NousResearch/hermes-agent

Pattern Findings

41759 matches across 21 categories. Click a row to expand file-level details.

Decorative Section Separators8826 hits · 30987 pts

Severity	File	Line	Snippet
MEDIUM	hermes_constants.py	386	# ─── Well-Known Paths ─────────────────────────────────────────────────────────
MEDIUM	hermes_constants.py	409	# ─── Network Preferences ─────────────────────────────────────────────────────
MEDIUM	hermes_constants.py	454	# ─── Streaming Response Constants ────────────────────────────────────────────
MEDIUM	setup-hermes.sh	2	# ============================================================================
MEDIUM	setup-hermes.sh	4	# ============================================================================
MEDIUM	setup-hermes.sh	18	# ============================================================================
MEDIUM	setup-hermes.sh	269	# ============================================================================
MEDIUM	setup-hermes.sh	270	# ============================================================================
MEDIUM	setup-hermes.sh	272	# ============================================================================
MEDIUM	setup-hermes.sh	62	# ============================================================================
MEDIUM	setup-hermes.sh	64	# ============================================================================
MEDIUM	setup-hermes.sh	129	# ============================================================================
MEDIUM	setup-hermes.sh	131	# ============================================================================
MEDIUM	setup-hermes.sh	165	# ============================================================================
MEDIUM	setup-hermes.sh	167	# ============================================================================
MEDIUM	setup-hermes.sh	187	# ============================================================================
MEDIUM	setup-hermes.sh	189	# ============================================================================
MEDIUM	setup-hermes.sh	325	# ============================================================================
MEDIUM	setup-hermes.sh	327	# ============================================================================
MEDIUM	setup-hermes.sh	344	# ============================================================================
MEDIUM	setup-hermes.sh	346	# ============================================================================
MEDIUM	setup-hermes.sh	398	# ============================================================================
MEDIUM	setup-hermes.sh	400	# ============================================================================
MEDIUM	setup-hermes.sh	417	# ============================================================================
MEDIUM	setup-hermes.sh	419	# ============================================================================
MEDIUM	run_agent.py	185	# =========================================================================
MEDIUM	run_agent.py	187	# =========================================================================
MEDIUM	run_agent.py	190	# =========================================================================
MEDIUM	run_agent.py	194	# =========================================================================
MEDIUM	run_agent.py	771	# ── Buffered retry/fallback status ────────────────────────────────────
MEDIUM	run_agent.py	1318	# ------------------------------------------------------------------
MEDIUM	run_agent.py	1320	# ------------------------------------------------------------------
MEDIUM	run_agent.py	3375	# ── Unified streaming API call ─────────────────────────────────────────
MEDIUM	run_agent.py	3553	# ── Per-turn primary restoration ─────────────────────────────────────
MEDIUM	toolsets.py	340	# ==========================================================================
MEDIUM	toolsets.py	345	# ==========================================================================
MEDIUM	hermes_logging.py	68	# ---------------------------------------------------------------------------
MEDIUM	hermes_logging.py	70	# ---------------------------------------------------------------------------
MEDIUM	hermes_logging.py	86	# ---------------------------------------------------------------------------
MEDIUM	hermes_logging.py	88	# ---------------------------------------------------------------------------
MEDIUM	hermes_logging.py	122	# ---------------------------------------------------------------------------
MEDIUM	hermes_logging.py	124	# ---------------------------------------------------------------------------
MEDIUM	hermes_logging.py	152	# ---------------------------------------------------------------------------
MEDIUM	hermes_logging.py	154	# ---------------------------------------------------------------------------
MEDIUM	hermes_logging.py	294	# ---------------------------------------------------------------------------
MEDIUM	hermes_logging.py	296	# ---------------------------------------------------------------------------
MEDIUM	mini_swe_runner.py	64	# ============================================================================
MEDIUM	mini_swe_runner.py	66	# ============================================================================
MEDIUM	mini_swe_runner.py	113	# ============================================================================
MEDIUM	mini_swe_runner.py	115	# ============================================================================
MEDIUM	mini_swe_runner.py	153	# ============================================================================
MEDIUM	mini_swe_runner.py	155	# ============================================================================
MEDIUM	mini_swe_runner.py	632	# ============================================================================
MEDIUM	mini_swe_runner.py	634	# ============================================================================
MEDIUM	cli.py	970	# =============================================================================
MEDIUM	cli.py	972	# =============================================================================
MEDIUM	cli.py	1461	# ============================================================================
MEDIUM	cli.py	1463	# ============================================================================
MEDIUM	cli.py	2103	# ---------------------------------------------------------------------------
MEDIUM	cli.py	2105	# ---------------------------------------------------------------------------
8766 more matches not shown…

Hyper-Verbose Identifiers24037 hits · 20835 pts

Severity	File	Line	Snippet
LOW	batch_runner.py	101	def _normalize_tool_error_counts(tool_error_counts: Dict[str, int]) -> Dict[str, int]:
LOW	batch_runner.py	732	def _scan_completed_prompts_by_content(self) -> set:
LOW	batch_runner.py	776	def _filter_dataset_by_completed(self, completed_prompts: set) -> Tuple[List[Dict], List[int]]:
LOW	hermes_constants.py	30	def reset_hermes_home_override(token: Token) -> None:
LOW	toolset_distributions.py	247	def sample_toolsets_from_distribution(distribution_name: str) -> List[str]:
LOW	run_agent.py	848	def _disable_codex_reasoning_replay(
LOW	run_agent.py	1328	def _summarize_background_review_actions(
LOW	run_agent.py	2110	def _format_file_mutation_failure_footer(failed: Dict[str, Dict[str, Any]]) -> str:
LOW	run_agent.py	2169	def _format_turn_completion_explanation(turn_exit_reason: str) -> str:
LOW	run_agent.py	2902	def _replace_primary_openai_client(self, *, reason: str) -> bool:
LOW	run_agent.py	3418	def _record_streamed_assistant_text(self, text: str) -> None:
LOW	run_agent.py	3426	def _normalize_interim_visible_text(text: str) -> str:
LOW	run_agent.py	3431	def _interim_content_was_streamed(self, content: str) -> bool:
LOW	run_agent.py	4249	def _copy_reasoning_content_for_api(self, source_msg: dict, api_msg: dict) -> None:
LOW	run_agent.py	4254	def _reapply_reasoning_echo_for_provider(self, api_messages: list) -> int:
LOW	run_agent.py	4260	def _sanitize_tool_calls_for_strict_api(api_msg: dict) -> dict:
LOW	run_agent.py	207	def _pool_may_recover_from_rate_limit(
LOW	run_agent.py	456	def _get_session_db_for_recall(self):
LOW	run_agent.py	497	def _transition_context_engine_session(
LOW	run_agent.py	618	def _ensure_lmstudio_runtime_loaded(self, config_context_length: Optional[int] = None) -> None:
LOW	run_agent.py	701	def _should_start_quiet_spinner(self) -> bool:
LOW	run_agent.py	720	def _should_emit_quiet_tool_messages(self) -> bool:
LOW	run_agent.py	891	def _stream_diag_capture_response(
LOW	run_agent.py	904	def _is_provider_stream_parse_error(self, error: BaseException) -> bool:
LOW	run_agent.py	976	def _check_compression_model_feasibility(self) -> None:
LOW	run_agent.py	981	def _replay_compression_warning(self) -> None:
LOW	run_agent.py	1022	def _resolved_api_call_timeout(self) -> float:
LOW	run_agent.py	1042	def _resolved_api_call_stale_timeout_base(self) -> tuple[float, bool]:
LOW	run_agent.py	1070	def _compute_non_stream_stale_timeout(self, api_payload: Any) -> float:
LOW	run_agent.py	1147	def _anthropic_prompt_cache_policy(
LOW	run_agent.py	1160	def _model_requires_responses_api(model: str) -> bool:
LOW	run_agent.py	1175	def _provider_model_requires_responses_api(
LOW	run_agent.py	1209	def _has_content_after_think_block(self, content: str) -> bool:
LOW	run_agent.py	1238	def _has_natural_response_ending(content: str) -> bool:
LOW	run_agent.py	1267	def _should_treat_stop_as_truncated(
LOW	run_agent.py	1298	def _looks_like_codex_intermediate_ack(
LOW	run_agent.py	1360	def _build_memory_write_metadata(
LOW	run_agent.py	1378	def _apply_persist_user_message_override(self, messages: List[Dict]) -> None:
LOW	run_agent.py	1407	def _drop_trailing_empty_response_scaffolding(self, messages: List[Dict]) -> None:
LOW	run_agent.py	1465	def _flush_messages_to_session_db(self, messages: List[Dict], conversation_history: List[Dict] = None):
LOW	run_agent.py	1524	def _get_messages_up_to_last_assistant(self, messages: List[Dict]) -> List[Dict]:
LOW	run_agent.py	1555	def _format_tools_for_system_message(self) -> str:
LOW	run_agent.py	1560	def _convert_to_trajectory_format(self, messages: List[Dict[str, Any]], user_query: str, completed: bool) -> List[Di
LOW	run_agent.py	1732	def _extract_api_error_context(error: Exception) -> Dict[str, Any]:
LOW	run_agent.py	1737	def _usage_summary_for_api_request_hook(self, response: Any) -> Optional[Dict[str, Any]]:
LOW	run_agent.py	2043	def _record_file_mutation_result(
LOW	run_agent.py	2082	def _file_mutation_verifier_enabled(self) -> bool:
LOW	run_agent.py	2141	def _turn_completion_explainer_enabled(self) -> bool:
LOW	run_agent.py	2261	def _apply_pending_steer_to_tool_results(self, messages: list, num_tool_msgs: int) -> None:
LOW	run_agent.py	2311	def _check_openrouter_cache_status(self, http_response: Any) -> None:
LOW	run_agent.py	2403	def _sync_external_memory_for_turn(
LOW	run_agent.py	2606	def _build_system_prompt_parts(self, system_message: str = None) -> Dict[str, str]:
LOW	run_agent.py	2624	def _get_tool_call_name_static(tc) -> str:
LOW	run_agent.py	2649	def _is_thinking_only_assistant(msg: Dict[str, Any]) -> bool:
LOW	run_agent.py	2703	def _drop_thinking_only_and_merge_users(
LOW	run_agent.py	2764	def _invalidate_system_prompt(self):
LOW	run_agent.py	2784	def _derive_responses_function_call_id(
LOW	run_agent.py	2843	def _build_keepalive_http_client(base_url: str = "") -> Any:
LOW	run_agent.py	2919	def _ensure_primary_openai_client(self, *, reason: str) -> Any:
LOW	run_agent.py	2935	def _cleanup_dead_connections(self) -> bool:
23977 more matches not shown…

