Home / wshobson / agents
AI Slop Code RIsk Monitor

wshobson/agents

Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi

8.7 Moderate pattern signal View on GitHub

Maintenance and Governance Review

This report summarizes scanner evidence for wshobson/agents, a Python project with 40,335 GitHub stars. SynthScan examined 238,109 lines of code across 1125 source files, recording 1414 pattern matches distributed across 17 syntactic categories. The legacy adjusted pattern signal is 8.7 (Moderate pattern signal); it is not an authorship estimate.

Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.

8.7
Adjusted Signal
8.7
Raw Pattern Score
100%
Time Factor
2026-10-05
Last Push
40.3K
Stars
Python
Language
238.1K
Lines of Code
1.1K
Files
1.4K
Pattern Hits
2026-10-12
Scan Date
0.02
HC Hit Rate

Risk Review · v3

Use each vector to guide manual verification of the underlying findings.

Cognitive Ownership Risk 24.5/100 · LOW

Can maintainers explain intent, assumptions, and trade-offs? 1068 finding(s).

Hallucinated Dependency & Supply Chain Risk 4.2/100 · LOW

Are imports declared and package/API names verified? 130 finding(s).

Agent Over-Engineering Ratio 21.4/100 · LOW

Are wrappers, guards, and repeated structures necessary? 902 finding(s).

PR Review Velocity Impact 33.3/100 · MEDIUM

Which changes need focused human review? 1414 finding(s).

What These Metrics Mean

Adjusted Signal
Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score
Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor
A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits
Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate
High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files
Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.

Severity Breakdown

Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.

CRITICAL 0HIGH 23MEDIUM 199LOW 1192

Directory Score Breakdown

This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.

