verifiers/v1/rollout.py	414	# harness that dies on it surfaces the stashed error through the except above.	COMMENT
MEDIUM	verifiers/v1/agent.py	342	# Multi-turn capability is derived: a harness needs transcript replay, a	COMMENT
MEDIUM	verifiers/v1/agent.py	672	# `Agent.interaction()` may fail before yielding (e.g. task/harness setup).	COMMENT
MEDIUM	verifiers/v1/clients/train.py	440	# deterministic 400, so the harness SDK never retries it.	COMMENT
MEDIUM	verifiers/v1/clients/eval.py	22	# The harness uses this rollout secret to authenticate with the localhost server.	COMMENT
MEDIUM	verifiers/v1/clients/eval.py	85	# failure — map these to a retryable 502 so the harness SDK retries the	COMMENT
MEDIUM⚡	verifiers/v1/interception/server.py	68	# Each session proxies one rollout's own harness requests, so aiohttp's default 1 MiB body	COMMENT
MEDIUM⚡	verifiers/v1/interception/server.py	70	# and the harness gets a 413. Allow large bodies; the upstream provider and the model's	COMMENT
MEDIUM⚡	verifiers/v1/interception/server.py	962	# The harness went away mid-stream; the provider exchange still happened.	COMMENT
MEDIUM	verifiers/v1/interception/server.py	438	# A malformed harness knob must not kill recording (this runs in the	COMMENT
MEDIUM	verifiers/v1/interception/server.py	717	# Stash the real cause; the rollout re-raises it after the harness returns.	COMMENT
MEDIUM	verifiers/v1/interception/server.py	718	# Relay the provider's status so the harness SDK retries 5xx/429 and not 4xx.	COMMENT
MEDIUM	verifiers/v1/interception/server.py	741	# A cancelled exchange (harness disconnect, shutdown) is still	COMMENT
MEDIUM	verifiers/v1/harnesses/bash/harness.py	16	# harness-injected prompt). The edit clause is appended only when the `edit` tool is enabled.	COMMENT
MEDIUM	verifiers/v1/harnesses/bash/harness.py	85	# inheriting it via $SERPER_API_KEY / /proc/self/environ. Prefer a key set in the harness	COMMENT
MEDIUM	verifiers/v1/harnesses/bash/harness.py	86	# env (harness config env / forward_env); fall back to the host env only when the key is	COMMENT
MEDIUM	verifiers/v1/harnesses/null/program.py	218	# Context exhaustion is a budget limit, not a crash: this harness has no	COMMENT
MEDIUM	verifiers/v1/harnesses/browser_use/harness.py	75	# prompt, that transcript already contains this harness prompt.	COMMENT
MEDIUM	verifiers/v1/harnesses/browser_use/program.py	4	# "browser-harness==0.1.8",	COMMENT
MEDIUM	verifiers/v1/harnesses/browser_use/program.py	106	# browser-harness uses five seconds for this same DevTools HTTP probe.	COMMENT
MEDIUM	verifiers/v1/runtimes/modal.py	133	"infinity", # keep-alive entrypoint; the harness runs via `exec`	CODE
MEDIUM	verifiers/v1/mcp/launch.py	356	# Colocated servers inherit the harness cut. A separately provisioned filtered	COMMENT
MEDIUM⚡	verifiers/v1/mcp/launch.py	392	# The harness consumes the server, and decides reachability: colocated when the	COMMENT
MEDIUM⚡	verifiers/v1/mcp/launch.py	393	# server shares the harness's runtime, reached with the harness's locality (read	COMMENT
MEDIUM⚡	verifiers/v1/mcp/launch.py	394	# off the harness runtime when there is one, else `harness_is_local` for an	COMMENT
MEDIUM	verifiers/v1/cli/debug.py	200	# No agent plays here (no model, no harness): the seat records the	COMMENT
MEDIUM	verifiers/v1/cli/init.py	194	uv run eval {dash} -n 3 # evaluate a few tasks with the bash harness	STRING
MEDIUM	verifiers/v1/cli/dashboard/eval.py	246	# row per seat when they diverge (a judge on its own harness/runtime).	COMMENT
MEDIUM	verifiers/v1/cli/dashboard/eval.py	591	# The trace's own stamp, not the run-level runtime: a role's harness	COMMENT
19 more matches not shown…