Excessive Try-Catch Wrapping5016 hits · 3800 pts

Severity	File	Line	Snippet
LOW	batch_runner.py	299	except Exception as img_err:
LOW	batch_runner.py	381	except Exception as e:
LOW	batch_runner.py	706	except Exception as e:
LOW	batch_runner.py	771	except Exception as e:
LOW	batch_runner.py	978	except Exception as ckpt_err:
LOW	batch_runner.py	981	except Exception as e:
LOW	batch_runner.py	1012	except Exception as ckpt_err:
LOW	batch_runner.py	1281	except Exception as e:
LOW	batch_runner.py	1312	except Exception as e:
LOW	hermes_constants.py	98	except Exception:
LOW	hermes_constants.py	350	except Exception:
LOW	run_agent.py	763	except Exception:
LOW	run_agent.py	768	except Exception:
LOW	run_agent.py	843	except Exception:
LOW	run_agent.py	845	except Exception:
LOW	run_agent.py	2100	except Exception:
LOW	run_agent.py	2105	except Exception:
LOW	run_agent.py	2159	except Exception:
LOW	run_agent.py	2164	except Exception:
LOW	run_agent.py	2362	except Exception:
LOW	run_agent.py	2366	except Exception:
LOW	run_agent.py	2375	except Exception:
LOW	run_agent.py	2486	except Exception:
LOW	run_agent.py	2490	except Exception:
LOW	run_agent.py	2492	except Exception:
LOW	run_agent.py	2501	except Exception:
LOW	run_agent.py	2523	except Exception:
LOW	run_agent.py	2529	except Exception:
LOW	run_agent.py	2535	except Exception:
LOW	run_agent.py	2546	except Exception:
LOW	run_agent.py	2548	except Exception:
LOW	run_agent.py	2557	except Exception:
LOW	run_agent.py	2893	except Exception as exc:
LOW	run_agent.py	2907	except Exception as exc:
LOW	run_agent.py	3413	except Exception:
LOW	run_agent.py	471	except Exception as exc:
LOW	run_agent.py	490	except Exception as e:
LOW	run_agent.py	523	except Exception as exc:
LOW	run_agent.py	529	except Exception as exc:
LOW	run_agent.py	552	except Exception as exc:
LOW	run_agent.py	563	except Exception as exc:
LOW	run_agent.py	648	except Exception as err:
LOW	run_agent.py	746	except Exception:
LOW	run_agent.py	751	except Exception:
LOW	run_agent.py	798	except Exception:
LOW	run_agent.py	810	except Exception:
LOW	run_agent.py	819	except Exception:
LOW	run_agent.py	959	except Exception:
LOW	run_agent.py	1190	except Exception:
LOW	run_agent.py	1521	except Exception as e:
LOW	run_agent.py	1830	except Exception:
LOW	run_agent.py	1862	except Exception:
LOW	run_agent.py	1885	except Exception as e:
LOW	run_agent.py	1945	except Exception:
LOW	run_agent.py	1953	except Exception as e:
LOW	run_agent.py	1980	except Exception:
LOW	run_agent.py	2281	except Exception:
LOW	run_agent.py	2304	except Exception:
LOW	run_agent.py	2330	except Exception:
LOW	run_agent.py	2386	except Exception:
4956 more matches not shown…

Cross-Language Confusion174 hits · 992 pts

Severity	File	Line	Snippet
HIGH	cli.py	10869	"Fallback: pkg install python-numpy portaudio && python -m pip install sounddevice"
HIGH	cli.py	10874	"Option 2: pkg install python-numpy portaudio && python -m pip install sounddevice"
HIGH	cli.py	11202	_cprint(f" {_BOLD}Option 2: pkg install python-numpy portaudio && python -m pip install sounddevice
HIGH	tools/schema_sanitizer.py	140	{"anyOf": [{"type": "string"}, {"type": "null"}], "default": null}
HIGH	tools/voice_mode.py	57	return "pkg install python-numpy portaudio && python -m pip install sounddevice"
HIGH	tools/voice_mode.py	138	" 3. Verify with: arecord -d 3 /tmp/test.wav && aplay /tmp/test.wav"
HIGH	tools/process_registry.py	788	f"kill -0 \"$(cat {quoted_pid_path} 2>/dev/null)\" 2>/dev/null; echo $?",
HIGH	tools/browser_tool.py	597	return "npm install -g agent-browser && agent-browser install"
HIGH	tools/browser_tool.py	598	return "npm install -g agent-browser && agent-browser install --with-deps"
HIGH	tools/terminal_tool.py	589	"""Wrap `A && B &` (or `A \|\| B &`) to `A && { B & }` at depth 0.
HIGH	tools/terminal_tool.py	589	"""Wrap `A && B &` (or `A \|\| B &`) to `A && { B & }` at depth 0.
HIGH	tools/terminal_tool.py	591	Bash parses ``A && B &`` with `&&` tighter than `&`, so it forks a
HIGH	tools/terminal_tool.py	592	subshell for the whole `A && B` compound and backgrounds it. Inside
HIGH	tools/browser_supervisor.py	88	xhr.open("GET", ENDPOINT + "?" + params.toString(), false); // sync
HIGH	tools/browser_supervisor.py	89	xhr.send(null);
HIGH	tools/browser_supervisor.py	90	if (xhr.status !== 200) return null;
HIGH	tools/browser_supervisor.py	93	try { parsed = JSON.parse(body); } catch (e) { return null; }
HIGH	tools/browser_supervisor.py	94	if (kind === "alert") return undefined;
HIGH	tools/browser_supervisor.py	95	if (kind === "confirm") return Boolean(parsed && parsed.accept);
HIGH	tools/browser_supervisor.py	97	if (!parsed \|\| !parsed.accept) return null;
HIGH	tools/browser_supervisor.py	100	return null;
HIGH	tools/browser_supervisor.py	104	return null;
HIGH	tools/browser_camofox.py	14	git clone https://github.com/jo-inc/camofox-browser && cd camofox-browser
HIGH	tools/browser_camofox.py	15	npm install && npm start # downloads Camoufox (~300MB) on first run
HIGH	tools/file_operations.py	1612	check = self._exec(f"test -e {self._escape_shell_arg(path)} && echo exists \|\| echo not_found")
HIGH	tools/file_operations.py	1620	f"test -d {self._escape_shell_arg(parent)} && echo yes \|\| echo no"
HIGH	tools/file_operations.py	647	result = self._exec(f"command -v {cmd} >/dev/null 2>&1 && echo 'yes'")
HIGH	tools/code_execution_tool.py	752	f"ls -1 {quoted_rpc_dir}/req_* 2>/dev/null \|\| true",
HIGH	tools/code_execution_tool.py	908	"command -v python3 >/dev/null 2>&1 && echo OK",
HIGH	tools/environments/local.py	431	prelude_parts.append(f"[ -r '{safe}' ] && . '{safe}' 2>/dev/null \|\| true")
HIGH	tools/environments/modal.py	113	"RUN rm -rf /usr/local/lib/python/site-packages/pip 2>/dev/null; "
HIGH	tools/environments/modal.py	114	"python -m ensurepip --upgrade --default-pip 2>/dev/null \|\| true",
HIGH	tools/environments/modal.py	118	"RUN apt-get update -qq && apt-get install -y -qq python3 python3-venv > /dev/null 2>&1 \|\| true"
HIGH	tools/environments/modal.py	118	"RUN apt-get update -qq && apt-get install -y -qq python3 python3-venv > /dev/null 2>&1 \|\| true"
HIGH	tools/environments/base.py	379	f"builtin cd {_quoted_cwd} 2>/dev/null \|\| true\n"
HIGH	tools/environments/base.py	380	f"pwd -P > {_quoted_cwd_file} 2>/dev/null \|\| true\n"
HIGH	tools/environments/base.py	439	f"source {_quoted_snap} >/dev/null 2>&1 \|\| true"
HIGH	tools/environments/base.py	454	parts.append(f"export -p > {_quoted_snap} 2>/dev/null \|\| true")
HIGH	tools/environments/base.py	457	parts.append(f"pwd -P > {_quoted_cwd_file} 2>/dev/null \|\| true")
HIGH	hermes_cli/models.py	723	# "paidRecommendedCompactionModel": {modelName, ...} \| null,
HIGH	hermes_cli/models.py	724	# "paidRecommendedVisionModel": {modelName, ...} \| null,
HIGH	hermes_cli/models.py	725	# "freeRecommendedCompactionModel": {modelName, ...} \| null,
HIGH	hermes_cli/models.py	726	# "freeRecommendedVisionModel": {modelName, ...} \| null,
HIGH	hermes_cli/models.py	852	# paid tier → paid, then free (if paid field is null)
HIGH	hermes_cli/models.py	828	Returns ``None`` when every candidate is missing, null, or the fetch
HIGH	hermes_cli/completion.py	108	profiles="$profiles $(ls "$profiles_dir" 2>/dev/null)"
HIGH	hermes_cli/completion.py	209	profiles+=("${{(@f)$(ls $HOME/.hermes/profiles 2>/dev/null)}}")
HIGH	hermes_cli/service_manager.py	676	f'chown -R hermes:hermes "$log_dir" 2>/dev/null \|\| true\n'
HIGH	hermes_cli/web_server.py	3831	{"error": "Frontend not built. Run: cd web && npm run build"},
HIGH	hermes_cli/tools_config.py	788	_print_warning(f" npm install failed - run manually: cd {display_hermes_home()}/hermes-agent && npm i
HIGH	hermes_cli/main.py	1307	f'source "{helper}" >&2 && ensure_node >&2 && command -v node',
HIGH	hermes_cli/main.py	6683	_say("Install Node.js, then run: cd web && npm install && npm run build")
HIGH	hermes_cli/main.py	6710	_say(" Run manually: cd web && npm install && npm run build")
HIGH	hermes_cli/main.py	6751	_say(" Run manually: cd web && npm install && npm run build")
HIGH	hermes_cli/main.py	9172	f" Try manually: git fetch origin && git reset --hard origin/{branch}"
HIGH	hermes_cli/main.py	9214	print(f" cd {PROJECT_ROOT} && git reflog && git reset --hard <prev-sha>")
HIGH	hermes_cli/main.py	10925	print(" Pre-build first: cd web && npm install && npm run build")
HIGH	hermes_cli/main.py	14152	"where npm may not be available. Pre-build with: cd web && npm run build"
HIGH	hermes_cli/doctor.py	1090	f"Reinstall entry point: cd {PROJECT_ROOT} && source venv/bin/activate && pip install -e '.[all]'"
HIGH	hermes_cli/doctor.py	1274	check_info("Install it manually later with: npm install -g agent-browser && agent-browser install")
114 more matches not shown…