Pattern Findings

The scanner identified 1414 distinct pattern matches across 17 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. 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 configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Hyper-Verbose Identifiers686 hits · 620 pts
SeverityFileLineSnippetContext
LOWtools/doc_gardener.py129def marketplace_entry_problem(entry: object) -> str | None:CODE
LOWtools/doc_gardener.py360def check_generated_frontmatter_yaml(report: Report) -> None:CODE
LOWtools/doc_gardener.py415def check_oversized_context_files(report: Report) -> None:CODE
LOWtools/doc_gardener.py487def _report_dead_skill_references(md: Path, content: str, report: Report) -> None:CODE
LOWtools/doc_gardener.py564def check_marketplace_consistency(report: Report) -> None:CODE
LOWtools/doc_gardener.py644def canonical_frontmatter_value(value: object) -> object:CODE
LOWtools/validate_generated.py67def _check_nonempty_str_field(CODE
LOWtools/validate_generated.py345def _extract_permission_block(raw: str) -> dict | None:CODE
LOWtools/install_antigravity.py36def default_legacy_config_dir() -> Path:CODE
LOW⚡tools/tests/test_install_copilot.py24def test_default_config_dir_prefers_copilot_config_dir(tmp_path: Path):CODE
LOW⚡tools/tests/test_install_copilot.py32def test_default_config_dir_uses_xdg_config_home(tmp_path: Path):CODE
LOW⚡tools/tests/test_install_copilot.py38def test_install_creates_idempotent_symlinks(tmp_path: Path):CODE
LOWtools/tests/test_install_copilot.py55def test_install_refuses_to_overwrite_real_files(tmp_path: Path):CODE
LOWtools/tests/test_install_copilot.py70def test_force_replaces_conflicting_symlink_only(tmp_path: Path):CODE
LOWtools/tests/test_install_copilot.py90def test_main_does_not_clear_caches_on_failed_install(tmp_path: Path, monkeypatch):CODE
LOWtools/tests/test_install_copilot.py130def test_main_clears_caches_on_successful_install(tmp_path: Path, monkeypatch):CODE
LOWtools/tests/test_install_copilot.py163def test_uninstall_removes_only_repo_owned_symlinks(tmp_path: Path):CODE
LOWtools/tests/test_real_world.py60 def test_every_local_marketplace_entry_resolves_to_plugin_dir(self):CODE
LOWtools/tests/test_real_world.py71 def test_every_local_plugin_dir_appears_in_marketplace(self):CODE
LOWtools/tests/test_real_world.py78 def test_marketplace_version_matches_per_plugin_json(self):CODE
LOW⚡tools/tests/test_real_world.py105 def test_plugin_loads_without_error(self, plugin_name: str):CODE
LOW⚡tools/tests/test_real_world.py109 def test_no_plugin_name_contains_double_underscore(self):CODE
LOW⚡tools/tests/test_real_world.py114 def test_every_agent_has_name_and_description(self):CODE
LOWtools/tests/test_real_world.py127 def test_every_skill_has_trigger_phrase(self):CODE
LOWtools/tests/test_real_world.py142 def test_no_agent_collides_with_codex_builtin(self):CODE
LOWtools/tests/test_real_world.py156 def test_agent_frontmatter_names_are_unique_across_plugins(self):CODE
LOWtools/tests/test_real_world.py173 def test_command_phase_output_references_match_task_keys(self):CODE
LOWtools/tests/test_real_world.py220 def test_every_refactored_skill_has_meaningful_details(self):CODE
LOWtools/tests/test_real_world.py233 def test_extracted_skills_have_pointer_to_references(self):CODE
LOWtools/tests/test_real_world.py245 def test_extracted_skills_preserve_when_to_use(self):CODE
LOWtools/tests/test_real_world.py267 def test_no_refactored_skill_is_stub_only(self):CODE
LOWtools/tests/test_real_world.py288 def test_plugin_json_has_name_and_version(self, plugin_name: str):CODE
LOW⚡tools/tests/test_round_trip.py70 def test_codex_agent_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py119 def test_opencode_agent_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py125 def test_opencode_command_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py131 def test_opencode_skill_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py137 def test_every_opencode_agent_has_required_frontmatter(self):CODE
LOW⚡tools/tests/test_round_trip.py245 def test_copilot_agent_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py251 def test_copilot_skill_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py259 def test_copilot_command_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py267 def test_copilot_command_entrypoints_exist_for_every_plugin(self):CODE
LOW⚡tools/tests/test_round_trip.py275 def test_every_copilot_agent_has_required_frontmatter(self):CODE
LOW⚡tools/tests/test_round_trip.py294 def test_antigravity_plugin_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py300 def test_antigravity_skill_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py306 def test_antigravity_agent_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py312 def test_antigravity_command_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py318 def test_every_antigravity_plugin_json_matches_source_plugin(self):CODE
LOW⚡tools/tests/test_round_trip.py378 def test_pi_skill_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py384 def test_pi_prompt_count_matches_source_commands(self):CODE
LOW⚡tools/tests/test_round_trip.py390 def test_pi_agent_count_matches_source(self):CODE
LOW⚡tools/tests/test_round_trip.py396 def test_every_pi_prompt_maps_back_to_a_source_command(self):CODE
LOW⚡tools/tests/test_round_trip.py406 def test_every_pi_agent_name_is_unique_and_model_is_provider_qualified(self):CODE
LOWtools/tests/test_round_trip.py85 def test_every_codex_agent_toml_parses_and_has_required_fields(self):CODE
LOWtools/tests/test_round_trip.py106 def test_agents_md_within_cap(self):CODE
LOWtools/tests/test_round_trip.py152 def test_locked_agents_have_proper_permission_block(self):CODE
LOWtools/tests/test_round_trip.py184 def test_every_opencode_skill_has_valid_frontmatter(self):CODE
LOWtools/tests/test_round_trip.py206 def test_cursor_marketplace_lists_all_local_plugins(self):CODE
LOWtools/tests/test_round_trip.py217 def test_cursor_per_plugin_manifests_exist(self):CODE
LOWtools/tests/test_round_trip.py226 def test_cursor_rules_only_use_allowed_keys(self):CODE
LOWtools/tests/test_round_trip.py330 def test_no_at_path_injection_in_antigravity_commands(self):CODE
626 more matches not shown…
Structural Annotation Overuse277 hits · 476 pts
SeverityFileLineSnippetContext
LOW…ns/backend-development/commands/feature-development.md69### Step 1: Requirements GatheringCOMMENT