Excessive Try-Catch Wrapping230 hits · 235 pts

Severity	File	Line	Snippet	Context
LOW	environments/gsm8k/gsm8k/verify.py	29	except Exception: # noqa: BLE001 - malformed answers can fail anywhere in math-verify	CODE
LOW	verifiers/v1/env.py	279	except Exception as e: # noqa: BLE001 - episode boundary records every hook failure	CODE
LOW	verifiers/v1/env.py	293	except Exception as e: # noqa: BLE001 - episode boundary records every hook failure	CODE
LOW	verifiers/v1/session.py	234	except Exception as error:	CODE
LOW	verifiers/v1/session.py	315	except Exception as error:	CODE
LOW	verifiers/v1/rollout.py	332	except Exception as e: # noqa: BLE001 - setup boundary records every rollout failure	CODE
LOW	verifiers/v1/rollout.py	394	except Exception as e: # noqa: BLE001 - harness boundary records every rollout failure	CODE
LOW	verifiers/v1/rollout.py	453	except Exception:	CODE
LOW	verifiers/v1/rollout.py	488	except Exception as e: # noqa: BLE001 - finalize boundary records every rollout failure	CODE
LOW	verifiers/v1/rollout.py	512	except Exception:	CODE
LOW	verifiers/v1/rollout.py	522	except Exception:	CODE
LOW	verifiers/v1/agent.py	482	except Exception as e:	CODE
LOW	verifiers/v1/errors.py	88	except Exception as e:	CODE
LOW⚡	verifiers/v1/interception/server.py	950	except Exception as e: # noqa: BLE001 - defer parser failure	CODE
LOW⚡	verifiers/v1/interception/server.py	959	except Exception as e: # noqa: BLE001 - defer parser failure	CODE
LOW	verifiers/v1/interception/server.py	607	except Exception as error: # noqa: BLE001 - surface task hook failures	CODE
LOW	verifiers/v1/interception/server.py	731	except Exception as e: # noqa: BLE001 - surface as an API error	CODE
LOW	verifiers/v1/interception/server.py	806	except Exception as e: # noqa: BLE001 - surface as an API error	CODE
LOW	verifiers/v1/interception/server.py	852	except Exception as e: # noqa: BLE001 - malformed provider stream	CODE
LOW	verifiers/v1/interception/server.py	1051	except Exception as e: # noqa: BLE001 - surface auxiliary relay failures	CODE
LOW	verifiers/v1/interception/tunnel/prime.py	53	except Exception as e:	CODE
LOW	verifiers/v1/harnesses/bash/program.py	132	except Exception as e: # noqa: BLE001 - tool failures are returned to the model	CODE
LOW	verifiers/v1/harnesses/bash/program.py	146	except Exception as e: # noqa: BLE001 - tool failures are returned to the model	CODE
LOW	verifiers/v1/harnesses/bash/program.py	168	except Exception as e: # noqa: BLE001 - tool failures are returned to the model	CODE
LOW	verifiers/v1/harnesses/bash/program.py	175	except Exception as e: # noqa: BLE001 - tool failures are returned to the model	CODE
LOW	verifiers/v1/harnesses/browser_use/program.py	172	except Exception as e: # noqa: BLE001 - tool failures are returned to the model	CODE
LOW	verifiers/v1/harnesses/terminus_2/harness.py	75	except Exception:	CODE
LOW	verifiers/v1/runtimes/prime.py	287	except Exception as e:	CODE
LOW	verifiers/v1/runtimes/prime.py	337	except Exception as e:	CODE
LOW	verifiers/v1/runtimes/prime.py	349	except Exception as e: # surface prime's exposure constraints actionably	CODE
LOW	verifiers/v1/runtimes/prime.py	369	except Exception as e:	CODE
LOW	verifiers/v1/runtimes/prime.py	385	except Exception as e:	CODE
LOW	verifiers/v1/runtimes/prime.py	407	except Exception as e:	CODE
LOW	verifiers/v1/runtimes/prime.py	430	except Exception as e: # noqa: BLE001 - provider teardown is best-effort	CODE
LOW	verifiers/v1/runtimes/modal.py	168	except Exception as e:	CODE
LOW	verifiers/v1/runtimes/modal.py	230	except Exception:	CODE
LOW	verifiers/v1/runtimes/modal.py	246	except Exception as e:	CODE
LOW⚡	verifiers/v1/runtimes/modal.py	271	except Exception as e:	CODE
LOW⚡	verifiers/v1/runtimes/modal.py	282	except Exception as e:	CODE
LOW	verifiers/v1/runtimes/modal.py	306	except Exception as e: # noqa: BLE001 - provider teardown is best-effort	CODE
MEDIUM	verifiers/v1/runtimes/modal.py	117	def start(self) -> None:	CODE
LOW	verifiers/v1/runtimes/base.py	217	except Exception: # noqa: BLE001 - failing to exec at all means the box is gone	CODE
LOW	verifiers/v1/runtimes/docker/egress.py	324	except Exception: # noqa: BLE001 - proxy failures become a generic 502	CODE
LOW	verifiers/v1/utils/git.py	169	except Exception: # noqa: BLE001, S110 - cleanup must never fail the rollout	CODE
LOW	verifiers/v1/utils/platform.py	311	except Exception as e: # noqa: BLE001 - push is best-effort across the full upload	CODE
LOW	verifiers/v1/utils/artifacts.py	159	except Exception:	CODE
LOW	verifiers/v1/mcp/launch.py	63	except Exception:	CODE
LOW	verifiers/v1/cli/validate.py	258	except Exception as e: # noqa: BLE001 - validation reports plugin failures per task	CODE
LOW	verifiers/v1/cli/validate.py	263	except Exception:	CODE
LOW	verifiers/v1/cli/replay.py	112	except Exception:	CODE
LOW	verifiers/v1/cli/replay.py	169	except Exception as exc:	CODE
LOW	verifiers/v1/cli/debug.py	161	except Exception as e: # noqa: BLE001 - report any debug action failure	CODE
LOW	verifiers/v1/cli/debug.py	250	except Exception as e: # noqa: BLE001 - persist any framework failure on the trace	CODE
LOW	verifiers/v1/cli/debug.py	261	except Exception:	CODE
LOW	verifiers/v1/cli/eval/resume.py	72	except Exception: # noqa: BLE001, S112	CODE
LOW	verifiers/v1/tasksets/harbor/env.py	124	except Exception as e: # noqa: BLE001 - each attempt's failure is retried	CODE
LOW	verifiers/v1/serve/pool.py	206	except Exception: # noqa: BLE001 - one bad frame must not kill the broker	CODE
LOW	verifiers/v1/serve/pool.py	360	except Exception:	CODE
LOW	verifiers/v1/envs/agentic_judge/env.py	192	except Exception as e:	CODE
LOW	verifiers/v1/acp/runner.py	292	except Exception as error: # noqa: BLE001 - serialize protocol failures	CODE
170 more matches not shown…