Unused Imports1068 hits · 909 pts

Severity	File	Line
LOW	batch_runner.py	26
LOW	hermes_bootstrap.py	50
LOW	run_agent.py	72
LOW	run_agent.py	72
LOW	run_agent.py	77
LOW	run_agent.py	97
LOW	run_agent.py	97
LOW	run_agent.py	97
LOW	run_agent.py	112
LOW	run_agent.py	118
LOW	run_agent.py	119
LOW	run_agent.py	120
LOW	run_agent.py	120
LOW	run_agent.py	120
LOW	run_agent.py	120
LOW	run_agent.py	120
LOW	run_agent.py	120
LOW	run_agent.py	128
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	129
LOW	run_agent.py	142
LOW	run_agent.py	161
LOW	run_agent.py	161
LOW	run_agent.py	161
LOW	run_agent.py	161
LOW	run_agent.py	161
LOW	run_agent.py	26
LOW	run_agent.py	883
LOW	run_agent.py	1321
LOW	run_agent.py	1321
LOW	run_agent.py	1321
LOW	setup.py	1
LOW	cli.py	18
LOW	mcp_serve.py	30
LOW	tools/schema_sanitizer.py	31
LOW	tools/tool_search.py	28
LOW	tools/web_tools.py	45
LOW	tools/web_tools.py	53
LOW	tools/web_tools.py	53
LOW	tools/web_tools.py	63
LOW	tools/web_tools.py	63
LOW	tools/web_tools.py	63
LOW	tools/web_tools.py	71
LOW	tools/web_tools.py	71
LOW	tools/web_tools.py	75
LOW	tools/web_tools.py	94
LOW	tools/web_tools.py	94
LOW	tools/web_tools.py	94
LOW	tools/web_tools.py	99
LOW	tools/web_tools.py	99
LOW	tools/web_tools.py	99
1008 more matches not shown…

Deep Nesting1274 hits · 812 pts

Severity	File	Line
LOW	batch_runner.py	125
LOW	batch_runner.py	244
LOW	batch_runner.py	642
LOW	batch_runner.py	732
LOW	batch_runner.py	776
LOW	batch_runner.py	810
LOW	run_agent.py	4493
LOW	run_agent.py	822
LOW	run_agent.py	1465
LOW	run_agent.py	1775
LOW	run_agent.py	1804
LOW	run_agent.py	2457
LOW	run_agent.py	2649
LOW	run_agent.py	3242
LOW	run_agent.py	3377
LOW	run_agent.py	3867
LOW	run_agent.py	3979
LOW	run_agent.py	4012
LOW	run_agent.py	4134
LOW	toolsets.py	606
LOW	mini_swe_runner.py	636
LOW	mini_swe_runner.py	304
LOW	mini_swe_runner.py	414
LOW	cli.py	118
LOW	cli.py	335
LOW	cli.py	1037
LOW	cli.py	1249
LOW	cli.py	1596
LOW	cli.py	1965
LOW	cli.py	2173
LOW	cli.py	2373
LOW	cli.py	2486
LOW	cli.py	15057
LOW	cli.py	2907
LOW	cli.py	3385
LOW	cli.py	3823
LOW	cli.py	3932
LOW	cli.py	4088
LOW	cli.py	4255
LOW	cli.py	4629
LOW	cli.py	4856
LOW	cli.py	5240
LOW	cli.py	5443
LOW	cli.py	5550
LOW	cli.py	5811
LOW	cli.py	5877
LOW	cli.py	6429
LOW	cli.py	7200
LOW	cli.py	7583
LOW	cli.py	7976
LOW	cli.py	8021
LOW	cli.py	8371
LOW	cli.py	9079
LOW	cli.py	9460
LOW	cli.py	9947
LOW	cli.py	10273
LOW	cli.py	10742
LOW	cli.py	10973
LOW	cli.py	11091
LOW	cli.py	11143
1214 more matches not shown…

Cross-File Repetition148 hits · 740 pts

Severity	File	Line	Snippet
HIGH	plugins/platforms/discord/adapter.py	0	check if message reactions are enabled via config/env.
HIGH	gateway/platforms/telegram.py	0	check if message reactions are enabled via config/env.
HIGH	gateway/platforms/slack.py	0	check if message reactions are enabled via config/env.
HIGH	plugins/platforms/discord/adapter.py	0	plugin entry point — called by the hermes plugin system.
HIGH	plugins/platforms/teams/adapter.py	0	plugin entry point — called by the hermes plugin system.
HIGH	plugins/platforms/mattermost/adapter.py	0	plugin entry point — called by the hermes plugin system.
HIGH	…bsite/docs/developer-guide/adding-platform-adapters.md	0	plugin entry point — called by the hermes plugin system.
HIGH	plugins/platforms/ntfy/adapter.py	0	plugin entry point — called by the hermes plugin system at startup.
HIGH	plugins/platforms/simplex/adapter.py	0	plugin entry point — called by the hermes plugin system at startup.
HIGH	plugins/platforms/line/adapter.py	0	plugin entry point — called by the hermes plugin system at startup.
HIGH	plugins/memory/holographic/retrieval.py	0	select fact_id, content, category, tags, trust_score, retrieval_count, helpful_count, created_at, updated_at, hrr_vector
HIGH	plugins/memory/holographic/retrieval.py	0	select fact_id, content, category, tags, trust_score, retrieval_count, helpful_count, created_at, updated_at, hrr_vector
HIGH	plugins/memory/holographic/retrieval.py	0	select fact_id, content, category, tags, trust_score, retrieval_count, helpful_count, created_at, updated_at, hrr_vector
HIGH	plugins/memory/holographic/retrieval.py	0	select fact_id, content, category, tags, trust_score, retrieval_count, helpful_count, created_at, updated_at, hrr_vector
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	curl -x post https://api.example.com/users \\ -h 'content-type: application/json' \\ -h "authorization: bearer $token" \
HIGH	…development/software-development-rest-graphql-debug.md	0	curl -x post https://api.example.com/users \\ -h 'content-type: application/json' \\ -h "authorization: bearer $token" \
HIGH	…development/software-development-rest-graphql-debug.md	0	curl -x post https://api.example.com/users \\ -h 'content-type: application/json' \\ -h "authorization: bearer $token" \
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	curl -x post https://api.example.com/graphql \\ -h 'content-type: application/json' \\ -h "authorization: bearer $token"
HIGH	…development/software-development-rest-graphql-debug.md	0	curl -x post https://api.example.com/graphql \\ -h 'content-type: application/json' \\ -h "authorization: bearer $token"
HIGH	…development/software-development-rest-graphql-debug.md	0	curl -x post https://api.example.com/graphql \\ -h 'content-type: application/json' \\ -h "authorization: bearer $token"
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	import os, requests resp = requests.post( "https://api.example.com/graphql", json={"query": "{ user(id: 1) { name email
HIGH	…development/software-development-rest-graphql-debug.md	0	import os, requests resp = requests.post( "https://api.example.com/graphql", json={"query": "{ user(id: 1) { name email
HIGH	…development/software-development-rest-graphql-debug.md	0	import os, requests resp = requests.post( "https://api.example.com/graphql", json={"query": "{ user(id: 1) { name email
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	import requests resp = requests.get( "https://api.example.com/users/1", headers={"authorization": "bearer <token>"}, tim
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests resp = requests.get( "https://api.example.com/users/1", headers={"authorization": "bearer <token>"}, tim
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests resp = requests.get( "https://api.example.com/users/1", headers={"authorization": "bearer <token>"}, tim
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	curl -w "dns:%{time_namelookup}s connect:%{time_connect}s tls:%{time_appconnect}s ttfb:%{time_starttransfer}s total:%{ti
HIGH	…development/software-development-rest-graphql-debug.md	0	curl -w "dns:%{time_namelookup}s connect:%{time_connect}s tls:%{time_appconnect}s ttfb:%{time_starttransfer}s total:%{ti
HIGH	…development/software-development-rest-graphql-debug.md	0	curl -w "dns:%{time_namelookup}s connect:%{time_connect}s tls:%{time_appconnect}s ttfb:%{time_starttransfer}s total:%{ti
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	import requests from requests.exceptions import connecttimeout, readtimeout try: requests.get(url, timeout=(3.05, 30)) e
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests from requests.exceptions import connecttimeout, readtimeout try: requests.get(url, timeout=(3.05, 30)) e
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests from requests.exceptions import connecttimeout, readtimeout try: requests.get(url, timeout=(3.05, 30)) e
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	import json, base64, os tok = os.environ["token"] payload = tok.split(".")[1] payload += "=" * (-len(payload) % 4) print
HIGH	…development/software-development-rest-graphql-debug.md	0	import json, base64, os tok = os.environ["token"] payload = tok.split(".")[1] payload += "=" * (-len(payload) % 4) print
HIGH	…development/software-development-rest-graphql-debug.md	0	import json, base64, os tok = os.environ["token"] payload = tok.split(".")[1] payload += "=" * (-len(payload) % 4) print
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	curl -v -x post https://api.example.com/endpoint \\ -h 'content-type: application/json' \\ -d '{"key":"value"}' 2>&1
HIGH	…development/software-development-rest-graphql-debug.md	0	curl -v -x post https://api.example.com/endpoint \\ -h 'content-type: application/json' \\ -d '{"key":"value"}' 2>&1
HIGH	…development/software-development-rest-graphql-debug.md	0	curl -v -x post https://api.example.com/endpoint \\ -h 'content-type: application/json' \\ -d '{"key":"value"}' 2>&1
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	import requests resp = requests.post(url, json=payload, timeout=10) print(f"status={resp.status_code}") print(f"headers=
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests resp = requests.post(url, json=payload, timeout=10) print(f"status={resp.status_code}") print(f"headers=
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests resp = requests.post(url, json=payload, timeout=10) print(f"status={resp.status_code}") print(f"headers=
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	import time, requests def with_backoff(method, url, **kwargs): for attempt in range(5): resp = requests.request(method,
HIGH	…development/software-development-rest-graphql-debug.md	0	import time, requests def with_backoff(method, url, **kwargs): for attempt in range(5): resp = requests.request(method,
HIGH	…development/software-development-rest-graphql-debug.md	0	import time, requests def with_backoff(method, url, **kwargs): for attempt in range(5): resp = requests.request(method,
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	import requests def validate_user(data: dict) -> list[str]: errors = [] required = {"id": int, "email": str, "created_at
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests def validate_user(data: dict) -> list[str]: errors = [] required = {"id": int, "email": str, "created_at
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests def validate_user(data: dict) -> list[str]: errors = [] required = {"id": int, "email": str, "created_at
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	import requests resp = requests.post(url, json=payload, headers=headers, timeout=10) request_id = ( resp.headers.get("x-
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests resp = requests.post(url, json=payload, headers=headers, timeout=10) request_id = ( resp.headers.get("x-
HIGH	…development/software-development-rest-graphql-debug.md	0	import requests resp = requests.post(url, json=payload, headers=headers, timeout=10) request_id = ( resp.headers.get("x-
HIGH	…kills/software-development/rest-graphql-debug/SKILL.md	0	follow the rest-graphql-debug skill (optional-skills/software-development/rest-graphql-debug). base url: https://api.exa
HIGH	…development/software-development-rest-graphql-debug.md	0	follow the rest-graphql-debug skill (optional-skills/software-development/rest-graphql-debug). base url: https://api.exa
HIGH	…development/software-development-rest-graphql-debug.md	0	follow the rest-graphql-debug skill (optional-skills/software-development/rest-graphql-debug). base url: https://api.exa
HIGH	optional-skills/mlops/guidance/SKILL.md	0	{ "name": <gen name regex="[a-za-z ]+" max_tokens=20>, "age": <gen age regex="[0-9]+" max_tokens=3>, "email": <gen email
HIGH	…ocs/user-guide/skills/optional/mlops/mlops-guidance.md	0	{ "name": <gen name regex="[a-za-z ]+" max_tokens=20>, "age": <gen age regex="[0-9]+" max_tokens=3>, "email": <gen email
HIGH	…ent/user-guide/skills/optional/mlops/mlops-guidance.md	0	{ "name": <gen name regex="[a-za-z ]+" max_tokens=20>, "age": <gen age regex="[0-9]+" max_tokens=3>, "email": <gen email
HIGH	optional-skills/mlops/training/trl-fine-tuning/SKILL.md	0	compute rewards for completions. args: completions: list of generated texts returns: list of reward scores (floats)
HIGH	…kills/optional/mlops/mlops-training-trl-fine-tuning.md	0	compute rewards for completions. args: completions: list of generated texts returns: list of reward scores (floats)
HIGH	…kills/optional/mlops/mlops-training-trl-fine-tuning.md	0	compute rewards for completions. args: completions: list of generated texts returns: list of reward scores (floats)
HIGH	optional-skills/mlops/inference/outlines/SKILL.md	0	apple inc. was founded in 1976 in the technology industry. the company employs approximately 164,000 people worldwide.
88 more matches not shown…

Over-Commented Block638 hits · 434 pts

Severity	File	Line	Snippet
LOW	docker-compose.windows.yml	1	#
LOW	setup-hermes.sh	1	#!/bin/bash
LOW	setup-hermes.sh	241	# (the direct deps in pyproject.toml are exact-pinned, but
LOW	.hadolint.yaml	1	# hadolint configuration for the Hermes Agent Dockerfile.
LOW	.hadolint.yaml	21	- DL3003
LOW	hermes_bootstrap.py	81	os.environ.setdefault("PYTHONIOENCODING", "utf-8")
LOW	run_agent.py	41	import os
LOW	run_agent.py	1921	self._interrupt_thread_signal_pending = False
LOW	run_agent.py	3041	from agent.codex_runtime import run_codex_create_stream_fallback
LOW	pyproject.toml	21	# captured by `mistralai>=2.3.0,<3` rather than an exact pin, every
LOW	pyproject.toml	41	"ruamel.yaml==0.18.17",
LOW	pyproject.toml	61	# Cross-platform process / PID management. `psutil` is the canonical
LOW	pyproject.toml	121	# Computer use — macOS background desktop control via cua-driver (MCP stdio).
LOW	pyproject.toml	161	google = [
LOW	pyproject.toml	181	all = [
LOW	cli.py	1501	# to remap "near-white" skin colors (e.g. #FFF8DC banner_text, #B8860B
LOW	cli.py	2061	except Exception:
LOW	cli.py	3221	self._interrupt_queue = queue.Queue()
LOW	cli.py	4281	# These tags are model-generated (system prompt tells the model
LOW	cli.py	9481	if mgr is None or not mgr.is_active():
LOW	cli.py	11961	nonlocal result
LOW	cli.py	12041	# Start agent in background thread (daemon so it cannot keep the
LOW	cli.py	12081	_f.write(f" child[{_ci}]._interrupt={_ch._interrupt_requested}\n")
LOW	cli.py	12941	# can safely use prompt_toolkit terminal handoff helpers.
LOW	cli.py	14521	# to suppress the deliberate "reserve vertical space" scroll-up.
LOW	cli.py	14841	raise KeyboardInterrupt() # fallback for non-prompt_toolkit contexts
LOW	cli.py	14861	# reaches this OS-signal path. This matches how Claude Code
LOW	cli.py	15241	# Also install signal handlers in single-query / `-q` mode. Interactive
LOW	cli.py	15261	_agent.interrupt(f"received signal {signum}")
LOW	cli.py	15461	sys.exit(1)
LOW	hermes_state.py	41	# SQLite's WAL mode requires shared-memory (mmap) coordination and fcntl
LOW	hermes_state.py	401	self._init_schema()
LOW	hermes_state.py	841	# is shared across all instances. Two AIAgents that share the same
LOW	hermes_state.py	1441	# Compute effective_last_active by walking each surfaced session's
LOW	hermes_state.py	2261	# Step 2: Strip remaining (unmatched) FTS5-special characters
LOW	hermes_state.py	2421	# CJK queries bypass the unicode61 FTS5 table. The default tokenizer
LOW	hermes_state.py	3441	" + VACUUM" if result["vacuumed"] else "",
LOW	docker-compose.yml	1	#
LOW	docker-compose.yml	41	# To expose the OpenAI-compatible API server beyond localhost,
LOW	model_tools.py	181
LOW	model_tools.py	241	# =============================================================================
LOW	model_tools.py	481	# Sanitize schemas for broad backend compatibility. llama.cpp's
LOW	model_tools.py	561	# Tool error sanitization
LOW	model_tools.py	641	# Wrap bare non-list values when the schema declares ``array``.
LOW	model_tools.py	841	# ── Tool Search bridge dispatch ──────────────────────────────────
LOW	ui-tui/packages/hermes-ink/src/ink/output.ts	281
LOW	ui-tui/packages/hermes-ink/src/ink/dom.ts	41	hasRenderedContent?: boolean
LOW	ui-tui/packages/hermes-ink/src/ink/dom.ts	61	pendingScrollDelta?: number
LOW	…i/packages/hermes-ink/src/ink/render-node-to-output.ts	641	const boxBackgroundColor = node.style.backgroundColor ?? inheritedBackgroundColor
LOW	…i/packages/hermes-ink/src/ink/render-node-to-output.ts	761	// previous max, pin to the new max. Scroll away → stop following;
LOW	…i/packages/hermes-ink/src/ink/render-node-to-output.ts	821	// wheel-accel curve relies on.
LOW	…i/packages/hermes-ink/src/ink/render-node-to-output.ts	921	}
LOW	…i/packages/hermes-ink/src/ink/render-node-to-output.ts	1021
LOW	…i/packages/hermes-ink/src/ink/render-node-to-output.ts	1041	const spaces = ' '.repeat(w)
LOW	…i/packages/hermes-ink/src/ink/render-node-to-output.ts	1321	// child's own blit check already fails (node.dirty=true at line 216), so
LOW	ui-tui/packages/hermes-ink/src/ink/ink.tsx	221	private altScreenParkPatch: Readonly<{
LOW	ui-tui/packages/hermes-ink/src/ink/ink.tsx	241	currentIdx: number
LOW	ui-tui/packages/hermes-ink/src/ink/ink.tsx	261
LOW	ui-tui/packages/hermes-ink/src/ink/ink.tsx	281	private prevFrameContaminated = false
LOW	ui-tui/packages/hermes-ink/src/ink/ink.tsx	521
578 more matches not shown…

Self-Referential Comments125 hits · 403 pts

Severity	File	Line	Snippet
MEDIUM	cli.py	1073	# Create the worktree
MEDIUM	cli.py	6945	# Create the new session with parent link
MEDIUM	cli.py	13718	# Create the input area with multiline (Alt+Enter), autocomplete, and paste handling
MEDIUM	cli.py	14507	# Create the application
MEDIUM	cli.py	15141	# Create an isolated worktree so this agent instance doesn't collide
MEDIUM	trajectory_compressor.py	1403	# Create a temporary directory for processing
MEDIUM	trajectory_compressor.py	1450	# Create a temp directory with sampled files
MEDIUM	tools/skill_manager_tool.py	504	# Create the skill directory
MEDIUM	tools/discord_tool.py	442	# Create a standalone thread
MEDIUM	docker/stage2-hook.sh	24	# Create the directory (and any missing parents) while we still have root
MEDIUM	hermes_cli/backup.py	201	# Create the zip
MEDIUM	hermes_cli/config.py	1013	# Create a guardrail in the Bedrock console, then set the ID and version here.
MEDIUM	tests/test_tui_gateway_server.py	2529	# Create a minimal PNG file with a space in its name
MEDIUM	tests/test_toolsets.py	65	# Create a cycle: A includes B, B includes A
MEDIUM	tests/test_mcp_serve.py	186	# Create a mock SessionDB that reads from our test DB
MEDIUM	tests/test_mcp_serve.py	1094	# Create a mock SessionDB that reads our test DB
MEDIUM	tests/test_hermes_state.py	1265	# Create a recent session
MEDIUM	tests/test_hermes_state.py	2503	# Create a newer standalone session that should sort above the lineage
MEDIUM	tests/test_timezone.py	248	# Create a job with a NAIVE past timestamp (simulating pre-tz data)
MEDIUM	tests/test_timezone.py	297	# Create an aware datetime in UTC
MEDIUM	tests/test_timezone.py	273	# Create a naive datetime — will be interpreted as system-local time
MEDIUM	tests/test_hermes_constants.py	251	# Create a symlink with fewer path components
MEDIUM	tests/honcho_plugin/test_session.py	873	# Create a cached session so dialectic_query doesn't bail early
MEDIUM	tests/tools/test_transcription_tools.py	769	# Create a directory with a valid audio extension
MEDIUM	tests/tools/test_modal_bulk_upload.py	182	# Create a minimal env without full __init__
MEDIUM	tests/tools/test_docker_find.py	26	# Create a fake docker binary at a known path
MEDIUM	tests/tools/test_kanban_tools.py	569	# Create a real child via the tool so it gets the worker-profile
MEDIUM	tests/tools/test_browser_hardening.py	196	# Create a snapshot that exceeds 8000 chars
MEDIUM	tests/tools/test_browser_homebrew_paths.py	363	# Create a mock Popen that captures the env dict
MEDIUM	tests/tools/test_send_message_tool.py	1032	# Create a test file
MEDIUM	tests/tools/test_tirith_security.py	1018	# Create a fake executable
MEDIUM	tests/tools/test_browser_orphan_reaper.py	159	# Create a dir that doesn't match h_* or cdp_* pattern
MEDIUM	tests/tools/test_skill_view_traversal.py	24	# Create a legitimate file inside the skill
MEDIUM	tests/tools/test_skill_view_traversal.py	29	# Create a sensitive file outside skills dir (simulating .env)
MEDIUM	tests/tools/test_browser_lightpanda.py	187	# Create a tiny file simulating the Lightpanda placeholder PNG
MEDIUM	tests/tools/test_browser_lightpanda.py	203	# Create a larger file simulating a real Chrome screenshot
MEDIUM	tests/tools/test_credential_files.py	144	# Create a symlink pointing outside the skills tree
MEDIUM	tests/tools/test_credential_files.py	222	# Create a sensitive file one level above hermes_home
MEDIUM	tests/tools/test_credential_files.py	237	# Create a fake sensitive file outside hermes_home
MEDIUM	tests/tools/test_credential_files.py	253	# Create a file at an absolute path
MEDIUM	tests/tools/test_credential_files.py	295	# Create a sensitive file outside hermes_home
MEDIUM	tests/tools/test_credential_files.py	299	# Create a symlink inside hermes_home pointing outside
MEDIUM	tests/tools/test_docker_environment.py	1378	# Create a directory that looks like a corrupted credential file path
MEDIUM	tests/tools/test_mcp_stability.py	185	# Create a mock HermesCLI-like object with the needed attributes
MEDIUM	tests/tools/test_skill_size_limits.py	90	# Create a small skill first
MEDIUM	tests/tools/test_skill_size_limits.py	107	# Create a skill near the limit
MEDIUM	tests/tools/test_skill_size_limits.py	147	# Create a supporting file
MEDIUM	tests/tools/test_vision_tools.py	544	# Create a fake image file under a fake home directory
MEDIUM	tests/tools/test_vision_tools.py	755	# Create a small 10x10 red PNG
MEDIUM	tests/tools/test_vision_tools.py	319	# Create a real temp file that will be "downloaded"
MEDIUM	tests/tools/test_vision_tools.py	774	# Create a large image that will exceed 5 MB in base64
MEDIUM	tests/tools/test_vision_tools.py	878	# Create a dummy file
MEDIUM	tests/tools/test_voice_mode.py	867	# Create a file that doesn't match the pattern
MEDIUM	tests/tools/test_sync_back_backends.py	216	# Create a fake control socket so cleanup tries the SSH exit
MEDIUM	tests/tools/test_interrupt.py	91	# Create a minimal mock agent with _interrupt_requested = True
MEDIUM	tests/docker/test_container_restart.py	145	# Create the profile + start its gateway. The Phase 4 hooks
MEDIUM	tests/hermes_cli/test_copilot_token_exchange.py	154	# Create a minimal pconfig mock
MEDIUM	tests/hermes_cli/test_kanban_boards.py	151	# Create the board so the env-var value is honoured (get_current_board
MEDIUM	tests/hermes_cli/test_kanban_cli.py	408	# Create a triage task via the same slash surface.
MEDIUM	tests/hermes_cli/test_mcp_config.py	158	# Create a fake token file
65 more matches not shown…

Magic Placeholder Names39 hits · 195 pts

Severity	File	Line	Snippet
HIGH	hermes_cli/auth.py	540	"your_api_key",
HIGH	hermes_cli/auth.py	542	"your-api-key",
HIGH	optional-skills/devops/cli/references/authentication.md	30	export INFSH_API_KEY=your-api-key
HIGH	optional-skills/mlops/guidance/SKILL.md	276	api_key="your-api-key" # Or set ANTHROPIC_API_KEY env var
HIGH	optional-skills/mlops/guidance/SKILL.md	285	api_key="your-api-key" # Or set OPENAI_API_KEY env var
HIGH	optional-skills/mlops/guidance/references/backends.md	28	api_key="your-api-key-here"
HIGH	optional-skills/mlops/guidance/references/backends.md	53	api_key="your-api-key",
HIGH	optional-skills/mlops/guidance/references/backends.md	95	api_key="your-api-key-here"
HIGH	optional-skills/mlops/guidance/references/backends.md	120	api_key="your-api-key",
HIGH	optional-skills/mlops/pinecone/SKILL.md	54	pc = Pinecone(api_key="your-api-key")
HIGH	optional-skills/mlops/qdrant/SKILL.md	422	api_key="your-api-key"
HIGH	…onal-skills/mlops/qdrant/references/troubleshooting.md	117	api_key="your-api-key"
HIGH	optional-skills/mlops/inference/outlines/SKILL.md	228	api_key="your-api-key"
HIGH	…skills/mlops/inference/outlines/references/backends.md	381	model = outlines.models.openai("gpt-4o-mini", api_key="your-api-key")
HIGH	…skills/mlops/inference/outlines/references/backends.md	393	api_key="your-api-key", # Or set OPENAI_API_KEY env var
HIGH	optional-skills/mlops/instructor/SKILL.md	345	Anthropic(api_key="your-api-key")
HIGH	optional-skills/mlops/instructor/SKILL.md	363	OpenAI(api_key="your-api-key")
HIGH	…tional-skills/mlops/instructor/references/providers.md	16	Anthropic(api_key="your-api-key")
HIGH	…user-guide/skills/bundled/mlops/mlops-research-dspy.md	313	api_key="your-api-key", # Or set ANTHROPIC_API_KEY env var
HIGH	…user-guide/skills/bundled/mlops/mlops-research-dspy.md	325	api_key="your-api-key",
HIGH	…/docs/user-guide/skills/optional/mlops/mlops-qdrant.md	439	api_key="your-api-key"
HIGH	…s/user-guide/skills/optional/mlops/mlops-instructor.md	362	Anthropic(api_key="your-api-key")
HIGH	…s/user-guide/skills/optional/mlops/mlops-instructor.md	380	OpenAI(api_key="your-api-key")
HIGH	…ocs/user-guide/skills/optional/mlops/mlops-pinecone.md	71	pc = Pinecone(api_key="your-api-key")
HIGH	…ocs/user-guide/skills/optional/mlops/mlops-guidance.md	293	api_key="your-api-key" # Or set ANTHROPIC_API_KEY env var
HIGH	…ocs/user-guide/skills/optional/mlops/mlops-guidance.md	302	api_key="your-api-key" # Or set OPENAI_API_KEY env var
HIGH	…uide/skills/optional/mlops/mlops-inference-outlines.md	245	api_key="your-api-key"
HIGH	…user-guide/skills/bundled/mlops/mlops-research-dspy.md	313	api_key="your-api-key", # 或设置 ANTHROPIC_API_KEY 环境变量
HIGH	…user-guide/skills/bundled/mlops/mlops-research-dspy.md	325	api_key="your-api-key",
HIGH	…rrent/user-guide/skills/optional/mlops/mlops-qdrant.md	439	api_key="your-api-key"
HIGH	…t/user-guide/skills/optional/mlops/mlops-instructor.md	362	Anthropic(api_key="your-api-key")
HIGH	…t/user-guide/skills/optional/mlops/mlops-instructor.md	380	OpenAI(api_key="your-api-key")
HIGH	…ent/user-guide/skills/optional/mlops/mlops-pinecone.md	71	pc = Pinecone(api_key="your-api-key")
HIGH	…ent/user-guide/skills/optional/mlops/mlops-guidance.md	293	api_key="your-api-key" # 或设置 ANTHROPIC_API_KEY 环境变量
HIGH	…ent/user-guide/skills/optional/mlops/mlops-guidance.md	302	api_key="your-api-key" # 或设置 OPENAI_API_KEY 环境变量
HIGH	…uide/skills/optional/mlops/mlops-inference-outlines.md	245	api_key="your-api-key"
HIGH	tests/gateway/test_weak_credential_guard.py	59	config = _make_gateway_config(Platform.SLACK, "your_api_key")
HIGH	skills/mlops/research/dspy/SKILL.md	296	api_key="your-api-key", # Or set ANTHROPIC_API_KEY env var
HIGH	skills/mlops/research/dspy/SKILL.md	308	api_key="your-api-key",

Redundant / Tautological Comments142 hits · 162 pts

Severity	File	Line	Snippet
LOW	batch_runner.py	171	# Check if error field exists AND has a non-null value
LOW	hermes_constants.py	133	# Check if this is a profile path: <root>/profiles/<name>
LOW	setup-hermes.sh	288	# Check if sudo is available
LOW	run_agent.py	1229	# Check if there's any non-whitespace content remaining
LOW	cli.py	4292	# Check if we're entering a reasoning block.
LOW	cli.py	4312	# Check if this is a block boundary position
LOW	cli.py	8963	# Display result in the CLI (thread-safe via patch_stdout).
LOW	cli.py	9134	# Check if a Chromium-family browser is already serving CDP on the debug port
LOW	cli.py	12108	# Check if user fired ANOTHER interrupt (Ctrl+C sets
LOW	trajectory_compressor.py	739	# Check if compression needed
LOW	trajectory_compressor.py	750	# Check if there's anything to compress
LOW	trajectory_compressor.py	775	# Check if we have enough savings
LOW	trajectory_compressor.py	846	# Check if compression needed
LOW	trajectory_compressor.py	857	# Check if there's anything to compress
LOW	mcp_serve.py	352	# Check if sessions.json has changed (mtime check is ~1μs)
LOW	mcp_serve.py	363	# Check if state.db has changed
LOW	tools/vision_tools.py	980	# Check if vision model is available
LOW	tools/process_registry.py	786	# Check if process is still running
LOW	tools/process_registry.py	1422	# Check if PID is still alive
LOW	tools/web_tools.py	374	# Check if we need chunked processing
LOW	tools/web_tools.py	1180	# Check if API keys are available
LOW	tools/skills_hub.py	681	# Check if ANY entry lives under the target path
LOW	tools/fuzzy_match.py	691	# Check if this block matches
LOW	tools/mixture_of_agents_tool.py	337	# Check if we have enough successful responses to proceed
LOW	tools/mixture_of_agents_tool.py	448	# Check if API key is available
LOW	tools/browser_tool.py	1379	# Check if the daemon is still alive. ``os.kill(pid, 0)`` on Windows
LOW	tools/browser_tool.py	1679	# Check if we already have a session for this task
LOW	tools/browser_tool.py	1779	# Check if it's in PATH (global install)
LOW	tools/browser_tool.py	2523	# Check if snapshot needs summarization
LOW	tools/browser_tool.py	3174	# Check if screenshot file was created
LOW	tools/browser_tool.py	3429	# Check if session exists (under lock), but don't remove yet -
LOW	tools/terminal_tool.py	1928	# Check if this is an approval_required (gateway ask mode)
LOW	tools/skills_tool.py	1007	# Read the file once — reused for platform check and main content below
LOW	tools/skills_tool.py	1064	# Check if the skill is disabled by the user
LOW	tools/skills_tool.py	1152	# Read the file content
LOW	tools/skills_guard.py	933	# Check if source matches any trusted repo exactly, or a skill path inside
LOW	tools/mcp_tool.py	1750	# Check if shutdown was requested during the sleep
LOW	tools/mcp_tool.py	2514	# Check if the MCP tool itself returned an error
LOW	tools/file_operations.py	1618	# Check if parent directory exists and list similar entries
LOW	tools/file_operations.py	783	# Check if file exists and get size (wc -c is POSIX, works on Linux + macOS)
LOW	tools/file_operations.py	797	# Check if file is too large
LOW	tools/file_operations.py	844	# Check if truncated
LOW	hermes_cli/backup.py	305	# Check if all entries share a common first directory
LOW	hermes_cli/gateway.py	4656	# Check if signal-cli is available
LOW	hermes_cli/config.py	1265	# Set this to True to re-enable the surfaces with the understanding
LOW	hermes_cli/config.py	2097	# Set 0 to disable.
LOW	hermes_cli/config.py	3694	# Check if dict keys look like they should be list-entry fields
LOW	hermes_cli/config.py	5565	# Check if it's an API key (goes to .env)
LOW	hermes_cli/models.py	1386	# Check if this provider has credentials available
LOW	hermes_cli/skills_hub.py	482	# Check if any source hit GitHub API rate limit
LOW	hermes_cli/skills_hub.py	561	# Check if already installed
LOW	hermes_cli/model_switch.py	951	# Check if the requested model matches the entry's model
LOW	hermes_cli/model_switch.py	1223	# Check if any env var is set
LOW	hermes_cli/model_switch.py	1283	# Check if credentials exist
LOW	hermes_cli/web_server.py	4464	# Check if this plugin provides tools that require auth
LOW	hermes_cli/setup.py	1108	# Check if already installed
LOW	hermes_cli/setup.py	1254	# Check if already installed
LOW	hermes_cli/setup.py	1371	# Check if Docker is available
LOW	hermes_cli/setup.py	1390	# Check if singularity/apptainer is available
LOW	hermes_cli/setup.py	1450	# Check if modal SDK is installed
82 more matches not shown…

Verbosity Indicators99 hits · 153 pts

Severity	File	Line	Snippet
LOW	hermes_state.py	2251	# Step 1: Extract balanced double-quoted phrases and protect them
LOW	hermes_state.py	2261	# Step 2: Strip remaining (unmatched) FTS5-special characters
LOW	hermes_state.py	2264	# Step 3: Collapse repeated * (e.g. "***") into a single one,
LOW	hermes_state.py	2269	# Step 4: Remove dangling boolean operators at start/end that would
LOW	hermes_state.py	2274	# Step 5: Wrap unquoted dotted and/or hyphenated terms in double
LOW	hermes_state.py	2282	# Step 6: Restore preserved quoted phrases
LOW	tools/skills_hub.py	1417	# Step 1: fetch the sitemap index → list of skill-sitemap URLs.
LOW	tools/skills_hub.py	1439	# Step 2: fetch each skill sitemap and collect canonical "owner/repo/skill" IDs.
LOW	tools/skills_sync.py	609	# Step 1: drop the manifest entry so next sync treats it as new
LOW	tools/skills_sync.py	644	# Step 3: run sync to re-baseline (or re-copy if we deleted)
LOW	tools/mcp_oauth_manager.py	212	# Step 1: PRM discovery to learn the authorization_server URL.
LOW	tools/mcp_oauth_manager.py	234	# Step 2: ASM discovery against the auth_server_url (or
LOW	tools/mcp_oauth_manager.py	539	# Step 1: Did disk change? Picks up external refresh.
LOW	tools/mcp_oauth_manager.py	548	# Step 2: No disk change — if the SDK can refresh
LOW	tools/yuanbao_tools.py	372	# Step 2: Send text DM + media
LOW	tools/yuanbao_tools.py	382	# Step 3: Send media files
LOW	tools/yuanbao_tools.py	324	# Step 1: Resolve user_id from group member list if not provided
LOW	tools/send_message_tool.py	1694	# Step 1: Get access token
LOW	tools/send_message_tool.py	1706	# Step 2: Send message via REST
LOW	tools/computer_use/cua_backend.py	359	# Step 1: enumerate on-screen windows to find target pid/window_id.
LOW	tools/computer_use/cua_backend.py	421	# Step 2: capture.
LOW	hermes_cli/auth.py	6736	# Step 1: Request device code
LOW	hermes_cli/auth.py	6767	# Step 2: Show user the code
LOW	hermes_cli/auth.py	6775	# Step 3: Poll for authorization code
LOW	hermes_cli/auth.py	6810	# Step 4: Exchange authorization code for tokens
LOW	hermes_cli/skills_config.py	136	# Step 1: Select platform
LOW	hermes_cli/skills_config.py	140	# Step 2: Select mode — individual or by category
LOW	hermes_cli/dingtalk_auth.py	66	# Step 1: init → nonce
LOW	hermes_cli/dingtalk_auth.py	72	# Step 2: begin → device_code, verification_uri_complete
LOW	hermes_cli/send_cmd.py	217	# Step 1: dotenv
LOW	hermes_cli/send_cmd.py	241	# Step 2: bridge top-level config.yaml values into the environment so
LOW	hermes_cli/web_server.py	2233	# Step 1: request device code
LOW	hermes_cli/web_server.py	2260	# Step 2: poll until authorized
LOW	hermes_cli/web_server.py	2284	# Step 3: exchange authorization_code for tokens
LOW	hermes_cli/setup.py	3258	# Step 1: Model & Provider (essential — skips rotation/vision/TTS)
LOW	hermes_cli/setup.py	3261	# Step 2: Terminal Backend — where commands run is a core decision
LOW	hermes_cli/setup.py	3264	# Step 3: Apply defaults for everything else
LOW	hermes_cli/setup.py	3269	# Step 4: Offer messaging gateway setup
LOW	hermes_cli/tools_config.py	795	# Step 2: only the local browser provider actually needs Chromium on
LOW	hermes_cli/tools_config.py	801	# Step 3: ensure the Chromium / headless-shell build agent-browser
LOW	hermes_cli/tools_config.py	772	# Step 1: install the agent-browser npm package into node_modules/
LOW	hermes_cli/copilot_auth.py	174	# Step 1: Request device code
LOW	hermes_cli/copilot_auth.py	207	# Step 2: Show instructions
LOW	hermes_cli/copilot_auth.py	214	# Step 3: Poll for completion
LOW	hermes_cli/main.py	2370	# Step 1: Provider selection — flat list from CANONICAL_PROVIDERS
LOW	hermes_cli/main.py	2414	# Step 2: Provider-specific setup + model selection
LOW	hermes_cli/main.py	5121	# Step 1: Check / prompt for API key
LOW	hermes_cli/main.py	5134	# Step 2: Auto-detect endpoint from key prefix
LOW	hermes_cli/main.py	5147	# Step 3: Model selection — show appropriate models for the endpoint
LOW	plugins/memory/hindsight/__init__.py	657	# Step 1: Mode selection
LOW	plugins/memory/hindsight/__init__.py	673	# Step 2: Install/upgrade deps for selected mode
LOW	plugins/memory/hindsight/__init__.py	700	# Step 3: Mode-specific config
LOW	plugins/memory/hindsight/__init__.py	775	# Step 4: Save everything
LOW	optional-skills/finance/stocks/scripts/stocks_client.py	156	# Step 1: touch Yahoo Finance to get cookies
LOW	optional-skills/finance/stocks/scripts/stocks_client.py	164	# Step 2: fetch crumb
LOW	…tional-skills/productivity/here-now/scripts/publish.sh	307	# Step 1: Create/update publish
LOW	…tional-skills/productivity/here-now/scripts/publish.sh	331	# Step 2: Upload files (skipped files are unchanged from previous version)
LOW	…tional-skills/productivity/here-now/scripts/publish.sh	371	# Step 3: Finalize
LOW	tests/test_model_tools.py	252	# Step 1: caller checks for a block directive (this fires pre_tool_call once).
LOW	tests/test_model_tools.py	258	# Step 2: caller dispatches with skip=True so the hook isn't re-fired.
39 more matches not shown…

AI Slop Vocabulary46 hits · 96 pts

Severity	File	Line	Snippet
LOW	cli.py	2078	# • None (some mocks / older PT builds) — just call the inner
MEDIUM	trajectory_compressor.py	1182	"""Print comprehensive compression summary statistics."""
MEDIUM	tools/web_tools.py	465	system_prompt = """You are an expert content analyst. Your job is to process web content and create a comprehens
MEDIUM	tools/web_tools.py	474	user_prompt = f"""Please process this web content and create a comprehensive markdown summary:
LOW	tools/web_tools.py	611	# If only one chunk succeeded, just return it (with cap)
MEDIUM	tools/mixture_of_agents_tool.py	83	AGGREGATOR_SYSTEM_PROMPT = """You have been provided with a set of responses from various open-source models to the late
MEDIUM	tools/browser_supervisor.py	1057	# Parse query string for dialog metadata. Use urllib to be robust.
LOW	tools/kanban_tools.py	569	# the write txn), so the worker can simply call
MEDIUM	docker/hermes-exec-shim.sh	69	# Reference it by absolute path so the drop is robust against PATH
MEDIUM	hermes_cli/gateway.py	3343	# Absolutely everything else: Exception, asyncio.CancelledError,
LOW	hermes_cli/models.py	1632	# Already on openrouter, just return the resolved slug
LOW	hermes_cli/web_server.py	1235	pass # can't read disk config — just use the string form
LOW	hermes_cli/kanban.py	1245	# dispatcher doesn't need to enumerate — we just pass the name
MEDIUM	plugins/kanban/dashboard/plugin_api.py	1911	# the simplest and most robust approach; it adds a fraction of a percent
MEDIUM	web/package-lock.json	8239	"resolved": "https://registry.npmjs.org/robust-predicates/-/robust-predicates-3.0.3.tgz",
MEDIUM	website/package-lock.json	17646	"resolved": "https://registry.npmjs.org/robust-predicates/-/robust-predicates-3.0.2.tgz",
LOW	tests/tools/test_env_probe.py	154	# Should not raise, should just return ""
MEDIUM	tests/docker/test_gateway_run_supervised.py	92	# harness profile has a configured model, but the want-intent
LOW	tests/hermes_cli/test_codex_runtime_plugin_migration.py	842	# We can't easily create one in the test, so just use a stable path
LOW	tests/hermes_cli/test_commands.py	1802	# Both calls should succeed and just return the built-in set.
LOW	tests/hermes_cli/test_voice_wrapper.py	289	# Should simply return None without raising.
LOW	tests/plugins/test_langfuse_plugin.py	166	# Each hook should just return; no exceptions.
MEDIUM	tests/plugins/transcription/check_parity_vs_main.py	192	# so the harness can distinguish command-provider dispatch from a
MEDIUM	tests/plugins/tts/check_parity_vs_main.py	198	# This is the ONLY acceptable diff in the harness.
MEDIUM	tests/agent/test_codex_ttfb_watchdog.py	49	# the test is robust to detection-logic changes elsewhere.
LOW	tests/agent/test_context_engine.py	40	# Trivial: just return as-is
MEDIUM	tests/acp/test_ping_suppression.py	166	# Test harness reads agent output via this StreamReader:
MEDIUM	tests/gateway/conftest.py	43	"""Install a comprehensive telegram mock in sys.modules.
MEDIUM	tests/gateway/conftest.py	87	"""Install a comprehensive discord mock in sys.modules.
MEDIUM	tests/gateway/test_api_server.py	1163	# the test robust against preview-formatter tweaks.
LOW	tests/gateway/test_session_env.py	29	# Can't use var.reset() without a token; just set back to sentinel.
LOW	tests/gateway/test_session_env.py	215	# After clearing, the session key must not retain the value we just set.
LOW	tests/gateway/test_slash_access_dispatch.py	414	# If /history has aliases, use one. Otherwise just use /history.
LOW	tests/gateway/test_pairing.py	272	# Approving with any code must just return None, not crash.
MEDIUM	agent/error_classifier.py	479	# Build a comprehensive error message string for pattern matching.
MEDIUM	agent/background_review.py	389	# run_conversation() then leaks the harness prompt
MEDIUM	agent/background_review.py	393	# sync_all (harness prompt + review output recorded
MEDIUM	tui_gateway/server.py	3893	# Save-first: mirrors CLI keybinding path; more robust than has_image() precheck
MEDIUM	.github/workflows/docker-publish.yml	126	# real-API calls from inside the harness.
MEDIUM	skills/index-cache/lobehub_index.json	1	{"schemaVersion": 1, "agents": [{"author": "CSY2022", "createdAt": "2025-06-19", "homepage": "https://github.com/CSY2022
MEDIUM	skills/index-cache/lobehub_index.json	1	{"schemaVersion": 1, "agents": [{"author": "CSY2022", "createdAt": "2025-06-19", "homepage": "https://github.com/CSY2022
MEDIUM	skills/index-cache/lobehub_index.json	1	{"schemaVersion": 1, "agents": [{"author": "CSY2022", "createdAt": "2025-06-19", "homepage": "https://github.com/CSY2022
MEDIUM	skills/index-cache/lobehub_index.json	1	{"schemaVersion": 1, "agents": [{"author": "CSY2022", "createdAt": "2025-06-19", "homepage": "https://github.com/CSY2022
MEDIUM	skills/index-cache/lobehub_index.json	1	{"schemaVersion": 1, "agents": [{"author": "CSY2022", "createdAt": "2025-06-19", "homepage": "https://github.com/CSY2022
LOW	gateway/run.py	9635	# No existing session, just create one
MEDIUM	gateway/platforms/telegram.py	5306	# Normalize mime_type for robust comparisons (some clients send

Docstring Block Structure17 hits · 85 pts

Severity	File	Line	Snippet
HIGH	toolset_distributions.py	248	Sample toolsets based on a distribution's probabilities. Each toolset in the distribution has a % chance o
HIGH	tools/vision_tools.py	131	Download an image from a URL to a local destination (async) with retry logic. Args: image_url (str
HIGH	tools/vision_tools.py	668	Analyze an image from a URL or local file path using vision AI. This tool accepts either an HTTP/HTTPS URL
HIGH	tools/web_tools.py	765	Search the web for information using available search API backend. This function provides a generic interface
HIGH	tools/web_tools.py	878	Extract content from specific web pages using available extraction API backend. This function provides a gener
HIGH	tools/mixture_of_agents_tool.py	241	Process a complex query using the Mixture-of-Agents methodology. This tool leverages multiple frontier lan
HIGH	tools/terminal_tool.py	1732	Execute a command in the configured terminal environment. Args: command: The command to execute
HIGH	hermes_cli/model_normalize.py	247	Detect the vendor slug from a bare model name. Uses the first hyphen-delimited token of the model name to look up
HIGH	hermes_cli/model_normalize.py	327	Translate a model name into the format the target provider's API expects. This is the primary entry point for model
HIGH	agent/auxiliary_client.py	4825	Centralized synchronous LLM call. Resolves provider + model (from task config, explicit args, or auto-detect),
HIGH	gateway/platforms/base.py	587	Save raw image bytes to the cache and return the absolute file path. Args: data: Raw image bytes.
HIGH	gateway/platforms/base.py	615	Download an image from a URL and save it to the local cache. Retries on transient failures (timeouts, 429, 5xx
HIGH	gateway/platforms/base.py	729	Download an audio file from a URL and save it to the local cache. Retries on transient failures (timeouts, 429
HIGH	gateway/platforms/base.py	1210	Save raw document bytes to the cache and return the absolute file path. The cached filename preserves the orig
HIGH	gateway/platforms/yuanbao_media.py	206	下载 URL 内容，返回 (bytes, content_type)。 Args: url: HTTP(S) URL max_size_mb: 最大允许大小（MB），超
HIGH	gateway/platforms/yuanbao_media.py	348	调用 genUploadInfo 接口获取 COS 临时密钥及上传配置。 Args: app_key: 应用 Key（用于 X-ID 头） api_domain: A
HIGH	gateway/platforms/yuanbao_media.py	425	通过 httpx PUT 请求将文件上传到 COS。使用临时凭证（tmpSecretId/tmpSecretKey/sessionToken）构建 HMAC-SHA1 签名。 Args: fil