LOW…ns/backend-development/commands/feature-development.md121### Step 2: Architecture & Security DesignCOMMENT
LOW…ns/backend-development/commands/feature-development.md174### Step 3: Backend ImplementationCOMMENT
LOW…ns/backend-development/commands/feature-development.md208### Step 4: Frontend ImplementationCOMMENT
LOW…ns/backend-development/commands/feature-development.md246### Step 5: Testing & ValidationCOMMENT
LOW…ns/backend-development/commands/feature-development.md377### Step 6: Deployment & MonitoringCOMMENT
LOW…ns/backend-development/commands/feature-development.md411### Step 7: Documentation & HandoffCOMMENT
LOWplugins/incident-response/commands/incident-response.md69### Step 1: Incident Detection and ClassificationCOMMENT
LOWplugins/incident-response/commands/incident-response.md97### Step 2: Observability AnalysisCOMMENT
LOWplugins/incident-response/commands/incident-response.md127### Step 3: Initial MitigationCOMMENT
LOWplugins/incident-response/commands/incident-response.md185### Step 4: Deep System DebuggingCOMMENT
LOWplugins/incident-response/commands/incident-response.md216### Step 5: Security AssessmentCOMMENT
LOWplugins/incident-response/commands/incident-response.md242### Step 6: Performance AnalysisCOMMENT
LOWplugins/incident-response/commands/incident-response.md319### Step 7: Fix ImplementationCOMMENT
LOWplugins/incident-response/commands/incident-response.md347### Step 8: Deployment and ValidationCOMMENT
LOWplugins/incident-response/commands/incident-response.md399### Step 9: Stakeholder CommunicationCOMMENT
LOWplugins/incident-response/commands/incident-response.md429### Step 10: Customer Impact AssessmentCOMMENT
LOWplugins/incident-response/commands/incident-response.md463### Step 11: Blameless PostmortemCOMMENT
LOWplugins/incident-response/commands/incident-response.md494### Step 12: Monitoring EnhancementCOMMENT
LOWplugins/incident-response/commands/incident-response.md525### Step 13: System HardeningCOMMENT
LOWplugins/incident-response/commands/smart-fix.md69### Step 1: Error Detection and Context GatheringCOMMENT
LOWplugins/incident-response/commands/smart-fix.md107### Step 2: Root Cause IdentificationCOMMENT
LOWplugins/incident-response/commands/smart-fix.md174### Step 3: Deep Code AnalysisCOMMENT
LOWplugins/incident-response/commands/smart-fix.md208### Step 4: Code Review Deep DiveCOMMENT
LOWplugins/incident-response/commands/smart-fix.md253### Step 5: Implement FixCOMMENT
LOWplugins/incident-response/commands/smart-fix.md320### Step 6: Regression TestingCOMMENT
LOWplugins/incident-response/commands/smart-fix.md346### Step 7: Performance ValidationCOMMENT
LOWplugins/incident-response/commands/smart-fix.md373### Step 8: Security ReviewCOMMENT
LOWplugins/incident-response/commands/smart-fix.md445### Step 9: Final Code ReviewCOMMENT
LOWplugins/incident-response/commands/smart-fix.md474### Step 10: Documentation & PreventionCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md75# Step 1: Check pod statusCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md78# Step 2: If pods are crash-looping, check logsCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md81# Step 3: Check recent deploymentsCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md84# Step 4: ROLLBACK if recent deploy is suspectCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md87# Step 5: Scale up if resource constrainedCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md90# Step 6: Verify recoveryCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md97# Step 1: Check database connectionsCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md101# Step 2: Check slow queries (if DB issue)COMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md108# Step 3: Kill long-running queries if neededCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md111# Step 4: Check external dependency latencyCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md114# Step 5: Enable circuit breaker if dependency is slowCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md122# Step 1: Identify error patternCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md126# Step 2: Check error trackingCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md129# Step 3: If specific endpoint, enable feature flag to disableCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md133# Step 4: If data issue, check recent data changesCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md143# Step 1: Check current request rateCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md146# Step 2: Scale horizontallyCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md149# Step 3: Enable rate limitingCOMMENT
LOW⚡…kills/incident-runbook-templates/references/details.md154# Step 4: If attack, block suspicious IPsCOMMENT
LOW⚡plugins/plugin-eval/agents/eval-orchestrator.md18## Step 1: Run Static AnalysisCOMMENT
LOW⚡plugins/plugin-eval/agents/eval-orchestrator.md27## Step 2: LLM Judge (Standard+ Depth)COMMENT
LOW⚡plugins/plugin-eval/agents/eval-orchestrator.md35## Step 3: Compute Final CompositeCOMMENT
LOWplugins/plugin-eval/agents/eval-orchestrator.md54## Step 4: Badge AssignmentCOMMENT
LOW⚡plugins/plugin-eval/commands/eval.md15### Step 1: Run Static Analysis (Layer 1)COMMENT
LOW⚡plugins/plugin-eval/commands/eval.md24### Step 2: LLM Judge (Layer 2) — if NOT --depth quickCOMMENT
LOW⚡plugins/plugin-eval/commands/eval.md34### Step 3: Compute Final ScoreCOMMENT
LOWplugins/plugin-eval/commands/eval.md56### Step 4: Present ResultsCOMMENT
LOWplugins/multi-platform-apps/commands/multi-platform.md69### Step 1: Define Feature Requirements and API ContractsCOMMENT
LOWplugins/multi-platform-apps/commands/multi-platform.md107### Step 2: Design System and UI/UX ConsistencyCOMMENT
LOWplugins/multi-platform-apps/commands/multi-platform.md149### Step 3: Shared Business Logic ArchitectureCOMMENT
217 more matches not shown…
Decorative Section Separators131 hits · 420 pts
SeverityFileLineSnippetContext
MEDIUMtools/doc_gardener.py97# ── Findings ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/doc_gardener.py162# ── Checks ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/validate_generated.py30# ── Findings ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/validate_generated.py64# ── Helpers ──────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/validate_generated.py111# ── Codex validators ─────────────────────────────────────────────────────────COMMENT