Modern Structural Boilerplate193 hits · 199 pts

Severity	File	Line	Snippet	Context
LOW	…ronments/nemo_gym_weather/nemo_gym_weather/__init__.py	4	__all__ = ["NeMoGymEnv", "NeMoGymWeatherTaskset"]	CODE
LOW	…yscale_interception/grayscale_interception/__init__.py	3	__all__ = ["GrayscaleInterceptionTaskset"]	CODE
LOW	environments/deepwiki/deepwiki/__init__.py	3	__all__ = ["DeepWikiTaskset"]	CODE
LOW	environments/compact/compact/__init__.py	6	__all__ = ["CompactingHarness", "CompactingHarnessConfig"]	CODE
LOW	…vironments/proposer_solver/proposer_solver/__init__.py	7	__all__ = ["ProposerSolverEnv", "ProposerSolverEnvConfig", "ProposerSolverTaskset"]	CODE
LOW	environments/kuhn_poker/kuhn_poker/__init__.py	3	__all__ = ["KuhnPokerEnv", "KuhnPokerTaskset"]	CODE
LOW	environments/interception/interception/__init__.py	3	__all__ = ["InterceptionTaskset"]	CODE
LOW	environments/openenv_wordle/openenv_wordle/taskset.py	13	__all__ = ["OpenEnvEnv", "OpenEnvWordleConfig", "OpenEnvWordleTaskset"]	CODE
LOW	environments/openenv_wordle/openenv_wordle/__init__.py	3	__all__ = ["OpenEnvEnv", "OpenEnvWordleTaskset"]	CODE
LOW	environments/wiki_search/wiki_search/__init__.py	4	__all__ = ["WikiSearchJudge", "WikiSearchTaskset"]	CODE
LOW	environments/wiki_search/wiki_search/judge.py	20	__all__ = ["WikiSearchJudge", "WikiSearchJudgeConfig"]	CODE
LOW	environments/scratchpad/scratchpad/__init__.py	3	__all__ = ["ScratchpadTaskset"]	CODE
LOW	…earch_interception/web_search_interception/__init__.py	6	__all__ = [	CODE
LOW	environments/reverse_text/reverse_text/__init__.py	3	__all__ = ["ReverseTextTaskset"]	CODE
LOW	environments/wordle/wordle/__init__.py	4	__all__ = ["TextArenaEnv", "WordleTaskset"]	CODE
LOW	environments/alphabet_sort/alphabet_sort/__init__.py	3	__all__ = ["AlphabetSortEnv", "AlphabetSortTaskset"]	CODE
LOW	environments/gsm8k/gsm8k/__init__.py	3	__all__ = ["GSM8KTaskset"]	CODE
LOW	…nments/bash_interception/bash_interception/__init__.py	3	__all__ = ["BashInterceptionTaskset"]	CODE
LOW	environments/color_codeword/color_codeword/__init__.py	3	__all__ = ["ColorCodewordEnv", "ColorCodewordTaskset"]	CODE
LOW	environments/glossary/glossary/__init__.py	3	__all__ = ["GlossaryTaskset"]	CODE
LOW	environments/code_golf/code_golf/__init__.py	3	__all__ = ["CodeGolfEnv", "CodeGolfTaskset"]	CODE
LOW	verifiers/v1/task.py	42	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/harness.py	27	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/env.py	39	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/session.py	36	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/__init__.py	188	__all__ = [ # noqa: RUF022 - grouped by public API area	CODE
LOW	verifiers/v1/rollout.py	37	logger = logging.getLogger(__name__)	CODE
LOW⚡	verifiers/v1/agent.py	52	__all__ = ["Agent", "AgentConfig", "Agents", "TimeoutConfig", "make_agent"]	CODE
LOW⚡	verifiers/v1/agent.py	54	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/clients/__init__.py	11	__all__ = [	CODE
LOW	verifiers/v1/clients/train.py	35	logger = logging.getLogger(__name__)	CODE
LOW⚡	verifiers/v1/interception/server.py	65	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/interception/__init__.py	104	__all__ = [	CODE
LOW	verifiers/v1/interception/pool.py	32	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/interception/tunnel/__init__.py	22	__all__ = [	CODE
LOW	verifiers/v1/gepa/runner.py	26	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/gepa/__init__.py	5	__all__ = ["GEPAAdapter", "GEPAConfig", "run_gepa"]	CODE
LOW	verifiers/v1/harnesses/__init__.py	31	__all__ = [	CODE
LOW	verifiers/v1/harnesses/prime_agent/harness.py	17	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/harnesses/prime_agent/__init__.py	6	__all__ = ["PrimeAgentHarness", "PrimeAgentHarnessConfig"]	CODE
LOW⚡	verifiers/v1/harnesses/openclaw/harness.py	18	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/harnesses/openclaw/__init__.py	6	__all__ = ["OpenClawHarness", "OpenClawHarnessConfig"]	CODE
LOW⚡	verifiers/v1/harnesses/kimi_code/harness.py	17	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/harnesses/kimi_code/__init__.py	6	__all__ = ["KimiCodeHarness", "KimiCodeHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/codex/harness.py	20	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/harnesses/codex/__init__.py	3	__all__ = ["CodexHarness", "CodexHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/claude_code/__init__.py	6	__all__ = ["ClaudeCodeHarness", "ClaudeCodeHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/bash/__init__.py	6	__all__ = ["BashHarness", "BashHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/pi/harness.py	18	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/harnesses/pi/__init__.py	3	__all__ = ["PiHarness", "PiHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/null/__init__.py	3	__all__ = ["NullHarness", "NullHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/rlm/harness.py	17	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/harnesses/rlm/__init__.py	3	__all__ = ["RLMHarness", "RLMHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/mini_swe_agent/__init__.py	6	__all__ = ["MiniSWEAgentHarness", "MiniSWEAgentHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/browser_use/__init__.py	6	__all__ = ["BrowserUseHarness", "BrowserUseHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/pool/__init__.py	3	__all__ = ["PoolHarness", "PoolHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/hermes_agent/__init__.py	6	__all__ = ["HermesAgentHarness", "HermesAgentHarnessConfig"]	CODE
LOW	verifiers/v1/harnesses/terminus_2/harness.py	14	logger = logging.getLogger(__name__)	CODE
LOW	verifiers/v1/harnesses/terminus_2/__init__.py	6	__all__ = ["Terminus2Harness", "Terminus2HarnessConfig"]	CODE
LOW	verifiers/v1/runtimes/prime.py	38	logger = logging.getLogger(__name__)	CODE
133 more matches not shown…