Fake / Example Data74 hits · 74 pts

Severity	File	Line	Snippet
LOW	plugins/memory/holographic/store.py	402	1. Capitalized multi-word phrases e.g. "John Doe"
LOW	optional-skills/mlops/inference/outlines/SKILL.md	78	print(user.name) # "John Doe"
LOW	optional-skills/mlops/instructor/SKILL.md	70	print(user.name) # "John Doe"
LOW	optional-skills/mlops/instructor/SKILL.md	636	"name": "John Doe",
LOW	optional-skills/mlops/instructor/SKILL.md	678	"name": "John Doe",
LOW	optional-skills/productivity/here-now/SKILL.md	140	-d '{"email": "user@example.com"}'
LOW	optional-skills/productivity/here-now/SKILL.md	149	-d '{"email":"user@example.com","code":"ABCD-2345"}'
LOW	…user-guide/skills/bundled/mlops/mlops-research-dspy.md	375	print(result.person.name) # "John Doe"
LOW	…/user-guide/skills/bundled/creative/creative-sketch.md	103	- Realistic fake content — actual sentences, actual names, not "Lorem ipsum"
LOW	…user-guide/skills/bundled/creative/creative-pretext.md	67	- Real source/text, not lorem ipsum. The corpus should mean something. Short manifestos, poetry, real source code, a
LOW	…user-guide/skills/bundled/creative/creative-pretext.md	217	- [ ] Corpus is real prose, not lorem ipsum, and matches the demo's concept
LOW	…ide/skills/bundled/productivity/productivity-notion.md	332	- Email: `{"email": "user@example.com"}`
LOW	…e/skills/bundled/productivity/productivity-nano-pdf.md	61	nano-pdf edit contract.pdf 2 "Change the client name from 'Acme Corp' to 'Acme Industries'"
LOW	…e/skills/bundled/productivity/productivity-airtable.md	122	- Exact match: `{Email}='user@example.com'`
LOW	…e/skills/bundled/productivity/productivity-airtable.md	184	{"fields": {"Email": "user@example.com", "Status": "Active"}}
LOW	…s/user-guide/skills/optional/mlops/mlops-instructor.md	87	print(user.name) # "John Doe"
LOW	…s/user-guide/skills/optional/mlops/mlops-instructor.md	653	"name": "John Doe",
LOW	…s/user-guide/skills/optional/mlops/mlops-instructor.md	695	"name": "John Doe",
LOW	…uide/skills/optional/mlops/mlops-inference-outlines.md	95	print(user.name) # "John Doe"
LOW	…/skills/optional/productivity/productivity-here-now.md	154	-d '{"email": "user@example.com"}'
LOW	…/skills/optional/productivity/productivity-here-now.md	163	-d '{"email":"user@example.com","code":"ABCD-2345"}'
LOW	…user-guide/skills/bundled/mlops/mlops-research-dspy.md	375	print(result.person.name) # "John Doe"
LOW	…/user-guide/skills/bundled/creative/creative-sketch.md	103	- 真实的虚假内容——实际句子、实际姓名，而非"Lorem ipsum"
LOW	…user-guide/skills/bundled/creative/creative-pretext.md	67	- 使用真实语料，而非 lorem ipsum。语料库应有意义。短篇宣言、诗歌、真实源代码、发现的文本、库自身的 README —— 绝不用 `lorem ipsum`。
LOW	…user-guide/skills/bundled/creative/creative-pretext.md	217	- [ ] 语料库为真实散文，非 lorem ipsum，且与演示概念匹配
LOW	…ide/skills/bundled/productivity/productivity-notion.md	332	- 邮箱（Email）： `{"email": "user@example.com"}`
LOW	…e/skills/bundled/productivity/productivity-nano-pdf.md	61	nano-pdf edit contract.pdf 2 "Change the client name from 'Acme Corp' to 'Acme Industries'"
LOW	…e/skills/bundled/productivity/productivity-airtable.md	122	- 精确匹配：`{Email}='user@example.com'`
LOW	…e/skills/bundled/productivity/productivity-airtable.md	184	{"fields": {"Email": "user@example.com", "Status": "Active"}}
LOW	…t/user-guide/skills/optional/mlops/mlops-instructor.md	87	print(user.name) # "John Doe"
LOW	…t/user-guide/skills/optional/mlops/mlops-instructor.md	653	"name": "John Doe",
LOW	…t/user-guide/skills/optional/mlops/mlops-instructor.md	695	"name": "John Doe",
LOW	…uide/skills/optional/mlops/mlops-inference-outlines.md	95	print(user.name) # "John Doe"
LOW	…/skills/optional/productivity/productivity-here-now.md	154	-d '{"email": "user@example.com"}'
LOW	…/skills/optional/productivity/productivity-here-now.md	163	-d '{"email":"user@example.com","code":"ABCD-2345"}'
LOW	tests/hermes_cli/test_doctor.py	932	{"logged_in": True, "email": "user@example.com"},
LOW	tests/agent/test_file_safety_credentials.py	176	"email": "user@example.com",
LOW	tests/agent/test_gemini_cloudcode.py	204	email="user@example.com",
LOW	tests/cli/test_worktree_security.py	15	subprocess.run(["git", "config", "user.email", "test@test.com"], cwd=repo, check=True, capture_output=True)
LOW	tests/cli/test_worktree.py	21	["git", "config", "user.email", "test@test.com"],
LOW	tests/cli/test_worktree.py	55	["git", "config", "user.email", "test@test.com"],
LOW	tests/cli/test_worktree.py	78	["git", "config", "user.email", "test@test.com"],
LOW	tests/gateway/test_email.py	876	raw_email["From"] = '"John Doe" <john@test.com>'
LOW	tests/gateway/test_email.py	410	"sender_name": "John Doe",
LOW	tests/gateway/test_email.py	423	self.assertEqual(event.source.user_name, "John Doe")
LOW	tests/gateway/test_email.py	896	self.assertEqual(results[0]["sender_name"], "John Doe")
LOW	tests/gateway/test_bluebubbles.py	42	monkeypatch.setenv("BLUEBUBBLES_HOME_CHANNEL", "user@example.com")
LOW	tests/gateway/test_bluebubbles.py	49	assert hc.chat_id == "user@example.com"
LOW	tests/gateway/test_bluebubbles.py	95	result = await adapter.send("user@example.com", "first thought\n\nsecond thought")
LOW	tests/gateway/test_bluebubbles.py	140	"chatIdentifier": "user@example.com",
LOW	tests/gateway/test_bluebubbles.py	257	"chatIdentifier": "user@example.com",
LOW	tests/gateway/test_bluebubbles.py	158	"handle": {"address": "user@example.com"},
LOW	tests/gateway/test_bluebubbles.py	190	assert chat_identifier == "user@example.com"
LOW	tests/gateway/test_send_multiple_images.py	432	_run(adapter.send_multiple_images("user@example.com", images))
LOW	tests/gateway/test_send_multiple_images.py	436	assert to_addr == "user@example.com"
LOW	tests/gateway/test_send_multiple_images.py	449	_run(adapter.send_multiple_images("user@example.com", images))
LOW	tests/gateway/test_send_multiple_images.py	461	_run(adapter.send_multiple_images("user@example.com", []))
LOW	agent/google_oauth.py	19	"email": "user@example.com"
LOW	skills/mlops/research/dspy/SKILL.md	358	print(result.person.name) # "John Doe"
LOW	skills/mlops/research/dspy/references/modules.md	236	print(result.person.name) # "John Doe"
14 more matches not shown…

Hallucination Indicators6 hits · 60 pts

Severity	File	Line	Snippet
CRITICAL	…tional-skills/mlops/training/axolotl/references/api.md	658	core.trainers.grpo.sampler.SequenceParallelRepeatRandomSampler.set_epoch(epoch)
CRITICAL	…tional-skills/mlops/training/axolotl/references/api.md	1795	core.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer.get_train_dataloader(
CRITICAL	…tional-skills/mlops/training/axolotl/references/api.md	4690	core.trainers.dpo.trainer.AxolotlDPOTrainer.push_to_hub(args, *kwargs)
CRITICAL	…tional-skills/mlops/training/axolotl/references/api.md	4892	core.trainers.mixins.scheduler.SchedulerMixin.create_scheduler(
CRITICAL	tests/gateway/test_stream_consumer_thread_routing.py	176	mock_client.im.v1.message.create.assert_called_once()
CRITICAL	tests/gateway/test_stream_consumer_thread_routing.py	227	mock_client.im.v1.message.create.assert_called_once()

Synthetic Comment Markers5 hits · 30 pts

Severity	File	Line	Snippet
HIGH	…ve/kanban-video-orchestrator/references/tool-matrix.md	177	# - comfyui (AI-generated visuals)
HIGH	…er-guide/skills/bundled/creative/creative-humanizer.md	590	This skill is ported from [blader/humanizer](https://github.com/blader/humanizer) (MIT licensed), which is itself based
HIGH	skills/index-cache/lobehub_index.json	1	{"schemaVersion": 1, "agents": [{"author": "CSY2022", "createdAt": "2025-06-19", "homepage": "https://github.com/CSY2022
HIGH	…ls/creative/popular-web-designs/templates/replicate.md	266	- "Create a manifesto section on Replicate Dark (#202020) with 'Imagine what you can build.' at 128px rb-freigeist-neue
HIGH	skills/creative/humanizer/SKILL.md	574	This skill is ported from [blader/humanizer](https://github.com/blader/humanizer) (MIT licensed), which is itself based

Example Usage Blocks14 hits · 23 pts

Severity	File	Line	Snippet
LOW	docker-compose.windows.yml	9	# Usage:
LOW	setup-hermes.sh	8	# Usage:
LOW	docker-compose.yml	4	# Usage:
LOW	tools/registry.py	554	# Usage:
LOW	scripts/kill_modal.sh	4	# Usage:
LOW	scripts/install.sh	8	# Usage:
LOW	scripts/setup_open_webui.sh	12	# Usage:
LOW	scripts/run_tests.sh	16	# Usage:
LOW	scripts/lib/node-bootstrap.sh	15	# Usage:
LOW	skills/creative/comfyui/scripts/comfyui_setup.sh	14	# Usage:
LOW	skills/creative/p5js/scripts/render.sh	5	# Usage:
LOW	skills/creative/p5js/scripts/serve.sh	5	# Usage:
LOW	datagen-config-examples/web_research.yaml	6	# Usage:
LOW	datagen-config-examples/run_browser_tasks.sh	17	# Usage:

Dead Code4 hits · 8 pts

Severity	File	Line
MEDIUM	tests/gateway/test_discord_free_response.py	68
MEDIUM	tests/gateway/test_discord_free_response.py	93
MEDIUM	tests/gateway/test_discord_slash_commands.py	630
MEDIUM	tests/gateway/test_discord_slash_commands.py	649

Slop Phrases2 hits · 6 pts

Severity	File	Line	Snippet
MEDIUM	tools/web_tools.py	450	5. Note any references to other sections (e.g., "as mentioned earlier", "see below") without trying to resolve them
MEDIUM	datagen-config-examples/run_browser_tasks.sh	57	# Common options you can add:

Overly Generic Function Names5 hits · 5 pts

Severity	File	Line	Snippet
LOW	mini_swe_runner.py	414	def run_task(self, task: str) -> Dict[str, Any]:
LOW	tests/tools/test_patch_parser.py	199	+def helper():
LOW	tests/tools/test_patch_parser.py	226	assert "def helper():" in file_ops.written
LOW	tests/hermes_cli/test_xai_oauth_pkce_token_exchange.py	326	def handle_request(self, request):
LOW	tui_gateway/server.py	465	def handle_request(req: dict) -> dict \| None:

Score History

Severity Breakdown

Pattern Findings