MEDIUMtools/validate_generated.py222# ── Cursor validators ────────────────────────────────────────────────────────COMMENT
MEDIUMtools/validate_generated.py318# ── OpenCode validators ──────────────────────────────────────────────────────COMMENT
MEDIUMtools/validate_generated.py523# ── Antigravity validators ───────────────────────────────────────────────────COMMENT
MEDIUMtools/validate_generated.py654# ── Pi validators ────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/validate_generated.py757# ── Driver ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_real_world.py56# ── Marketplace consistency ─────────────────────────────────────────────────COMMENT
MEDIUM⚡tools/tests/test_real_world.py100# ── Plugin source integrity ─────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_real_world.py204# ── Progressive-disclosure refactor integrity ────────────────────────────────COMMENT
MEDIUMtools/tests/test_real_world.py283# ── plugin.json integrity ─────────────────────────────────────────────────COMMENT
MEDIUM⚡tools/tests/test_round_trip.py62# ── Per-harness output checks ────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_round_trip.py424# ── Native-install manifests (always run; these are committed source) ─────────COMMENT
MEDIUMtools/tests/test_round_trip.py483# ── Context file size budgets (always run) ───────────────────────────────────COMMENT
MEDIUM⚡tools/tests/test_doc_gardener.py1295# ── Marketplace shape ────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py42# ── Stale artifacts ──────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py156# ── Generated YAML frontmatter ────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py287# ── Context file size ────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py307# ── Dead links ───────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py482# ── Codex skill cap ──────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py526# ── Marketplace consistency ──────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py583# ── Doc counts ───────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py846# ── Agent divergence ─────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py1253# ── Unreadable files ─────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py1342# ── Shared entry rule ────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_doc_gardener.py1363# ── $ARGUMENTS framing ───────────────────────────────────────────────────────COMMENT
MEDIUM⚡tools/tests/test_validate_generated.py370# ── Antigravity ──────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_validate_generated.py27# ── Codex ────────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_validate_generated.py96# ── Cursor ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_validate_generated.py150# ── Copilot ──────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_validate_generated.py245# ── OpenCode ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_validate_generated.py600# ── Pi ───────────────────────────────────────────────────────────────────────COMMENT
MEDIUM⚡tools/tests/test_adapters.py740# ── OpenCode ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py26# ── Codex ────────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py638# ── Cursor ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py1043# ── Antigravity ──────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py1337# ── Copilot ──────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py1521# ── Cross-cutting: emitted frontmatter must parse as YAML ────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py1783# ── Cross-cutting: capabilities consistency ──────────────────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py1881# ── Tool-reference rewriting ─────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py2003# ── Pi: capability matrix entries ────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py2049# ── Pi adapter ───────────────────────────────────────────────────────────────COMMENT
MEDIUM⚡tools/tests/test_cli_smoke.py345# ── Codex CLI ────────────────────────────────────────────────────────────────COMMENT
MEDIUM⚡tools/tests/test_cli_smoke.py399# ── Agent Skills installers: gh skill + npx skills ───────────────────────────COMMENT
MEDIUMtools/tests/test_cli_smoke.py83# ── OpenCode CLI ─────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_cli_smoke.py134# ── Antigravity CLI ──────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_cli_smoke.py177# ── Pi ───────────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_cli_smoke.py378# ── Claude Code CLI ──────────────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_cli_smoke.py510# ── Cross-CLI sanity: marketplace + adapter agreement ────────────────────────COMMENT
MEDIUMtools/adapters/codex.py55# ── TOML emission (hand-rolled; no toml writer in stdlib) ────────────────────COMMENT
MEDIUMtools/adapters/codex.py78# ── Skill rewriting ──────────────────────────────────────────────────────────COMMENT
MEDIUMtools/adapters/codex.py245# ── Adapter ──────────────────────────────────────────────────────────────────COMMENT
MEDIUMtools/adapters/codex.py357 # ── Internals ──────────────────────────────────────────────────────────COMMENT
MEDIUMtools/adapters/codex.py486 # ── Marketplace manifests (native install; reads source skills) ──────────COMMENT
MEDIUMtools/adapters/pi.py95 # ── Internals ──────────────────────────────────────────────────────────COMMENT
MEDIUMtools/adapters/opencode.py195 # ── Internals ──────────────────────────────────────────────────────────COMMENT
MEDIUMtools/adapters/antigravity.py117 # ── Internals ──────────────────────────────────────────────────────────COMMENT
71 more matches not shown…
Modern AI Meta-Vocabulary39 hits · 111 pts
SeverityFileLineSnippetContext
MEDIUM⚡tools/tests/test_adapters.py1013 # Body mentions 'Agent' only as a substring (class name in code) — no actual orchestration.COMMENT
MEDIUM⚡tools/tests/test_adapters.py1020 # Body explicitly mentions `subagent` as a standalone word — IS orchestration.COMMENT
MEDIUMtools/tests/test_adapters.py1040 assert "subtask: true" in delegate # genuine orchestration still detectedCODE
MEDIUMtools/adapters/opencode.py34# Detects orchestration intent in command bodies. Word-boundary match so identifiersCOMMENT
MEDIUMtools/adapters/opencode.py257 # Heuristic: if command orchestrates subagents, force isolation.COMMENT
MEDIUM…learning-ops/skills/recsys-pipeline-architect/SKILL.md106### RAG retrieval reranker (Python async)COMMENT
MEDIUM…nt/skills/microservices-patterns/references/details.md271# Saga orchestration for order fulfillmentCOMMENT
MEDIUM…/workflow-orchestration-patterns/references/details.md1# workflow-orchestration-patterns — detailed patterns and worked examplesCOMMENT
MEDIUM…opment/skills/saga-orchestration/references/details.md1# saga-orchestration — detailed sectionsCOMMENT
MEDIUMplugins/plugin-eval/tests/test_judge.py263 # triggering runs on haiku; orchestration/output_quality/scope on sonnet.COMMENT
MEDIUMplugins/plugin-eval/tests/test_judge.py145 {"unmeasured": True, "error": "x"}, # orchestration failedCODE
MEDIUM…ns/skills/helm-chart-scaffolding/references/details.md1# helm-chart-scaffolding — detailed patterns and worked examplesCOMMENT
MEDIUMplugins/agent-orchestration/agents/context-manager.md55### RAG & Information RetrievalCOMMENT
MEDIUMplugins/dotnet-contribution/agents/dotnet-architect.md3description: Expert .NET backend architect specializing in C#, ASP.NET Core, Entity Framework, Dapper, and enterprise apCODE
MEDIUM…t-contribution/skills/dotnet-backend-patterns/SKILL.md3description: Master C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applicatiCODE
MEDIUMplugins/llm-application-dev/agents/prompt-engineer.md93#### RAG & Knowledge IntegrationCOMMENT
MEDIUMplugins/llm-application-dev/agents/ai-engineer.md25### Advanced RAG SystemsCOMMENT
MEDIUMplugins/llm-application-dev/commands/prompt-optimize.md202### 6. RAG IntegrationSTRING
MEDIUMplugins/llm-application-dev/commands/langchain-agent.md66## RAG PipelineCOMMENT
MEDIUMplugins/llm-application-dev/commands/langchain-agent.md88### Advanced RAG PatternsCOMMENT
MEDIUM…llm-application-dev/skills/rag-implementation/SKILL.md6# RAG ImplementationCOMMENT
MEDIUM…llm-application-dev/skills/rag-implementation/SKILL.md93# RAG promptCOMMENT
MEDIUM…llm-application-dev/skills/rag-implementation/SKILL.md120# Build RAG graphCOMMENT
MEDIUM…on-dev/skills/rag-implementation/references/details.md3## Advanced RAG PatternsCOMMENT
MEDIUM…on-dev/skills/rag-implementation/references/details.md117# Build HyDE RAG graphCOMMENT
MEDIUM…on-dev/skills/rag-implementation/references/details.md327## Prompt Engineering for RAGCOMMENT
MEDIUM…on-dev/skills/rag-implementation/references/details.md351### Structured Output for RAGCOMMENT
MEDIUM…ills/prompt-engineering-patterns/references/details.md260### With RAG SystemsCOMMENT
MEDIUM…engineering-patterns/assets/prompt-template-library.md200### RAG TemplateCOMMENT
MEDIUM…lls/hybrid-search-implementation/references/details.md365### Template 4: Custom Hybrid RAG PipelineCOMMENT
MEDIUM…application-dev/skills/langchain-architecture/SKILL.md23langchain (1.2.x) # High-level orchestrationCODE
MEDIUM…application-dev/skills/langchain-architecture/SKILL.md26langgraph # Agent orchestration and state managementCODE
MEDIUM…ev/skills/langchain-architecture/references/details.md5### Pattern 1: RAG with LangGraphCOMMENT
MEDIUM…ev/skills/langchain-architecture/references/details.md215# Build multi-agent graphCOMMENT
MEDIUMplugins/context-management/agents/context-manager.md55### RAG & Information RetrievalCOMMENT
MEDIUMplugins/ship-mate/commands/ship.md116### `orchestrate`COMMENT
MEDIUMdocs/architecture.md286├── commands/ # Python project scaffoldingCODE
MEDIUMdocs/usage.md327# Component scaffoldingCOMMENT
MEDIUMdocs/usage.md338# Python project scaffoldingCOMMENT
Excessive Try-Catch Wrapping80 hits · 90 pts
SeverityFileLineSnippetContext
MEDIUMtools/generate.py249 print(f"Error: {err}", file=sys.stderr)CODE
MEDIUMtools/generate.py277 print(f"Error: plugins directory not found at {PLUGINS_DIR}", file=sys.stderr)CODE
LOWtools/generate.py304 except Exception as e: # noqa: BLE001 — we want to aggregate, not crashCODE
LOWtools/generate.py321 except Exception as e: # noqa: BLE001CODE
LOWtools/yt-design-extractor/yt-design-extractor.py271 except Exception as e:CODE
LOWtools/yt-design-extractor/yt-design-extractor.py281 except Exception as e:CODE
LOWtools/yt-design-extractor/yt-design-extractor.py327 except Exception as e:CODE
LOWtools/yt-design-extractor/yt-design-extractor.py353 except Exception as e:CODE
LOW…essing/skills/stripe-integration/references/details.md274 except Exception as e:CODE
LOW…essing/skills/paypal-integration/references/details.md289 except Exception as e:CODE
LOW…nt/skills/microservices-patterns/references/details.md343 except Exception as e:CODE
LOW…nt/skills/microservices-patterns/references/details.md353 except Exception as e:CODE
LOW…nt/skills/microservices-patterns/references/details.md439 except Exception as e:CODE
LOW…lls/saga-orchestration/references/advanced-patterns.md443 except Exception as e:CODE
LOW…ls/temporal-python-testing/resources/replay-testing.md339 except Exception as e:CODE
LOW…kills/temporal-python-testing/resources/local-setup.md114 except Exception as e:CODE
LOW…pment/skills/cqrs-implementation/references/details.md394 except Exception as e:CODE
LOW…per-essentials/skills/error-handling-patterns/SKILL.md104 except Exception as e:CODE
LOW…s/skills/error-handling-patterns/references/details.md55 except Exception as e:CODE
LOW…s/skills/error-handling-patterns/references/details.md391 except Exception as e:CODE
LOW…s/skills/error-handling-patterns/references/details.md490 except Exception as e:CODE
LOW…s/skills/error-handling-patterns/references/details.md514 except Exception:CODE
LOW…eloper-essentials/skills/debugging-strategies/SKILL.md238except Exception:CODE
LOWplugins/plugin-eval/scripts/eval_all.py117 except Exception as exc:CODE
LOWplugins/plugin-eval/src/plugin_eval/corpus.py60 except Exception:CODE
LOW…gins/plugin-eval/src/plugin_eval/layers/monte_carlo.py101 except Exception: # noqa: BLE001 — a failed run is recorded as errored, not fatalCODE
LOW…gins/plugin-eval/src/plugin_eval/layers/monte_carlo.py217 except Exception:CODE
LOWplugins/plugin-eval/src/plugin_eval/layers/judge.py122 except Exception as exc: # noqa: BLE001 — judge is best-effort; degrade to unmeasuredCODE
LOW…liance/skills/gdpr-data-handling/references/details.md197 except Exception as e:CODE
LOW…liance/skills/gdpr-data-handling/references/details.md240 except Exception as e:CODE
LOW…folding/skills/fastapi-templates/references/details.md87 except Exception:CODE
LOW…lopment/skills/python-resilience/references/details.md91 except Exception as e:CODE
LOW…lopment/skills/python-resilience/references/details.md138 except Exception as e:CODE
LOW…lopment/skills/python-resilience/references/details.md171 except Exception as e:CODE
MEDIUM…lopment/skills/python-resilience/references/details.md168def wrapper(*args, **kwargs) -> T:CODE
LOW…nt/skills/python-background-jobs/references/details.md17 except Exception as e:CODE
LOW…ython-development/skills/python-anti-patterns/SKILL.md138except Exception:CODE
LOW…ython-development/skills/python-anti-patterns/SKILL.md178 except Exception as e:CODE
LOW…ent/skills/python-error-handling/references/details.md121 except Exception as e:CODE
LOW…ent/skills/python-error-handling/references/details.md164 except Exception as e:CODE
LOW…development/skills/python-resource-management/SKILL.md180 except Exception:CODE
LOW…ython-development/skills/python-observability/SKILL.md119 except Exception as e:CODE
LOW…ment/skills/python-observability/references/details.md59 except Exception as e:CODE
LOW…ment/skills/python-observability/references/details.md116 except Exception as e:CODE
MEDIUM…thon-development/skills/async-python-patterns/SKILL.md182 print(f"Error: {e}")CODE
LOW…ent/skills/async-python-patterns/references/details.md219 except Exception as e:CODE
LOW⚡…tx-reference-deck-analysis/scripts/validate_package.py84 except Exception as exc:CODE
LOW⚡…tx-reference-deck-analysis/scripts/validate_package.py92 except Exception as exc:CODE
LOW⚡…tx-reference-deck-analysis/scripts/validate_package.py100 except Exception:CODE
LOW…tx-reference-deck-analysis/scripts/validate_package.py133 except Exception as exc:CODE
MEDIUMplugins/code-documentation/commands/code-explain.md419 print("Error: Cannot divide by zero!")STRING
MEDIUMplugins/code-documentation/commands/code-explain.md422 print("Error: Please provide numbers only!")STRING
MEDIUMplugins/code-documentation/commands/code-explain.md706 print("Something went wrong")CODE
LOWplugins/code-documentation/commands/code-explain.md713except Exception as e:CODE
LOWplugins/error-debugging/commands/error-analysis.md655 except Exception as e:CODE
LOWplugins/error-debugging/commands/error-analysis.md886 except Exception as e:CODE
LOWplugins/team-collaboration/commands/issue.md368 except Exception as e:CODE
LOWplugins/security-scanning/commands/security-sast.md435 except Exception as e:CODE
LOW…ns/security-scanning/commands/security-dependencies.md124 except Exception as e:CODE
LOW…ns/security-scanning/commands/security-dependencies.md155 except Exception as e:CODE
20 more matches not shown…
Unused Imports68 hits · 66 pts
SeverityFileLineSnippetContext
LOWtools/generate.py8CODE
LOWtools/doc_gardener.py23CODE
LOWtools/doc_gardener.py33CODE
LOWtools/install_pi.py12CODE
LOWtools/install_opencode.py4CODE
LOWtools/validate_generated.py14CODE
LOWtools/check_agent_name_collisions.py4CODE
LOWtools/install_copilot.py4CODE
LOWtools/install_antigravity.py4CODE
LOWtools/tests/test_install_copilot.py3CODE
LOWtools/tests/conftest.py3CODE
LOWtools/tests/test_real_world.py10CODE
LOWtools/tests/test_round_trip.py12CODE
LOWtools/tests/test_install_pi.py3CODE
LOWtools/tests/test_install_antigravity.py3CODE
LOWtools/tests/test_doc_gardener.py3CODE
LOWtools/tests/test_install_opencode.py3CODE
LOWtools/tests/test_validate_generated.py3CODE
LOWtools/tests/test_adapters.py8CODE
LOWtools/tests/test_cli_smoke.py19CODE
LOWtools/adapters/codex.py18CODE
LOWtools/adapters/copilot.py3CODE
LOWtools/adapters/__init__.py8CODE
LOWtools/adapters/__init__.py8CODE
LOWtools/adapters/__init__.py8CODE
LOWtools/adapters/__init__.py8CODE
LOWtools/adapters/__init__.py8CODE
LOWtools/adapters/__init__.py8CODE
LOWtools/adapters/__init__.py8CODE
LOWtools/adapters/__init__.py8CODE
LOWtools/adapters/__init__.py8CODE
LOWtools/adapters/__init__.py19CODE
LOWtools/adapters/__init__.py19CODE
LOWtools/adapters/pi.py26CODE
LOWtools/adapters/opencode.py17CODE
LOWtools/adapters/capabilities.py8CODE
LOWtools/adapters/antigravity.py28CODE
LOWtools/adapters/base.py3CODE
LOWtools/adapters/cursor.py15CODE
LOW…ills/api-design-principles/assets/rest-api-template.py6CODE
LOWplugins/plugin-eval/tests/test_parser.py5CODE
LOWplugins/plugin-eval/tests/test_parser.py5CODE
LOWplugins/plugin-eval/tests/test_parser.py5CODE
LOWplugins/plugin-eval/tests/test_engine.py3CODE
LOWplugins/plugin-eval/tests/test_corpus.py3CODE
LOWplugins/plugin-eval/tests/test_harness_portability.py5CODE
LOWplugins/plugin-eval/tests/test_models.py4CODE
LOWplugins/plugin-eval/tests/test_models.py4CODE
LOWplugins/plugin-eval/tests/test_models.py4CODE
LOWplugins/plugin-eval/tests/test_models.py4CODE
LOWplugins/plugin-eval/scripts/eval_all.py20CODE
LOWplugins/plugin-eval/src/plugin_eval/elo.py3CODE
LOWplugins/plugin-eval/src/plugin_eval/models.py3CODE
LOWplugins/plugin-eval/src/plugin_eval/reporter.py3CODE
LOWplugins/plugin-eval/src/plugin_eval/parser.py3CODE
LOWplugins/plugin-eval/src/plugin_eval/engine.py3CODE
LOWplugins/plugin-eval/src/plugin_eval/cli.py3CODE
LOWplugins/plugin-eval/src/plugin_eval/stats.py3CODE
LOWplugins/plugin-eval/src/plugin_eval/corpus.py3CODE
LOWplugins/plugin-eval/src/plugin_eval/snapshot.py9CODE
8 more matches not shown…
Magic Placeholder Names8 hits · 55 pts
SeverityFileLineSnippetContext
HIGH…pi-design-principles/references/rest-best-practices.md249X-API-Key: your-api-key-hereCODE
HIGH⚡plugins/code-documentation/commands/doc-generate.md545headers = {{"Authorization": "Bearer YOUR_API_KEY"}}CODE
HIGH⚡plugins/code-documentation/commands/doc-generate.md555 headers: {{'Authorization': 'Bearer YOUR_API_KEY'}}CODE
HIGH⚡plugins/code-documentation/commands/doc-generate.md565 -H "Authorization: Bearer YOUR_API_KEY"CODE
HIGH⚡…gins/documentation-generation/commands/doc-generate.md545headers = {{"Authorization": "Bearer YOUR_API_KEY"}}CODE
HIGH⚡…gins/documentation-generation/commands/doc-generate.md555 headers: {{'Authorization': 'Bearer YOUR_API_KEY'}}CODE
HIGH⚡…gins/documentation-generation/commands/doc-generate.md565 -H "Authorization: Bearer YOUR_API_KEY"CODE
HIGH…ev/skills/langchain-architecture/references/details.md306os.environ["LANGCHAIN_API_KEY"] = "your-api-key"CODE
AI Slop Vocabulary17 hits · 54 pts
SeverityFileLineSnippetContext
MEDIUMtools/generate.py30# Per-harness output targets used by both `--clean` and `--prune`.COMMENT
MEDIUMtools/generate.py150 # Files to consider per-harness. We only prune files inside the adapter's own outputCOMMENT
MEDIUMtools/doc_gardener.py59# calls the agent total "subagents" in its cross-harness section, and a total of oneCOMMENT
MEDIUMtools/validate_generated.py871 # Sort findings by (severity priority, harness, path) for triage-friendly output.COMMENT
MEDIUMtools/install_copilot.py110 # src is like .copilot/commands/comprehensive-review, symlink to ~/.copilot/comprehensive-review/commandsCOMMENT
MEDIUM⚡tools/tests/test_round_trip.py62# ── Per-harness output checks ────────────────────────────────────────────────COMMENT
MEDIUMtools/tests/test_adapters.py1526# valid source into an artifact the target harness cannot load.COMMENT
MEDIUM⚡tools/tests/test_cli_smoke.py401# Neither is a harness. Both are distribution channels that read the source treeCOMMENT
MEDIUMtools/adapters/codex.py599 # repo root as the canonical cross-harness context file. `emit_global` aboveCOMMENT
MEDIUMtools/adapters/capabilities.py214# Tool name maps for body rewriting (CamelCase -> harness-native)COMMENT
MEDIUMtools/adapters/capabilities.py300# Model alias map: bare Claude alias -> full provider-prefixed ID per harness.COMMENT
MEDIUMtools/adapters/capabilities.py301# Targets verified against each harness's published model catalog 2026-07:COMMENT
MEDIUM…gin-eval/src/plugin_eval/layers/harness_portability.py60# Context file line cap (per harness-engineering principle)COMMENT
MEDIUM…kills/helm-chart-scaffolding/scripts/validate-chart.sh139# 7. Check for security best practicesCOMMENT
MEDIUM…lls/dotnet-backend-patterns/assets/service-template.cs2// This template demonstrates best practices for building robust servicesCOMMENT
MEDIUM.github/workflows/code-quality.yml83 # Lints top-level guides (README, AGENTS, ARCHITECTURE, CLAUDE, per-harnessCOMMENT
MEDIUM.github/workflows/validate.yml226 # Real-CLI subprocess tests: invokes the actual harness binaries against ourCOMMENT
Fake / Example Data49 hits · 52 pts
SeverityFileLineSnippetContext
LOWtools/tests/test_adapters.py700 assert manifest["author"] == {"name": "Jane Doe", "email": "jane@example.com"}CODE
LOW…mobile-android-design/references/android-navigation.md277 "John Doe",CODE
LOW…ills/api-design-principles/assets/rest-api-template.py153 email="user@example.com",CODE
LOW…r-essentials/skills/sql-optimization-patterns/SKILL.md31EXPLAIN SELECT * FROM users WHERE email = 'user@example.com';CODE
LOW…r-essentials/skills/sql-optimization-patterns/SKILL.md35SELECT * FROM users WHERE email = 'user@example.com';CODE
LOW⚡…r-essentials/skills/sql-optimization-patterns/SKILL.md111SELECT * FROM users WHERE LOWER(email) = 'user@example.com';CODE
LOW⚡…r-essentials/skills/sql-optimization-patterns/SKILL.md116SELECT * FROM users WHERE LOWER(email) = 'user@example.com';CODE
LOW⚡…r-essentials/skills/sql-optimization-patterns/SKILL.md119SELECT * FROM users WHERE email = 'user@example.com';CODE
LOW…skills/sql-optimization-patterns/references/details.md282WHERE email = 'user@example.com';STRING
LOW…eloper-essentials/skills/e2e-testing-patterns/SKILL.md84cy.getByLabel("Email address").type("user@example.com");CODE
LOW…eloper-essentials/skills/e2e-testing-patterns/SKILL.md85cy.get('[data-testid="email-input"]').type("user@example.com");CODE
LOW…ials/skills/e2e-testing-patterns/references/details.md80 await loginPage.login("user@example.com", "password123");CODE
LOW…ials/skills/e2e-testing-patterns/references/details.md130 email: "admin@example.com",CODE
LOW…ials/skills/e2e-testing-patterns/references/details.md291cy.login("user@example.com", "password");CODE
LOW…n/skills/postgresql-table-design/references/details.md75- **Expression index**: the expression must match the WHERE clause exactly: `WHERE LOWER(email) = 'user@example.com'`.CODE
LOW…t/skills/python-testing-patterns/references/details.md153 ("user@example.com", True),CODE
LOW…t/skills/python-testing-patterns/references/details.md222 mock_response.json.return_value = {"id": 1, "name": "John Doe"}CODE
LOW…t/skills/python-testing-patterns/references/details.md229 assert user["name"] == "John Doe"CODE
LOW…t/skills/python-testing-patterns/references/details.md250 mock_post.return_value.json.return_value = {"id": 2, "name": "Jane Doe"}CODE
LOW…t/skills/python-testing-patterns/references/details.md253 user_data = {"name": "Jane Doe", "email": "jane@example.com"}CODE
LOW…hon-development/skills/python-background-jobs/SKILL.md52send_email.delay("user@example.com", "Welcome!", "Thanks for signing up")CODE
LOW…nt/skills/python-background-jobs/references/details.md110job = queue.enqueue(send_email, "user@example.com", "Subject", "Body")CODE
LOW…thon-development/skills/python-error-handling/SKILL.md147 email="user@example.com",CODE
LOW…rformance-optimization/references/advanced-patterns.md253SELECT * FROM users WHERE email = 'user@example.com';STRING
LOW…rformance-optimization/references/advanced-patterns.md257SELECT * FROM users WHERE email = 'user@example.com';STRING
LOW…n/skills/openapi-spec-generation/references/details.md441 name: "John Doe"CODE
LOW…i-spec-generation/references/code-first-and-tooling.md55 "email": "user@example.com",CODE
LOW…i-spec-generation/references/code-first-and-tooling.md56 "name": "John Doe",CODE
LOW…i-spec-generation/references/code-first-and-tooling.md302 name: "John Doe",CODE
LOWplugins/team-collaboration/commands/issue.md271 await page.fill('[data-testid="email-input"]', "user@example.com");CODE
LOW…mpt-engineering-patterns/assets/few-shot-examples.json75 "name": "Jane Doe",CODE
LOW…framework-migration/skills/dependency-upgrade/SKILL.md261 cy.get('input[name="email"]').type("user@example.com");CODE
LOW…sting-patterns/references/advanced-testing-patterns.md35 name: "John Doe",CODE
LOW…sting-patterns/references/advanced-testing-patterns.md55 name: "John Doe",CODE
LOW…sting-patterns/references/advanced-testing-patterns.md70 name: "John Doe",CODE
LOW…sting-patterns/references/advanced-testing-patterns.md89 name: "John Doe",CODE
LOW…sting-patterns/references/advanced-testing-patterns.md102 name: "John Doe",CODE
LOW…sting-patterns/references/advanced-testing-patterns.md120 name: "John Doe",CODE
LOW⚡…sting-patterns/references/advanced-testing-patterns.md189 name: "John Doe",CODE
LOW⚡…sting-patterns/references/advanced-testing-patterns.md195 expect(user.name).toBe("John Doe");CODE
LOW⚡…sting-patterns/references/advanced-testing-patterns.md201 name: "John Doe",CODE
LOW⚡…sting-patterns/references/advanced-testing-patterns.md209 expect(user?.name).toBe("John Doe");CODE
LOW⚡…sting-patterns/references/advanced-testing-patterns.md281 fireEvent.change(nameInput, { target: { value: 'John Doe' } });CODE
LOW⚡…sting-patterns/references/advanced-testing-patterns.md284 expect(nameInput.value).toBe('John Doe');CODE
LOW⚡…sting-patterns/references/advanced-testing-patterns.md293 target: { value: 'John Doe' },CODE
LOW⚡…sting-patterns/references/advanced-testing-patterns.md301 name: 'John Doe',CODE
LOW…sting-patterns/references/advanced-testing-patterns.md407 const user = createUserFixture({ name: "John Doe" });CODE
LOW…sting-patterns/references/advanced-testing-patterns.md430 name: 'John Doe',CODE
LOW…kills/modern-javascript-patterns/references/details.md70 name: "John Doe",CODE
Docstring Block Structure7 hits · 35 pts
SeverityFileLineSnippetContext
HIGH…s/python-development/skills/python-code-style/SKILL.md211Process items concurrently using a worker pool. Processes each item in the batch using the configured number of STRING
HIGH…thon-development/skills/python-error-handling/SKILL.md91Parse string to OutputFormat enum. Args: value: Format string from user input. Returns: ValidaSTRING
HIGHplugins/codebase-cleanup/commands/refactor-clean.md765 Calculate the total discount for an order based on customer tier and order value. Args: order: The ordSTRING
HIGHplugins/code-documentation/commands/doc-generate.md429 def {func.__name__}({", ".join(params)}){return_type}: """ Brief description of {func.__name__} Args: STRING
HIGH…gins/documentation-generation/commands/doc-generate.md429 def {func.__name__}({", ".join(params)}){return_type}: """ Brief description of {func.__name__} Args: STRING
HIGHplugins/code-refactoring/commands/refactor-clean.md765 Calculate the total discount for an order based on customer tier and order value. Args: order: The ordSTRING
HIGHplugins/conductor/templates/code_styleguides/python.md184Calculate the discounted price. Args: price: Original price of the item. discount_percent: DiscountSTRING
Cross-Language Confusion5 hits · 32 pts
SeverityFileLineSnippetContext
HIGH⚡tools/tests/test_doc_gardener.py740 (tmp_path / ".claude-plugin" / "marketplace.json").write_text('{"plugins": null}')CODE
HIGH⚡tools/tests/test_doc_gardener.py809 (tmp_path / ".claude-plugin" / "marketplace.json").write_text('{"plugins": [null, null]}')CODE
HIGH⚡tools/tests/test_doc_gardener.py1305 (mp / "marketplace.json").write_text('{"plugins": [null]}')CODE
HIGHtools/adapters/base.py260# YAML 1.1 implicit booleans/null, which must be quoted to avoid loading as bool/None.COMMENT
HIGHtools/yt-design-extractor/yt-design-extractor.py15 cd tools/yt-design-extractor && uv run python yt-design-extractor.py <youtube_url> [options]STRING
Deep Nesting25 hits · 25 pts
SeverityFileLineSnippetContext
LOWtools/generate.py138CODE
LOWtools/doc_gardener.py165CODE
LOWtools/doc_gardener.py725CODE
LOWtools/doc_gardener.py826CODE
LOWtools/validate_generated.py345CODE
LOWtools/validate_generated.py382CODE
LOWtools/validate_generated.py530CODE
LOWtools/validate_generated.py661CODE
LOWtools/install_copilot.py136CODE
LOWtools/adapters/codex.py85CODE
LOWtools/adapters/codex.py137CODE
LOWtools/adapters/copilot.py20CODE
LOWtools/adapters/pi.py56CODE
LOWtools/adapters/opencode.py133CODE
LOWtools/adapters/antigravity.py81CODE
LOWtools/adapters/base.py41CODE
LOWtools/adapters/base.py199CODE
LOWtools/adapters/cursor.py153CODE
LOWtools/yt-design-extractor/yt-design-extractor.py286CODE
LOWplugins/plugin-eval/src/plugin_eval/engine.py344CODE
LOWplugins/plugin-eval/src/plugin_eval/corpus.py37CODE
LOWplugins/plugin-eval/src/plugin_eval/layers/static.py256CODE
LOWplugins/plugin-eval/src/plugin_eval/layers/static.py311CODE
LOWplugins/plugin-eval/src/plugin_eval/layers/_sdk.py23CODE
LOW…tx-reference-deck-analysis/scripts/validate_package.py75CODE
Empty Error Handlers3 hits · 15 pts
SeverityFileLineSnippetContext
HIGHtools/yt-design-extractor/yt-design-extractor.py47except ImportError:CODE
HIGHtools/yt-design-extractor/yt-design-extractor.py54except ImportError:CODE
HIGH…gins/plugin-eval/src/plugin_eval/layers/monte_carlo.py217except Exception:CODE
Over-Commented Block15 hits · 15 pts
SeverityFileLineSnippetContext
LOW…veloper-essentials/skills/monorepo-management/SKILL.md61npx create-turbo@latest my-monorepoCOMMENT
LOW…ls/skills/git-advanced-workflows/references/details.md1# git-advanced-workflows — detailed patterns and worked examplesCOMMENT
LOWplugins/protect-mcp/test/run-tests.sh1#!/usr/bin/env bashCOMMENT
LOW…lls/uv-package-manager/references/advanced-patterns.md1# UV Package Manager — Advanced ReferenceCOMMENT
LOW…/k8s-manifest-generator/assets/configmap-template.yaml261 regex: ([^:]+)(?::\d+)?;(\d+)COMMENT
LOW…/k8s-manifest-generator/assets/configmap-template.yaml281# 3. Mount specific keys as files:COMMENT
LOW…k8s-manifest-generator/assets/deployment-template.yaml201 # Image pull secrets (if using private registry)COMMENT
LOWplugins/error-debugging/commands/error-analysis.md1121# Find correlation between errors and deployments (DataDog)COMMENT
LOWplugins/team-collaboration/commands/standup-notes.md541# 1. Generate draft standup from data sourcesCOMMENT
LOW…s/reverse-engineering/skills/memory-forensics/SKILL.md181// Memory protection flagsCOMMENT
LOW…skills/anti-reversing-techniques/references/details.md241COMMENT
LOW…-ops/skills/spark-training-gotchas/assets/preflight.sh1#!/usr/bin/env bashCOMMENT
LOWplugins/error-diagnostics/commands/error-analysis.md1121# Find correlation between errors and deployments (DataDog)COMMENT
LOW.github/workflows/mlops.yml1name: MLOps (lab baseline)COMMENT
LOW.github/workflows/claude.yml101 # See AGENTS.md for the canonical command reference.COMMENT
Modern Structural Boilerplate2 hits · 2 pts
SeverityFileLineSnippetContext
LOWtools/adapters/__init__.py21__all__ = [CODE
LOWplugins/plugin-eval/src/plugin_eval/corpus.py99 def update_rating(self, name: str, new_rating: float) -> None:CODE
Redundant / Tautological Comments1 hit · 2 pts
SeverityFileLineSnippetContext
LOW…kills/helm-chart-scaffolding/scripts/validate-chart.sh30# Check if Helm is installedCOMMENT
Example Usage Blocks1 hit · 2 pts
SeverityFileLineSnippetContext
LOW…prompt-engineering-patterns/scripts/optimize-prompt.py241 # Example usageCOMMENT