Deep Nesting169 hits · 144 pts

Severity	File	Line	Context
LOW	…ayscale_interception/grayscale_interception/taskset.py	12	CODE
LOW	environments/wiki_search/wiki_search/servers/wiki.py	77	CODE
LOW	environments/alphabet_sort/alphabet_sort/taskset.py	116	CODE
LOW	tests/conftest.py	325	CODE
LOW	tests/conftest.py	337	CODE
LOW	tests/test_renderer_client.py	633	CODE
LOW	tests/test_gym_env.py	71	CODE
LOW	verifiers/v1/graph.py	228	CODE
LOW	verifiers/v1/session.py	155	CODE
LOW	verifiers/v1/agent.py	176	CODE
LOW	verifiers/v1/interception/server.py	474	CODE
LOW	verifiers/v1/interception/server.py	765	CODE
LOW	verifiers/v1/interception/server.py	655	CODE
LOW	verifiers/v1/gepa/adapter.py	84	CODE
LOW	verifiers/v1/harnesses/bash/program.py	337	CODE
LOW	verifiers/v1/harnesses/browser_use/program.py	318	CODE
LOW	verifiers/v1/runtimes/modal.py	193	CODE
LOW	verifiers/v1/runtimes/docker/egress.py	134	CODE
LOW	verifiers/v1/utils/generic.py	42	CODE
LOW	verifiers/v1/utils/score.py	142	CODE
LOW	verifiers/v1/cli/validate.py	107	CODE
LOW	verifiers/v1/cli/dashboard/eval.py	533	CODE
LOW	verifiers/v1/cli/dashboard/base.py	81	CODE
LOW	verifiers/v1/cli/eval/resume.py	24	CODE
LOW	verifiers/v1/tasksets/nemo_gym/response.py	11	CODE
LOW	verifiers/v1/tasksets/lean/scoring.py	102	CODE
LOW	verifiers/v1/dialects/responses.py	413	CODE
LOW	verifiers/v1/dialects/responses.py	549	CODE
LOW	verifiers/v1/dialects/chat.py	238	CODE
LOW	verifiers/v1/dialects/chat.py	374	CODE
LOW	verifiers/v1/dialects/chat.py	524	CODE
LOW	verifiers/v1/dialects/anthropic.py	107	CODE
LOW	verifiers/v1/dialects/anthropic.py	298	CODE
LOW	verifiers/v1/dialects/anthropic.py	363	CODE
LOW	verifiers/v1/dialects/anthropic.py	579	CODE
LOW	verifiers/v1/dialects/base.py	52	CODE
LOW	verifiers/v1/serve/server.py	105	CODE
LOW	verifiers/v1/serve/encoding.py	26	CODE
LOW	verifiers/v1/serve/pool.py	166	CODE
LOW	verifiers/v1/acp/runner.py	269	CODE
LOW	verifiers/v1/acp/runner.py	228	CODE
LOW	verifiers/v1/acp/__init__.py	282	CODE
LOW	verifiers/legacy/clients/openai_responses_client.py	268	CODE
LOW	verifiers/legacy/clients/openai_responses_client.py	315	CODE
LOW	verifiers/legacy/clients/openai_responses_client.py	328	CODE
LOW	verifiers/legacy/clients/anthropic_messages_client.py	104	CODE
LOW	verifiers/legacy/clients/anthropic_messages_client.py	382	CODE
LOW	verifiers/legacy/clients/anthropic_messages_client.py	407	CODE
LOW	verifiers/legacy/clients/anthropic_messages_client.py	107	CODE
LOW	verifiers/legacy/clients/anthropic_messages_client.py	169	CODE
LOW	verifiers/legacy/clients/anthropic_messages_client.py	230	CODE
LOW	verifiers/legacy/clients/anthropic_messages_client.py	408	CODE
LOW	verifiers/legacy/clients/openai_completions_client.py	51	CODE
LOW	verifiers/legacy/clients/client.py	108	CODE
LOW	…fiers/legacy/clients/openai_chat_completions_client.py	111	CODE
LOW	…fiers/legacy/clients/openai_chat_completions_client.py	191	CODE
LOW	…fiers/legacy/clients/openai_chat_completions_client.py	273	CODE
LOW	…fiers/legacy/clients/openai_chat_completions_client.py	206	CODE
LOW	…legacy/clients/openai_chat_completions_token_client.py	29	CODE
LOW	verifiers/legacy/clients/renderer_client.py	152	CODE
109 more matches not shown…

Cross-File Repetition22 hits · 110 pts

Severity	File	Snippet	Context
HIGH	verifiers/v1/task.py	timeout (in seconds) for the agent's solve attempt.	STRING
HIGH	verifiers/v1/rollout.py	timeout (in seconds) for the agent's solve attempt.	STRING
HIGH	verifiers/v1/configs/agent.py	timeout (in seconds) for the agent's solve attempt.	STRING
HIGH	verifiers/v1/harnesses/bash/program.py	one fresh streamable-http session to an mcp server, opened and closed within the caller's task so anyio cancellation sco	STRING
HIGH	verifiers/v1/harnesses/null/program.py	one fresh streamable-http session to an mcp server, opened and closed within the caller's task so anyio cancellation sco	STRING
HIGH	verifiers/v1/harnesses/browser_use/program.py	one fresh streamable-http session to an mcp server, opened and closed within the caller's task so anyio cancellation sco	STRING
HIGH	verifiers/v1/harnesses/bash/program.py	run one session-scoped operation, retrying transient failures with backoff. a call whose response was lost may be replay	STRING
HIGH	verifiers/v1/harnesses/null/program.py	run one session-scoped operation, retrying transient failures with backoff. a call whose response was lost may be replay	STRING
HIGH	verifiers/v1/harnesses/browser_use/program.py	run one session-scoped operation, retrying transient failures with backoff. a call whose response was lost may be replay	STRING
HIGH	verifiers/v1/harnesses/bash/program.py	call a tool on a fresh session per attempt — see `with_retry` for the replay semantics. the result is converted outside	STRING
HIGH	verifiers/v1/harnesses/null/program.py	call a tool on a fresh session per attempt — see `with_retry` for the replay semantics. the result is converted outside	STRING
HIGH	verifiers/v1/harnesses/browser_use/program.py	call a tool on a fresh session per attempt — see `with_retry` for the replay semantics. the result is converted outside	STRING
HIGH	…envs/experimental/composable/tasksets/harbor/harbor.py	apply gold patch, run tests, and check if reward > 0. exceptions propagate to the caller (``taskset.validate``) so that	STRING
HIGH	…erimental/composable/tasksets/swe/swe_bench/taskset.py	apply gold patch, run tests, and check if reward > 0. exceptions propagate to the caller (``taskset.validate``) so that	STRING
HIGH	…xperimental/composable/tasksets/swe/openswe/taskset.py	apply gold patch, run tests, and check if reward > 0. exceptions propagate to the caller (``taskset.validate``) so that	STRING
HIGH	…erimental/composable/tasksets/swe/multi_swe/taskset.py	apply gold patch, run tests, and check if reward > 0. exceptions propagate to the caller (``taskset.validate``) so that	STRING
HIGH	…xperimental/composable/tasksets/swe/r2e_gym/taskset.py	apply gold patch, run tests, and check if reward > 0. exceptions propagate to the caller (``taskset.validate``) so that	STRING
HIGH	…perimental/composable/tasksets/swe/swe_lego/taskset.py	apply gold patch, run tests, and check if reward > 0. exceptions propagate to the caller (``taskset.validate``) so that	STRING
HIGH	…perimental/composable/tasksets/swe/swe_lego/taskset.py	args: filter_fn: optional python expression string forwarded to :class:`taskset` — see its docstring. applied to post-``	STRING
HIGH	…erimental/composable/tasksets/swe/swe_bench/taskset.py	args: filter_fn: optional python expression string forwarded to :class:`taskset` — see its docstring. applied to post-``	STRING
HIGH	…xperimental/composable/tasksets/swe/openswe/taskset.py	args: filter_fn: optional python expression string forwarded to :class:`taskset` — see its docstring. applied to post-``	STRING
HIGH	…erimental/composable/tasksets/swe/multi_swe/taskset.py	args: filter_fn: optional python expression string forwarded to :class:`taskset` — see its docstring. applied to post-``	STRING

Modern AI Meta-Vocabulary15 hits · 42 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/v1/conftest.py	49	# Fixture tasksets (echo-v1, echo-agentic-v1) live in tests/v1/fixtures, added to the	COMMENT
MEDIUM	tests/v1/test_e2e.py	459	harness=None, # a multi-agent env refuses the run-level harness	CODE
MEDIUM	tests/v1/test_e2e.py	566	harness=None, # multi-agent: each seat pins its own	CODE
MEDIUM	tests/v1/test_e2e.py	603	harness=None, # multi-agent: each seat pins its own	CODE
MEDIUM	verifiers/v1/env.py	147	# --- the multi-agent surface (override these) ------------------------------	COMMENT
MEDIUM	verifiers/v1/graph.py	559	# and its re-rendered input form place the turn-close scaffold in different nodes but at the	COMMENT
MEDIUM	verifiers/v1/graph.py	612	# Assistant node: trailing scaffold (the generation prompt) + the sampled completion.	COMMENT
MEDIUM	verifiers/v1/clients/base.py	10	# No read timeout: agentic completions are slow and the rollout timeout is the real	COMMENT
MEDIUM⚡	verifiers/v1/interception/server.py	71	# context window are the real limits, this is just a host-OOM backstop.	COMMENT
MEDIUM	verifiers/v1/harnesses/null/program.py	23	# OpenAI Responses/Completions: "Your input exceeds the context window of this model".	COMMENT
MEDIUM	verifiers/v1/judges/rubric.py	26	# criterion carries a one-sentence `reason` written before the verdict (chain-of-thought), so the	COMMENT
MEDIUM	verifiers/v1/cli/gepa.py	60	# Refuse multi-agent before the dry-run return, so --dry-run can't write a	COMMENT
MEDIUM	verifiers/v1/cli/replay.py	63	# Refuse multi-agent up front, from the SOURCE run's saved config — the replay	COMMENT
MEDIUM	verifiers/v1/cli/dashboard/eval.py	535	# trace (a multi-agent episode shows each role's trace), braced per task.	COMMENT
MEDIUM	docs/legacy/training.md	109	Our [`prime-rl`](https://github.com/PrimeIntellect-ai/prime-rl) trainer is a production-ready async RL training framewor	CODE

AI Structural Patterns37 hits · 36 pts

Severity	File	Line	Context
LOW	tests/conftest.py	491	CODE
LOW	tests/conftest.py	553	CODE
LOW	tests/v1/conftest.py	120	CODE
LOW	verifiers/legacy/clients/openai_completions_client.py	98	CODE
LOW	verifiers/legacy/gepa/display.py	73	CODE
LOW	verifiers/legacy/utils/eval_display.py	251	CODE
LOW	verifiers/legacy/utils/display_utils.py	557	CODE
LOW	…iers/legacy/rubrics/experimental/hybrid_math_rubric.py	104	CODE
LOW	verifiers/legacy/serve/server/env_server.py	28	CODE
LOW	verifiers/legacy/serve/server/env_router.py	96	CODE
LOW	verifiers/legacy/envs/sandbox_env.py	58	CODE
LOW	verifiers/legacy/envs/environment.py	99	CODE
LOW	verifiers/legacy/envs/environment.py	769	CODE
LOW	verifiers/legacy/envs/environment.py	823	CODE
LOW	verifiers/legacy/envs/environment.py	1220	CODE
LOW	verifiers/legacy/envs/environment.py	1278	CODE
LOW	verifiers/legacy/envs/environment.py	1365	CODE
LOW	verifiers/legacy/envs/experimental/cli_agent_env.py	94	CODE
LOW	verifiers/legacy/envs/experimental/opencode_rlm_env.py	183	CODE
LOW	verifiers/legacy/envs/experimental/opencode_env.py	173	CODE
LOW	verifiers/legacy/envs/experimental/sandbox_mixin.py	167	CODE
LOW	verifiers/legacy/envs/experimental/gym_env.py	58	CODE
LOW	…gacy/envs/experimental/composable/sandbox_debug_env.py	46	CODE
LOW	…s/legacy/envs/experimental/composable/harnesses/rlm.py	128	CODE
LOW	…vs/experimental/composable/harnesses/mini_swe_agent.py	84	CODE
LOW	…vs/experimental/composable/harnesses/mini_swe_agent.py	172	CODE
LOW	…acy/envs/experimental/composable/harnesses/opencode.py	90	CODE
LOW	…acy/envs/experimental/composable/harnesses/opencode.py	149	CODE
LOW	…acy/envs/experimental/composable/harnesses/opencode.py	230	CODE
LOW	…xperimental/composable/tasksets/swe/r2e_gym/taskset.py	177	CODE
LOW	…nvs/experimental/composable/tasksets/math/math_task.py	40	CODE
LOW	…cy/envs/experimental/composable/tasksets/cp/cp_task.py	143	CODE
LOW	verifiers/legacy/envs/integrations/textarena_env.py	44	CODE
LOW	verifiers/legacy/envs/integrations/openenv_env.py	94	CODE
LOW	verifiers/legacy/envs/integrations/openenv_env.py	169	CODE
LOW	…rs/legacy/envs/integrations/browser_env/browser_env.py	48	CODE
LOW	…legacy/envs/integrations/browser_env/modes/cua_mode.py	69	CODE

Over-Commented Block23 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_renderer_client.py	601	# When vLLM hits max_tokens mid-completion, the previous step carries	COMMENT
LOW	verifiers/v1/harnesses/null/program.py	21	# OpenAI error code "context_length_exceeded"; OpenRouter relays the raw body.	COMMENT
LOW	verifiers/v1/utils/git.py	41	# reports: a failure in add, diff, reset, or head fails the capture. A failed	COMMENT
LOW	verifiers/legacy/utils/save_utils.py	301	# flatten metrics to top-level keys (backwards compatibility)	COMMENT
LOW	…/composable/tasksets/swe/swe_rebench_v2/log_parsers.py	1	# ruff: noqa	COMMENT
LOW	configs/gepa/nemotron-3.toml	1	# Nemotron 3 models. Update both fields when switching sizes.	COMMENT
LOW	configs/gepa/qwen-3-5.toml	1	# Qwen3.5 dense models. Update both fields when switching sizes.	COMMENT
LOW	configs/gepa/gpt-oss.toml	1	# gpt-oss models. Update both fields when switching sizes.	COMMENT
LOW	configs/gepa/llama-3.toml	1	# Llama 3.2 models. Update both fields when switching sizes.	COMMENT
LOW	configs/gepa/qwen-3-5-moe.toml	1	# Qwen3.5 MoE models. Update both fields when switching sizes.	COMMENT
LOW	configs/eval/nemotron-3.toml	21	# [[eval]]	COMMENT
LOW	configs/eval/qwen-3-5.toml	21	# env_id = "primeintellect/dspy-flights"	COMMENT
LOW	configs/eval/gpt-oss.toml	21	# [[eval]]	COMMENT
LOW	configs/eval/llama-3.toml	21	# [[eval]]	COMMENT
LOW	configs/rl/qwen.toml	21		COMMENT
LOW	configs/rl/qwen-moe.toml	21		COMMENT
LOW	configs/rl/gpt-oss.toml	21	# id = "primeintellect/wiki-search"	COMMENT
LOW	configs/rl/llama.toml	21		COMMENT
LOW	configs/rl/nemotron.toml	21	# id = "primeintellect/wiki-search"	COMMENT
LOW	assets/templates/browserbase/cua/setup.sh	1	#!/bin/bash	COMMENT
LOW	assets/templates/browserbase/cua/setup-binary.sh	1	#!/bin/bash	COMMENT
LOW	assets/templates/browserbase/cua/build-and-push.sh	1	#!/bin/bash	COMMENT
LOW	…sets/templates/browserbase/cua/scripts/build-binary.sh	1	#!/bin/bash	COMMENT

Self-Referential Comments6 hits · 20 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_stateful_tool_env.py	166	# Create a tool call with invalid JSON arguments	COMMENT
MEDIUM	tests/test_tool_env.py	158	# Create a tool call with invalid JSON arguments	COMMENT
MEDIUM	tests/test_cli_agent_env.py	406	# Create a second task	COMMENT
MEDIUM	tests/test_environment.py	25	# Create a concrete implementation for testing the abstract base class	COMMENT
MEDIUM⚡	verifiers/v1/runtimes/modal.py	275	# Create the parent first (Modal's write does not mkdir).	COMMENT
MEDIUM	…/composable/tasksets/swe/swe_rebench_v2/log_parsers.py	2892	# Create a unique key for the test	COMMENT

Verbosity Indicators9 hits · 19 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_save_utils.py	1210	# Step 2: prior was ["A"], current is ["A", "A"]. Multiset budget	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	31	# Step 1: Login to Docker Hub	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	36	# Step 2: Build the binary	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	41	# Step 3: Extract binary from builder	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	55	# Step 4: Build runtime image	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	60	# Step 5: Push to Docker Hub	COMMENT
LOW	…sets/templates/browserbase/cua/scripts/build-binary.sh	27	# Step 1: Bundle with esbuild	COMMENT
LOW⚡	…sets/templates/browserbase/cua/scripts/build-binary.sh	40	# Step 2: Generate SEA blob	COMMENT
LOW⚡	…sets/templates/browserbase/cua/scripts/build-binary.sh	46	# Step 3: Create the binary	COMMENT

Structural Annotation Overuse9 hits · 19 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_save_utils.py	1210	# Step 2: prior was ["A"], current is ["A", "A"]. Multiset budget	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	31	# Step 1: Login to Docker Hub	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	36	# Step 2: Build the binary	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	41	# Step 3: Extract binary from builder	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	55	# Step 4: Build runtime image	COMMENT
LOW⚡	assets/templates/browserbase/cua/build-and-push.sh	60	# Step 5: Push to Docker Hub	COMMENT
LOW	…sets/templates/browserbase/cua/scripts/build-binary.sh	27	# Step 1: Bundle with esbuild	COMMENT
LOW⚡	…sets/templates/browserbase/cua/scripts/build-binary.sh	40	# Step 2: Generate SEA blob	COMMENT
LOW⚡	…sets/templates/browserbase/cua/scripts/build-binary.sh	46	# Step 3: Create the binary	COMMENT

Redundant / Tautological Comments12 hits · 18 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_imports.py	41	# Check if this is an expected optional dependency error	COMMENT
LOW	verifiers/legacy/parsers/xml_parser.py	157	# Check if the message has at least one valid field	COMMENT
LOW	verifiers/legacy/parsers/xml_parser.py	182	# Check if field exists in non-stripped version too (proper spacing)	COMMENT
LOW	verifiers/legacy/parsers/xml_parser.py	203	# Check if any field from the first field set starts the message	COMMENT
LOW	verifiers/legacy/parsers/xml_parser.py	213	# Check if any field from the last field set ends the message	COMMENT
LOW	verifiers/legacy/gepa/display.py	173	# Check if this is a valset eval by matching example_ids	COMMENT
LOW	verifiers/legacy/utils/display_utils.py	453	# Check if more chars follow (escape sequence vs standalone Esc)	COMMENT
LOW	verifiers/legacy/envs/environment.py	322	# Check if a system message already exists (first message)	COMMENT
LOW	…/composable/tasksets/swe/swe_rebench_v2/log_parsers.py	2497	# Check if Pass column has a value (look for leading spaces pattern)	COMMENT
LOW	…/composable/tasksets/swe/swe_rebench_v2/log_parsers.py	2907	# Check if counters are consecutive (indicating pass)	COMMENT
LOW	…/composable/tasksets/swe/swe_rebench_v2/log_parsers.py	3121	# Check if this is a test line (starts with "- ")	COMMENT
LOW	…s/legacy/envs/experimental/utils/git_checkout_cache.py	23	# Open file handles that hold a process-lifetime shared lock on each	COMMENT

Docstring Block Structure2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	verifiers/legacy/utils/save_utils.py	202	Convert a State to a serializable RolloutOutput. Args: state: The State object to convert. state_co	STRING
HIGH	verifiers/legacy/utils/install_utils.py	30	Parse environment ID into (owner, name, version). Args: env_id: Environment ID like 'owner/name' or 'owner/	STRING

Magic Placeholder Names1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	…rifiers/legacy/envs/integrations/browser_env/README.md	46	export BROWSERBASE_API_KEY="your-api-key"	CODE

Slop Phrases1 hit · 2 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/v1/test_judges.py	442	response = JudgeResponse(text="as an AI language model I cannot grade this")	CODE

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	assets/templates/browserbase/cua/build-and-push.sh	9	# Usage:	COMMENT

Overly Generic Function Names1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	verifiers/v1/interception/server.py	474	async def handle_request(	CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings