Repository Analysis

code-yeongyu/oh-my-openagent

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

4.0 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of code-yeongyu/oh-my-openagent, a TypeScript project with 68,473 GitHub stars. SynthScan v2.0 examined 1,168,868 lines of code across 8431 source files, recording 3418 pattern matches distributed across 22 syntactic categories. The overall adjusted score of 4.0 places this repository in the Likely human-written band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

4.0
Adjusted Score
4.0
Raw Score
100%
Time Factor
2026-08-28
Last Push
68.5K
Stars
TypeScript
Language
1.2M
Lines of Code
8.4K
Files
3.4K
Pattern Hits
2026-08-29
Scan Date
0.01
HC Hit Rate

What These Metrics Mean

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

Score History

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

Severity Breakdown

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

CRITICAL 2HIGH 41MEDIUM 462LOW 2913

Directory Score Breakdown

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

Pattern Findings

The scanner identified 3418 distinct pattern matches across 22 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

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

Hyper-Verbose Identifiers2369 hits · 2459 pts
SeverityFileLineSnippetContext
LOWtest-setup.ts77function cleanupRulesInjectorStorage(): void {CODE
LOWpostinstall.test.ts20function runPostinstallInFixtureEnv(): PostinstallRun {CODE
LOW.omo/evidence/20260810-omo-native-telemetry/f4.md59377:export function createOmoNativeProductConfig(): TelemetryProductConfig & { readonly disableGeoip: true } {CODE
LOW…/evidence/20260809-omo-agent-toolkit-rename/task-4.txt321@@ -90 +90 @@ function buildCompletedLegacyGoalRemediation(goal: UlwLoopItem): string {CODE
LOW…/evidence/20260809-omo-agent-toolkit-rename/task-4.txt333@@ -98 +98 @@ function hasSteeringDirectiveMarker(prompt: string): boolean {CODE
LOW…/evidence/20260809-omo-agent-toolkit-rename/task-4.txt339@@ -179 +179 @@ export function parseUlwLoopSteeringDirective(text: string): UlwLoopSteeringPropCODE
LOW.omo/evidence/20260727-fix-6141/green-6141.txt28 export function isHephaestusSupportedModel(model: string | undefined): boolean {CODE
LOW.omo/evidence/20260727-fix-6141/red-6141.txt5253 | function assertHephaestusSupportedModel(model: string | undefined): void {CODE
LOW…o/evidence/20260727-fix-6141/negative-control-6141.txt5353 | function assertHephaestusSupportedModel(model: string | undefined): void {CODE
LOW…-remove-prompt-contract-tests/classification_bundle.py103def _parse_classification_text(text: str, source: Path) -> ClassificationDocument:CODE
LOW…-remove-prompt-contract-tests/classification_bundle.py132def dispositions_from_document(CODE
LOW…-remove-prompt-contract-tests/classification_bundle.py158def load_direct_classification(path: Path) -> dict[str, BundleDisposition]:CODE
LOW…-remove-prompt-contract-tests/classification_bundle.py166def load_classification_bundle(CODE
LOW…move-prompt-contract-tests/test_node_assert_scanner.py14def test_node_assert_assertions_are_detected_in_javascript_tests(tmp_path: Path) -> None:CODE
LOW…move-prompt-contract-tests/test_node_assert_scanner.py91def test_sync_skills_codex_compatibility_node_assertions_yield_candidates() -> None:STRING
LOW…move-prompt-contract-tests/test_node_assert_scanner.py104def test_callable_node_assert_aliases_only_emit_instruction_assertions(tmp_path: Path) -> None:STRING
LOW…remove-prompt-contract-tests/audit_prompt_contracts.py73def load_indexed_classification(path: Path) -> dict[str, Disposition]:CODE
LOW…remove-prompt-contract-tests/audit_prompt_contracts.py87def load_requested_classification(path: Path) -> dict[str, Disposition]:CODE
LOW…-remove-prompt-contract-tests/test_snapshot_scanner.py14def test_builtin_category_snapshot_with_prompt_payload_yields_candidate(tmp_path: Path) -> None:CODE
LOW…-remove-prompt-contract-tests/test_snapshot_scanner.py44def test_opaque_snapshot_subjects_always_yield_candidates(tmp_path: Path) -> None:CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py59def test_project_skill_includes_and_negative_assertion_are_detected(CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py74def test_team_mode_headings_resolve_through_for_of_loop(CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py87def test_playwright_marker_array_is_detected_through_order_helper(CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py102def test_memory_assets_and_seeds_derived_contracts_are_detected(CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py121def test_category_resolver_direct_prompt_and_prompt_assertions_are_detected(CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py155def test_tracked_tests_enumerates_only_tracked_test_files(tmp_path: Path) -> None:CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py174def test_allowed_entry_requires_non_empty_rationale_and_category(CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py198def test_indexed_classification_rejects_hash_mismatch(tmp_path: Path) -> None:CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py217def test_indexed_classification_loads_only_active_fingerprints(tmp_path: Path) -> None:CODE
LOWbin/oh-my-opencode.js111function maybeRunLazyCodexNodeInstaller(invocationName) {CODE
LOWbin/oh-my-opencode.test.ts231async function writeNodeInstallerFixture(root: string): Promise<void> {CODE
LOWbin/oh-my-opencode.test.ts247async function canonicalizePackageRootCapture(fixture: { readonly captureDir: string }): Promise<string> {CODE
LOWbin/platform.d.ts8export declare function getPlatformPackageCandidates(options: {CODE
LOWbin/platform.d.ts20export declare function resolvePlatformPackageBaseName(wrapperPackageName: string): string;CODE
LOWbin/version-mismatch.js37export function detectPlatformBinaryMismatch({ mainVersion, platformVersion, platformPackage }) {CODE
LOWbin/platform.js19export function resolvePlatformPackageBaseName(wrapperPackageName) {CODE
LOWbin/platform.js50export function getPlatformPackageCandidates({ platform, arch, libcFamily, preferBaseline = false, packageBaseName = "ohCODE
LOWbin/platform.js67function getBaselinePlatformPackage({ platform, arch, libcFamily, packageBaseName = "oh-my-opencode" }) {CODE
LOW…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
LOW…eration-1/eval-5/without_skill/outputs/code-changes.md207export async function processApplyPatchEditsWithCli(CODE
LOW…/iteration-1/eval-5/with_skill/outputs/code-changes.md118export async function processApplyPatchEditsWithCli(CODE
LOW…/iteration-1/eval-5/with_skill/outputs/code-changes.md132export async function processApplyPatchEditsWithCli(CODE
LOW…eration-1/eval-3/without_skill/outputs/code-changes.md116function renderPlanAgentCategoryRows(categories: AvailableCategory[]): string[] {CODE
LOW…eration-1/eval-3/without_skill/outputs/code-changes.md133export function buildPlanAgentSkillsSection(CODE
LOW…eration-1/eval-3/without_skill/outputs/code-changes.md156export function buildPlanAgentSystemPrepend(CODE
LOW…/iteration-1/eval-3/with_skill/outputs/code-changes.md113function renderPlanAgentCategoryRows(categories: AvailableCategory[]): string[] {CODE
LOW…/iteration-1/eval-3/with_skill/outputs/code-changes.md130export function buildPlanAgentSkillsSection(CODE
LOW…/iteration-1/eval-3/with_skill/outputs/code-changes.md153export function buildPlanAgentSystemPrepend(CODE
LOWtests/hashline/test-environment.ts21export function parseHashlineTestEnvironment(CODE
LOW…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
LOW…eration-1/eval-5/without_skill/outputs/code-changes.md207export async function processApplyPatchEditsWithCli(CODE
LOW…/iteration-1/eval-5/with_skill/outputs/code-changes.md118export async function processApplyPatchEditsWithCli(CODE
LOW…/iteration-1/eval-5/with_skill/outputs/code-changes.md132export async function processApplyPatchEditsWithCli(CODE
LOW…eration-1/eval-3/without_skill/outputs/code-changes.md116function renderPlanAgentCategoryRows(categories: AvailableCategory[]): string[] {CODE
LOW…eration-1/eval-3/without_skill/outputs/code-changes.md133export function buildPlanAgentSkillsSection(CODE
LOW…eration-1/eval-3/without_skill/outputs/code-changes.md156export function buildPlanAgentSystemPrepend(CODE
LOW…/iteration-1/eval-3/with_skill/outputs/code-changes.md113function renderPlanAgentCategoryRows(categories: AvailableCategory[]): string[] {CODE
LOW…/iteration-1/eval-3/with_skill/outputs/code-changes.md130export function buildPlanAgentSkillsSection(CODE
LOW…/iteration-1/eval-3/with_skill/outputs/code-changes.md153export function buildPlanAgentSystemPrepend(CODE
LOWdocs/reference/prompt-async-gate-rfc.md147export function releasePromptAsyncReservation(CODE
2309 more matches not shown…
Modern AI Meta-Vocabulary260 hits · 618 pts
SeverityFileLineSnippetContext
MEDIUMchanges.md154### Tool orchestration and observabilityCOMMENT
MEDIUMAGENTS.md68OpenCode plugin (npm: `oh-my-opencode`, dual-published as `oh-my-openagent` during the rename transition) extending OpenCODE
MEDIUMCLAUDE.md68OpenCode plugin (npm: `oh-my-opencode`, dual-published as `oh-my-openagent` during the rename transition) extending OpenCODE
MEDIUM…vidence/20260818-mass-ulw-usage-patterns/qa-output.txt7(pass) OMO Senpi scoped skill sync > #given codex-derived and native skill roots #when scanned #then no Codex or multi-aCODE
MEDIUM…vidence/20260818-mass-ulw-usage-patterns/qa-output.txt12(pass) OMO Senpi scoped skill sync > #given ported orchestration skills #when scanned #then no foreign-harness delegatioCODE
MEDIUM…825-dag-tui-paused-status-honesty/green-test-senpi.txt124(pass) OMO Senpi scoped skill sync > #given codex-derived and native skill roots #when scanned #then no Codex or multi-aCODE
MEDIUM…825-dag-tui-paused-status-honesty/green-test-senpi.txt129(pass) OMO Senpi scoped skill sync > #given ported orchestration skills #when scanned #then no foreign-harness delegatioCODE
MEDIUM…825-dag-tui-paused-status-honesty/green-test-senpi.txt315(pass) insertSenpiCompatibilityGuidance > #given content with no opencode orchestration calls #when processed #then it iCODE
MEDIUM…825-dag-tui-paused-status-honesty/green-test-senpi.txt1450(pass) omo-senpi lsp post-edit diagnostics > #given many mutated files #when post-edit diagnostics run #then shared orchCODE
MEDIUM…825-dag-tui-paused-status-honesty/green-test-senpi.txt1801(pass) omo-senpi skill-pointers component > #given a matching interactive prompt > #when the mass-ulw pointer is injecteCODE
MEDIUM…825-dag-tui-paused-status-honesty/green-test-senpi.txt3396(pass) selectRegistryFallbackModels > #given priced chat models > #when two models share a price #then the larger contexCODE
MEDIUM…825-dag-tui-paused-status-honesty/green-test-senpi.txt3398(pass) selectRegistryFallbackModels > #given models reflection cannot use > #when the context window is below the reflecCODE
MEDIUM…ce/omo-senpi-adapter/memory-v2/task-9/package-gate.txt134(pass) OMO Senpi scoped skill sync > #given codex-derived and native skill roots #when scanned #then no Codex or multi-aCODE
MEDIUM…ce/omo-senpi-adapter/memory-v2/task-9/package-gate.txt136(pass) OMO Senpi scoped skill sync > #given shared skill roots with opencode orchestration #when inspected #then a SenpiCODE
MEDIUM…ce/omo-senpi-adapter/memory-v2/task-9/package-gate.txt140(pass) OMO Senpi scoped skill sync > #given ported orchestration skills #when scanned #then no foreign-harness delegatioCODE
MEDIUM…ce/omo-senpi-adapter/memory-v2/task-9/package-gate.txt958(pass) omo-senpi lsp post-edit diagnostics > #given many mutated files #when post-edit diagnostics run #then shared orchCODE
MEDIUM…e/omo-senpi-adapter/memory-v2/task-24/package-gate.txt134(pass) OMO Senpi scoped skill sync > #given codex-derived and native skill roots #when scanned #then no Codex or multi-aCODE
MEDIUM…e/omo-senpi-adapter/memory-v2/task-24/package-gate.txt136(pass) OMO Senpi scoped skill sync > #given shared skill roots with opencode orchestration #when inspected #then a SenpiCODE
MEDIUM…e/omo-senpi-adapter/memory-v2/task-24/package-gate.txt140(pass) OMO Senpi scoped skill sync > #given ported orchestration skills #when scanned #then no foreign-harness delegatioCODE
MEDIUM…e/omo-senpi-adapter/memory-v2/task-24/package-gate.txt896(pass) omo-senpi lsp post-edit diagnostics > #given many mutated files #when post-edit diagnostics run #then shared orchCODE
MEDIUM…e/omo-senpi-adapter/memory-v2/task-13/package-gate.txt134(pass) OMO Senpi scoped skill sync > #given codex-derived and native skill roots #when scanned #then no Codex or multi-aCODE
MEDIUM…e/omo-senpi-adapter/memory-v2/task-13/package-gate.txt136(pass) OMO Senpi scoped skill sync > #given shared skill roots with opencode orchestration #when inspected #then a SenpiCODE
MEDIUM…e/omo-senpi-adapter/memory-v2/task-13/package-gate.txt140(pass) OMO Senpi scoped skill sync > #given ported orchestration skills #when scanned #then no foreign-harness delegatioCODE
MEDIUM…e/omo-senpi-adapter/memory-v2/task-13/package-gate.txt958(pass) omo-senpi lsp post-edit diagnostics > #given many mutated files #when post-edit diagnostics run #then shared orchCODE
MEDIUM…/evidence/omo-senpi-adapter/memory-v2/task-25/test.txt464(pass) OMO Senpi scoped skill sync > #given codex-derived and native skill roots #when scanned #then no Codex or multi-aCODE
MEDIUM…/evidence/omo-senpi-adapter/memory-v2/task-25/test.txt466(pass) OMO Senpi scoped skill sync > #given shared skill roots with opencode orchestration #when inspected #then a SenpiCODE
MEDIUM…/evidence/omo-senpi-adapter/memory-v2/task-25/test.txt470(pass) OMO Senpi scoped skill sync > #given ported orchestration skills #when scanned #then no foreign-harness delegatioCODE
MEDIUM…/evidence/omo-senpi-adapter/memory-v2/task-25/test.txt1269(pass) omo-senpi lsp post-edit diagnostics > #given many mutated files #when post-edit diagnostics run #then shared orchCODE
MEDIUM…/20260820-dag-completion-directive/gate-test-senpi.txt124(pass) OMO Senpi scoped skill sync > #given codex-derived and native skill roots #when scanned #then no Codex or multi-aCODE
MEDIUM…/20260820-dag-completion-directive/gate-test-senpi.txt129(pass) OMO Senpi scoped skill sync > #given ported orchestration skills #when scanned #then no foreign-harness delegatioCODE
MEDIUM…/20260820-dag-completion-directive/gate-test-senpi.txt315(pass) insertSenpiCompatibilityGuidance > #given content with no opencode orchestration calls #when processed #then it iCODE
MEDIUM…/20260820-dag-completion-directive/gate-test-senpi.txt1425(pass) omo-senpi lsp post-edit diagnostics > #given many mutated files #when post-edit diagnostics run #then shared orchCODE
MEDIUM…/20260820-dag-completion-directive/gate-test-senpi.txt3245(pass) selectRegistryFallbackModels > #given priced chat models > #when two models share a price #then the larger contexCODE
MEDIUM…/20260820-dag-completion-directive/gate-test-senpi.txt3247(pass) selectRegistryFallbackModels > #given models reflection cannot use > #when the context window is below the reflecCODE
MEDIUM…0-dag-completion-directive/gate-baseline-omo-senpi.txt125(pass) OMO Senpi scoped skill sync > #given codex-derived and native skill roots #when scanned #then no Codex or multi-aCODE
MEDIUM…0-dag-completion-directive/gate-baseline-omo-senpi.txt157(pass) OMO Senpi scoped skill sync > #given ported orchestration skills #when scanned #then no foreign-harness delegatioCODE
MEDIUM…0-dag-completion-directive/gate-baseline-omo-senpi.txt356(pass) insertSenpiCompatibilityGuidance > #given content with no opencode orchestration calls #when processed #then it iCODE
MEDIUM…0-dag-completion-directive/gate-baseline-omo-senpi.txt1517(pass) omo-senpi lsp post-edit diagnostics > #given many mutated files #when post-edit diagnostics run #then shared orchCODE
MEDIUM…0-dag-completion-directive/gate-baseline-omo-senpi.txt3356(pass) selectRegistryFallbackModels > #given priced chat models > #when two models share a price #then the larger contexCODE
MEDIUM…0-dag-completion-directive/gate-baseline-omo-senpi.txt3358(pass) selectRegistryFallbackModels > #given models reflection cannot use > #when the context window is below the reflecCODE
MEDIUM…ence/20260827-dag-fallback-waiter-guard/full-suite.txt1372(pass) DAG child in-process tool policy > #given a DAG node child #when its session options are built #then no orchestraCODE
MEDIUM…ence/20260827-dag-fallback-waiter-guard/full-suite.txt1373(pass) DAG child in-process tool policy > #given a persisted DAG node child #when resumed #then the shared orchestrationCODE
MEDIUM…ence/20260827-dag-fallback-waiter-guard/full-suite.txt2129(pass) shared parent tool family filter > #given task, team, and dag orchestration names #when classified #then only orcCODE
MEDIUM…blocker-harness-scope/red-control-section-restored.txt4Received: "<skill-instruction>\nBase directory for this skill: C:\\Users\\pss\\.omo-contrib\\work\\omo\\packages\\sharedCODE
MEDIUM…ence/20260801-plan-gate-hardening/e2e-read-unlock.json1{"result":"PASS","scenario":"read-unlock","expect":"gated","checks":{"read_does_not_unlock":true,"no_child_spawned":trueCODE
MEDIUM…ence/20260801-plan-gate-hardening/e2e-read-unlock.json1{"result":"PASS","scenario":"read-unlock","expect":"gated","checks":{"read_does_not_unlock":true,"no_child_spawned":trueCODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt657(pass) codex-config-toml > #given empty Codex config #when updating config #then creates MultiAgentV2 section without roCODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt658(pass) codex-config-toml > #given stale queue multi-agent mode #when updating config #then removes unsupported root key CODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt660(pass) codex-config-toml > #given stale proactive multi-agent mode #when updating config #then removes unsupported root CODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1077✔ #given Codex-facing orchestration surfaces #when inspected #then retired ChatGPT-account model names are not recommendCODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1080✔ #given long-running orchestration prompts #when waiting on child agents #then parent liveness is surfaced (2.111541ms)CODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1087✔ #given SessionStart migration removes unsupported root multi-agent mode #when startup check runs #then emits cleanup nCODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1280✔ #given the scaffold script and the workflow reference #when compared #then every plan header the script emits is documCODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1284✔ #given scaffold #when .omo/plans is a symlink outside the workspace #then it refuses before the plan write escapes (28CODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1285✔ #given scaffold #when .omo/drafts is a symlink outside the workspace #then it refuses before the draft write escapes (CODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1287✔ #given an explicit review modifier at startup #when draft-only scaffold runs #then the first durable write contains thCODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1288✔ #given automatic review for non-Trivial UNCLEAR intent #when draft-only scaffold runs #then the first durable write coCODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1289✔ #given Trivial UNCLEAR pre-approval planning #when draft-only scaffold runs #then it creates a review-optional draft wCODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1311✔ #given synced aggregate Codex skills #when they contain OpenCode orchestration examples #then Codex tool compatibilityCODE
MEDIUM…nce/20260812-define-goal-reference/test-codex-gate.txt1315✔ #given generated Codex compatibility guidance #when adapting a skill #then multi-agent role and load_skills guidance aCODE
200 more matches not shown…
Structural Annotation Overuse218 hits · 403 pts
SeverityFileLineSnippetContext
LOW…/evidence/20260809-omo-agent-toolkit-rename/task-3.txt2634Received: "# Installation\n\noh-my-openagent ships in **two editions** of the same product:\n\n- **Ultimate Edition (omoCODE
LOW…260816-grok-sisyphus-prompt/sisyphus-agent-before.json132 "prompt": "<agent-identity>\nYour designated identity for this session is \"Sisyphus\". This identity supersedes any pCODE
LOW.opencode/skills/github-triage/SKILL.md89# Step 1: Fetch basic metadata (without body/comments to avoid JSON parsing issues)COMMENT
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md50### Step 1: Create feature branchCOMMENT
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md57### Step 2: Extend CommentCheckerConfigSchemaCOMMENT
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md62### Step 3: Add a post-processing filter in cli-runner.tsCOMMENT
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md78### Step 4: Create dedicated filter moduleCOMMENT
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md83### Step 5: Pass allowed_comment_prefixes through the hook chainCOMMENT
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md88### Step 6: Add test casesCOMMENT
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md105### Step 7: VerifyCOMMENT
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md111### Step 8: Commit and pushCOMMENT
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md118### Step 9: Create PRCOMMENT
LOW…ation-1/eval-2/without_skill/outputs/execution-plan.md52### Step 1: Harden `readBoulderState()` validationCOMMENT
LOW…ation-1/eval-2/without_skill/outputs/execution-plan.md59### Step 2: Add try/catch in setTimeout callbackCOMMENT
LOW…ation-1/eval-2/without_skill/outputs/execution-plan.md65### Step 3: Add defensive guard in `getPlanProgress`COMMENT
LOW…ation-1/eval-2/without_skill/outputs/execution-plan.md70### Step 4: Add testsCOMMENT
LOW…ation-1/eval-2/without_skill/outputs/execution-plan.md75### Step 5: Run CI checksCOMMENT
LOW…ation-1/eval-2/without_skill/outputs/execution-plan.md83### Step 6: Create PRCOMMENT
LOW…teration-1/eval-2/with_skill/outputs/execution-plan.md18### Step 1: Fix `readBoulderState()` in `src/features/boulder-state/storage.ts`COMMENT
LOW…teration-1/eval-2/with_skill/outputs/execution-plan.md23### Step 2: Add defensive guard in `src/hooks/atlas/idle-event.ts`COMMENT
LOW…teration-1/eval-2/with_skill/outputs/execution-plan.md28### Step 3: Add test coverage in `src/hooks/atlas/index.test.ts`COMMENT
LOW…teration-1/eval-2/with_skill/outputs/execution-plan.md34### Step 4: Local validationCOMMENT
LOW…teration-1/eval-2/with_skill/outputs/execution-plan.md42### Step 5: Atomic commitCOMMENT
LOW…ation-1/eval-3/without_skill/outputs/execution-plan.md53### Step 1: Create branchCOMMENT
LOW…ation-1/eval-3/without_skill/outputs/execution-plan.md58### Step 2: Split `constants.ts` into 5 focused filesCOMMENT
LOW…ation-1/eval-3/without_skill/outputs/execution-plan.md90### Step 3: Convert `constants.ts` to barrel re-export fileCOMMENT
LOW…ation-1/eval-3/without_skill/outputs/execution-plan.md93### Step 4: Split `model-requirements.ts`COMMENT
LOW…ation-1/eval-3/without_skill/outputs/execution-plan.md106### Step 5: Verify no import breakageCOMMENT
LOW…ation-1/eval-3/without_skill/outputs/execution-plan.md111### Step 6: Verify LSP diagnostics cleanCOMMENT
LOW…ation-1/eval-3/without_skill/outputs/execution-plan.md114### Step 7: Commit and create PRCOMMENT
LOW…ation-1/eval-4/without_skill/outputs/execution-plan.md20### Step 1: Create `src/mcp/arxiv.ts`COMMENT
LOW…ation-1/eval-4/without_skill/outputs/execution-plan.md25### Step 2: Update `src/mcp/types.ts`COMMENT
LOW…ation-1/eval-4/without_skill/outputs/execution-plan.md29### Step 3: Update `src/mcp/index.ts`COMMENT
LOW…ation-1/eval-4/without_skill/outputs/execution-plan.md34### Step 4: Update `src/mcp/index.test.ts`COMMENT
LOW…ation-1/eval-4/without_skill/outputs/execution-plan.md41### Step 5: Create `src/mcp/arxiv.test.ts` (optional, only if factory pattern used)COMMENT
LOW…ation-1/eval-4/without_skill/outputs/execution-plan.md45### Step 6: Update `src/mcp/AGENTS.md`COMMENT
LOW…teration-1/eval-4/with_skill/outputs/execution-plan.md12### Step 1: Create `src/mcp/arxiv.ts`COMMENT
LOW…teration-1/eval-4/with_skill/outputs/execution-plan.md18### Step 2: Update `src/mcp/types.ts`COMMENT
LOW…teration-1/eval-4/with_skill/outputs/execution-plan.md21### Step 3: Update `src/mcp/index.ts`COMMENT
LOW…teration-1/eval-4/with_skill/outputs/execution-plan.md30### Step 4: Create `src/mcp/arxiv.test.ts`COMMENT
LOW…teration-1/eval-4/with_skill/outputs/execution-plan.md34### Step 5: Update `src/mcp/index.test.ts`COMMENT
LOW…teration-1/eval-4/with_skill/outputs/execution-plan.md39### Step 6: Update `src/mcp/AGENTS.md`COMMENT
LOW…teration-1/eval-4/with_skill/outputs/execution-plan.md42### Step 7: Local validationCOMMENT
LOW…ation-1/eval-1/without_skill/outputs/execution-plan.md9### Step 1: Create feature branchCOMMENT
LOW…ation-1/eval-1/without_skill/outputs/execution-plan.md15### Step 2: Add `max_background_agents` to BackgroundTaskConfigSchemaCOMMENT
LOW…ation-1/eval-1/without_skill/outputs/execution-plan.md24### Step 3: Modify `ConcurrencyManager` to enforce global limitCOMMENT
LOW…ation-1/eval-1/without_skill/outputs/execution-plan.md36### Step 4: Add tests for the new config schema fieldCOMMENT
LOW…ation-1/eval-1/without_skill/outputs/execution-plan.md43### Step 5: Add tests for ConcurrencyManager global limitCOMMENT
LOW…ation-1/eval-1/without_skill/outputs/execution-plan.md53### Step 6: Run typecheck and testsCOMMENT
LOW…ation-1/eval-1/without_skill/outputs/execution-plan.md61### Step 7: Verify LSP diagnostics cleanCOMMENT
LOW…ation-1/eval-1/without_skill/outputs/execution-plan.md65### Step 8: Create PRCOMMENT
LOW.agents/skills/github-triage/SKILL.md89# Step 1: Fetch basic metadata (without body/comments to avoid JSON parsing issues)COMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh748 # Step 2: Start fake-openai serverCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh758 # Step 3: Create isolated sandbox and write opencode.jsoncCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh768 # Step 4: Start opencode serve (using oqa_start_server internals but with our config)COMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh860 # Step 8: Plugin-init countCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh867 # Step 9: Route provenanceCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh727 # Step 1: Record real-DB session count (read-only)COMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh798 # Step 5: Create a sessionCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh817 # Step 6: Send the split probe promptCOMMENT
158 more matches not shown…
Decorative Section Separators112 hits · 362 pts
SeverityFileLineSnippetContext
MEDIUM…260819-btw-codex-side-ui/visual-side/terminal-ansi.txt1[?2031h]10;?]11;?[>0q[?25lP+q4d73\[?1016$p[?2027$p[?2031$p[?1004$p[?2004$p[?2026$p[?u]99;i=opentCODE
MEDIUM…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
MEDIUM…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
MEDIUMtests/hashline/test-edit-ops.ts18// ── CLI arg passthrough ───────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edit-ops.ts37// ── Colors ────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edit-ops.ts49// ── Test case definition ─────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edit-ops.ts251 // ── Creative cases (6-15) ────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edit-ops.ts447 // ── Whitespace cases (16-21) ──────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edit-ops.ts575// ── JSONL event types ─────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edit-ops.ts619// ── Run single test case ─────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edit-ops.ts741// ── Main ──────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edge-cases.ts18// ── CLI arg passthrough ───────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edge-cases.ts37// ── Colors ────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edge-cases.ts51// ── Test case definition ─────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edge-cases.ts881// ── JSONL event types ─────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edge-cases.ts925// ── Run single test case ─────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-edge-cases.ts1049// ── Main ──────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-multi-model.ts15// ── Models ────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-multi-model.ts20// ── CLI args ──────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-multi-model.ts35// ── Colors ────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-multi-model.ts44// ── Types ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-multi-model.ts61// ── Parse test-headless-edit-ops stdout ───────────────────────COMMENT
MEDIUMtests/hashline/test-multi-model.ts120// ── Run one model ────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-multi-model.ts192// ── Main ──────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/test-multi-model.ts227 // ── Summary Table ──────────────────────────────────────────COMMENT
MEDIUMtests/hashline/headless.ts22// ── CLI ──────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/headless.ts44// ── Tools ────────────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/headless.ts117// ── Agent Loop ───────────────────────────────────────────────COMMENT
MEDIUMtests/hashline/headless.ts189// ── Signal + Startup ─────────────────────────────────────────COMMENT
MEDIUM…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
MEDIUM…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
MEDIUM…ages/omo-opencode/src/tools/delegate-task/constants.ts50# ╚═╝ ╚═╝╚══════╝ ╚══▀▀═╝ ╚═════╝ ╚═╝╚═╝ ╚═╝╚══════╝╚═════╝ #COMMENT
MEDIUM…x/plugin/components/codegraph/NODE-RUNTIME-LICENSES.md686 # ----------------------------------------------------------------------STRING
MEDIUM…x/plugin/components/codegraph/NODE-RUNTIME-LICENSES.md711 # --------------------------------------------------------------------------STRING
MEDIUM…x/plugin/components/codegraph/NODE-RUNTIME-LICENSES.md723 # --------------------------------------------------------------------------STRING
MEDIUM…x/plugin/components/codegraph/NODE-RUNTIME-LICENSES.md753 # --------------------------------------------------------------------------STRING
MEDIUM…skills/frontend/scripts/perfection/lighthouse-audit.py20# ──────────────────COMMENT
MEDIUM…ills/skills/ultimate-browsing/engine/waf_profiles.yaml140# ---------------------------------------------------------------------------COMMENT
MEDIUM…ills/skills/ultimate-browsing/engine/waf_profiles.yaml142# ---------------------------------------------------------------------------COMMENT
MEDIUM…ls/skills/programming/references/go/golangci-strict.md20 # ── Correctness — bug catchers ───────────────────────────────COMMENT
MEDIUM…ls/skills/programming/references/go/golangci-strict.md47 # ── Architecture — file size, complexity, dead code ─────────COMMENT
MEDIUM…ls/skills/programming/references/go/golangci-strict.md57 # ── Exhaustiveness — Go's weakest spot ──────────────────────COMMENT
MEDIUM…ls/skills/programming/references/go/golangci-strict.md60 # ── Security ────────────────────────────────────────────────COMMENT
MEDIUM…ls/skills/programming/references/go/golangci-strict.md63 # ── Logging ─────────────────────────────────────────────────COMMENT
MEDIUM…ls/skills/programming/references/go/golangci-strict.md66 # ── Performance ─────────────────────────────────────────────COMMENT
MEDIUM…ills/programming/references/python/pyproject-strict.md41# ─────────────────────────────────────────────────────────────────COMMENT
MEDIUM…ills/programming/references/python/pyproject-strict.md44# ─────────────────────────────────────────────────────────────────COMMENT
MEDIUM…ills/programming/references/python/pyproject-strict.md64# ─────────────────────────────────────────────────────────────────COMMENT
MEDIUM…ills/programming/references/python/pyproject-strict.md68# ─────────────────────────────────────────────────────────────────COMMENT
MEDIUM…ills/programming/references/python/pyproject-strict.md132# ─────────────────────────────────────────────────────────────────COMMENT
MEDIUM…ills/programming/references/python/pyproject-strict.md134# ─────────────────────────────────────────────────────────────────COMMENT
MEDIUM…ills/programming/references/python/pyproject-strict.md145# ─────────────────────────────────────────────────────────────────COMMENT
MEDIUM…ills/programming/references/python/pyproject-strict.md147# ─────────────────────────────────────────────────────────────────COMMENT
MEDIUM…lls/skills/programming/references/python/one-liners.md42# ──────────────────COMMENT
MEDIUM…lls/skills/programming/references/python/one-liners.md81# ──────────────────COMMENT
MEDIUM…lls/skills/programming/references/python/one-liners.md132# ──────────────────COMMENT
MEDIUM…lls/skills/programming/references/python/one-liners.md170# ──────────────────COMMENT
MEDIUM…lls/skills/programming/references/python/one-liners.md209# ──────────────────COMMENT
MEDIUM…ills/programming/references/typescript/backend-hono.md56// ───────────────────────────────────────────────────────────────COMMENT
MEDIUM…ills/programming/references/typescript/backend-hono.md58// ───────────────────────────────────────────────────────────────COMMENT
52 more matches not shown…
AI Slop Vocabulary80 hits · 204 pts
SeverityFileLineSnippetContext
MEDIUM…ence/20260801-plan-gate-hardening/e2e-read-unlock.json1{"result":"PASS","scenario":"read-unlock","expect":"gated","checks":{"read_does_not_unlock":true,"no_child_spawned":trueCODE
MEDIUM…vidence/20260818-fix-6990-permission-task/qa-driver.sh6# `[opencode]` harness block that sets agents.<main-agent>.permission.taskCOMMENT
MEDIUM…260804-fix-6569-review-hardening/live-bindir-driver.sh10# The real ~/.codex is never read or written; the harness asserts that.COMMENT
MEDIUM…30-fix-6338-oracle-temperature/diag-temp-forwarding.sh2# Discriminating experiment: does the harness forward an agent's `temperature` into theCOMMENT
MEDIUM…30-fix-6338-oracle-temperature/diag-temp-forwarding.sh5# If YES -> the harness can observe temperature, and the absence for claude-opus-4-8 is aCOMMENT
MEDIUM…30-fix-6338-oracle-temperature/diag-temp-forwarding.sh7# If NO -> the harness cannot observe agent temperature, so the live-request proof isCOMMENT
MEDIUM…/20260821-dag-revive-terminalization/incident-run.json1{"schemaVersion":1,"checkpointSeq":19,"runId":"dag_2d12c2f7-38f3-487e-bead-2ceafd0ab87e","runKey":"dag-sdk-error-surfaciCODE
MEDIUM…260816-grok-sisyphus-prompt/sisyphus-agent-before.json132 "prompt": "<agent-identity>\nYour designated identity for this session is \"Sisyphus\". This identity supersedes any pCODE
MEDIUM…260816-grok-sisyphus-prompt/sisyphus-agent-before.json132 "prompt": "<agent-identity>\nYour designated identity for this session is \"Sisyphus\". This identity supersedes any pCODE
LOW…260816-grok-sisyphus-prompt/sisyphus-agent-before.json132 "prompt": "<agent-identity>\nYour designated identity for this session is \"Sisyphus\". This identity supersedes any pCODE
MEDIUM…260816-grok-sisyphus-prompt/sisyphus-agent-before.json132 "prompt": "<agent-identity>\nYour designated identity for this session is \"Sisyphus\". This identity supersedes any pCODE
MEDIUM…0260816-grok-sisyphus-prompt/sisyphus-agent-after.json132 "prompt": "<agent-identity>\nYour designated identity for this session is \"Sisyphus\". This identity supersedes any pCODE
MEDIUM…0260816-grok-sisyphus-prompt/sisyphus-agent-after.json132 "prompt": "<agent-identity>\nYour designated identity for this session is \"Sisyphus\". This identity supersedes any pCODE
MEDIUM…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh3# Serve-topology wake runner-split QA harness.COMMENT
MEDIUM…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh29# 1 expectation NOT met, or internal harness errorCOMMENT
MEDIUM.agents/skills/opencode-qa/scripts/tui-smoke.sh5# This is a feasibility/smoke check, NOT a functional assertion harness. TheCOMMENT
MEDIUMscript/agent-harness-wiring.test.ts94 test("#given a containerized harness #when reading .devcontainer/devcontainer.json #then host provider creds pass throCODE
MEDIUMscript/shared-core-extraction-guard.test.ts74 test("#given core package production sources #when scanned #then they stay harness-neutral", async () => {CODE
MEDIUMscript/shared-core-extraction-guard.test.ts103 test("#given core package manifests #when scanned #then they do not depend on harness adapters", async () => {CODE
MEDIUMscript/contributing-accuracy.test.ts62 test("#given the contributor guide #when scanned for the dev-environment sections #then cross-harness setup, credentiaCODE
MEDIUMscript/agents-md-dev-env.test.ts12 test("#given root AGENTS.md #when scanned #then it documents the shared setup/cleanup scripts and every harness wiringCODE
MEDIUMscript/agent/setup.sh2# Cross-harness dev-environment bootstrap for oh-my-openagent.COMMENT
MEDIUMscript/agent/cleanup.sh2# Cross-harness teardown for oh-my-openagent dev environments.COMMENT
MEDIUMscript/agent/cleanup.sh40# before traversal so short-lived harness shutdown hooks do not get cancelledCOMMENT
MEDIUM.codex/setup.sh4# delegates to the shared cross-harness bootstrap so every harness stays in sync.COMMENT
MEDIUMpackages/omo-senpi/plugin/extensions/omo.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUM…s/omo-senpi/plugin/extensions/omo-init-deep-advisor.js2import{execFileSync as e}from"node:child_process";import{fileURLToPath as n}from"node:url";var t=[{name:"explore",descriCODE
MEDIUM…s/omo-senpi/plugin/extensions/omo-init-deep-advisor.js2import{execFileSync as e}from"node:child_process";import{fileURLToPath as n}from"node:url";var t=[{name:"explore",descriCODE
MEDIUM…s/omo-senpi/plugin/extensions/omo-init-deep-advisor.js2import{execFileSync as e}from"node:child_process";import{fileURLToPath as n}from"node:url";var t=[{name:"explore",descriCODE
MEDIUM…s/omo-senpi/plugin/extensions/omo-init-deep-advisor.js2import{execFileSync as e}from"node:child_process";import{fileURLToPath as n}from"node:url";var t=[{name:"explore",descriCODE
MEDIUM…s/omo-senpi/plugin/extensions/omo-init-deep-advisor.js2import{execFileSync as e}from"node:child_process";import{fileURLToPath as n}from"node:url";var t=[{name:"explore",descriCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo-memory-mcp.js3import{dirname as e,resolve as t}from"node:path";import{pathToFileURL as r}from"node:url";function n(e){return"object"==CODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo-task.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo-task.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo-task.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo-task.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo-task.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo-task.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/scripts/qa/team-e2e-runtime.test.ts270 it("#given a Windows shim with no package CLI #when resolved #then the harness fails loudly instead of direct-spawningCODE
MEDIUMpackages/omo-senpi/src/skills-sync.test.ts143 test("#given codex-derived and native skill roots #when scanned #then no Codex or multi-agent harness guidance surviveCODE
MEDIUMpackages/omo-senpi/src/skills-sync.test.ts195 test("#given ported orchestration skills #when scanned #then no foreign-harness delegation guidance survives", () => {CODE
MEDIUM…-senpi/src/components/ultrawork/generated-directive.ts12export const SENPI_ULTRAWORK_DIRECTIVE = "<ultrawork-mode>\n\n**MANDATORY**: First user-visible line this turn MUST be eCODE
MEDIUM…/src/components/ulw-execute-continuation/index.test.ts127 it("#given work owned by another harness #when agent_end fires #then no injection", async () => {CODE
MEDIUM…src/components/task/resumption-channel-emitter.test.ts250 it("#given the local event contract #when the literal is inspected #then it exactly matches the harness event name", (CODE
MEDIUM…o-config-core/src/schema/unified-config-schema.test.ts66 test("#given partial model catalog entries in harness and profile overlays #when parsed #then they remain default-freeCODE
MEDIUMpackages/omo-config-core/src/schema/telemetry.test.ts6 test("#given the telemetry enabled setting #when checking harness support #then senpi is explicitly supported", () => CODE
MEDIUM…ckages/omo-config-core/src/schema/agent-schema.test.ts80 test("#given a harness-native preset in reasoning effort #when parsed #then it passes through as canonical reasoning",CODE
MEDIUMpackages/omo-config-core/src/schema/git-master.test.ts39 test("#given a [senpi] harness override #when parsed #then the git_master layer is accepted", () => {CODE
MEDIUM…mo-config-core/src/schema/memory-config-wiring.test.ts35 test("#given memory blocks in harness and profile overlays #when parsed #then they stay default-free", () => {CODE
MEDIUM…mo-config-core/src/schema/memory-config-wiring.test.ts66 test("#given base and senpi memory blocks #when folding the harness view #then memory deep-merges", () => {CODE
MEDIUM…mo-config-core/src/schema/memory-config-wiring.test.ts84 test("#given base harness and profile memory blocks #when folding the profile view #then later layers win per leaf", (CODE
MEDIUMpackages/omo-config-core/src/loader/resolution.test.ts95 test("#given base, harness, profile-base, and profile-harness layers #when resolving a harness profile #then later layCODE
MEDIUMpackages/omo-config-core/src/loader/resolution.test.ts143 test("#given an absent activated profile #when resolving a harness view #then a diagnostic is emitted and the no-profiCODE
MEDIUM…s/omo-config-core/src/loader/loader-resolution.test.ts21 test("#given base, harness, profile-base, and profile-harness layers #when loading the active senpi profile #then eachCODE
MEDIUM…s/omo-config-core/src/loader/loader-resolution.test.ts140 test("#given an unknown activated profile #when loading a harness view #then a profile diagnostic is emitted and no prCODE
20 more matches not shown…
Synthetic Comment Markers17 hits · 118 pts
SeverityFileLineSnippetContext
HIGH…pr-review-findings/artifacts/tui-esc/terminal-ansi.txt1^[[D^[[D^[[D[?2031h]10;?]11;?[>0q[?25lP+q4d73\[?1016$p[?2027$p[?2031$p[?1004$p[?2004$p[?2026$p[?uCODE
HIGH…/evidence/20260809-omo-agent-toolkit-rename/task-3.txt2634Received: "# Installation\n\noh-my-openagent ships in **two editions** of the same product:\n\n- **Ultimate Edition (omoCODE
HIGH…/evidence/20260809-omo-agent-toolkit-rename/task-3.txt2634Received: "# Installation\n\noh-my-openagent ships in **two editions** of the same product:\n\n- **Ultimate Edition (omoCODE
HIGH…ai-beta-release/task-11/04-attempt1-parser-failure.txt88{"model":"mock-1","messages":[{"role":"system","content":"You are senpi, a coding agent. Your work should be indistinguiCODE
HIGH…ai-beta-release/task-11/04-attempt1-parser-failure.txt89{"model":"mock-1","messages":[{"role":"system","content":"You are senpi, a coding agent. Your work should be indistinguiCODE
HIGH…ai-beta-release/task-11/04-plugin-load-and-toolkit.txt162{"model":"mock-1","messages":[{"role":"system","content":"You are senpi, a coding agent. Your work should be indistinguiCODE
HIGH…ai-beta-release/task-11/04-plugin-load-and-toolkit.txt163{"model":"mock-1","messages":[{"role":"system","content":"You are senpi, a coding agent. Your work should be indistinguiCODE
HIGH…ta-release/task-11/04-attempt2-cleanup-shell-scope.txt162{"model":"mock-1","messages":[{"role":"system","content":"You are senpi, a coding agent. Your work should be indistinguiCODE
HIGH…ta-release/task-11/04-attempt2-cleanup-shell-scope.txt163{"model":"mock-1","messages":[{"role":"system","content":"You are senpi, a coding agent. Your work should be indistinguiCODE
HIGH…revalidation/web-terminal-side-final/terminal-ansi.txt1^[[?2031h]10;?]11;?[>0q[?25lP+q4d73\[?1016$p[?2027$p[?2031$p[?1004$p[?2004$p[?2026$p[?u]99;i=opeCODE
HIGH…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
HIGH…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
HIGH…ation-1/eval-5/without_skill/outputs/pr-description.md9The comment-checker hook's upstream Go binary (`go-claude-code-comment-checker`) flags ALL non-filtered comments as probCODE
HIGH…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
HIGH…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
HIGH…ation-1/eval-5/without_skill/outputs/pr-description.md9The comment-checker hook's upstream Go binary (`go-claude-code-comment-checker`) flags ALL non-filtered comments as probCODE
HIGH…ills/skills/programming/references/go/data-modeling.md311## Common AI-generated antipatterns this rejectsCOMMENT
Over-Commented Block114 hits · 112 pts
SeverityFileLineSnippetContext
LOWtest-env.ts1/// <reference types="bun-types" />COMMENT
LOWtest-setup.ts21})COMMENT
LOWtest-setup.ts41// discovery tests pass or fail depending on whose laptop runs them. Point HOME (andCOMMENT
LOW…vidence/20260818-fix-6990-permission-task/qa-driver.sh1#!/usr/bin/env bashCOMMENT
LOW.omo/evidence/20260727-fix-6141/live-driver.sh1#!/usr/bin/env bashCOMMENT
LOW…260804-fix-6569-review-hardening/live-bindir-driver.sh1#!/usr/bin/env bashCOMMENT
LOW.omo/evidence/20260727-fix-6376/live-opencode-run.sh1#!/usr/bin/env bashCOMMENT
LOW.omo/evidence/20260727-fix-6376/live-driver.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/codex-qa/scripts/app-server-drive.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/codex-qa/scripts/hook-unit-probe.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/codex-qa/scripts/lsp-e2e.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/codex-qa/scripts/lib/common.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/opencode-qa/scripts/sse-hook-probe.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/opencode-qa/scripts/sse-hook-probe.sh21# then watch for e.g. message.part.updated.COMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh1#!/usr/bin/env bashCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh21# $XDG_CONFIG_HOME/opencode/oh-my-openagent.jsonCOMMENT
LOW.agents/skills/opencode-qa/scripts/tui-smoke.sh1#!/usr/bin/env bashCOMMENT
LOW…gents/skills/opencode-qa/scripts/db-session-by-name.sh1#!/usr/bin/env bashCOMMENT
LOW…gents/skills/opencode-qa/scripts/db-session-by-text.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/opencode-qa/scripts/lsp-e2e.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/opencode-qa/scripts/export-roundtrip.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/opencode-qa/scripts/server-smoke.sh1#!/usr/bin/env bashCOMMENT
LOW.agents/skills/opencode-qa/scripts/lib/common.sh1#!/usr/bin/env bashCOMMENT
LOWscript/root-test-serial-quarantine.ts1// Single source of truth for the root-test files that must run in one serialCOMMENT
LOWscript/build.ts21 try {COMMENT
LOWscript/qa/codex-marketplace-e2e.sh1#!/usr/bin/env bashCOMMENT
LOWscript/agent/setup.sh1#!/usr/bin/env bashCOMMENT
LOWscript/agent/qa-docker.sh1#!/usr/bin/env bashCOMMENT
LOWscript/agent/qa-sandbox.sh1#!/usr/bin/env bashCOMMENT
LOWscript/agent/cleanup.sh1#!/usr/bin/env bashCOMMENT
LOW.codex/setup.sh1#!/usr/bin/env bashCOMMENT
LOWpackages/mcp-stdio-core/src/server.test.ts321 // stall to outlast its 2s in-loop race. That is a volume bet, not a strongerCOMMENT
LOWpackages/omo-senpi/plugin/runtime/dag/sdk.js1// Dependency-free convenience wrapper around the `dag` tool, loaded by JavaScript eval cells fromCOMMENT
LOWpackages/omo-senpi/plugin/extensions/omo-memory-mcp.js1#!/usr/bin/env nodeCOMMENT
LOWpackages/omo-senpi/skills/ulw-research/SKILL.md281## Phase 5 — SynthesizeCOMMENT
LOWpackages/omo-senpi/src/bundle-size.test.ts1import { describe, expect, it } from "bun:test"COMMENT
LOWpackages/omo-senpi/src/bundle-size.test.ts21// minified bundle from 678,227 to a measured 706,927 bytes (pinned bun 1.3.12). This is plan-scopedCOMMENT
LOW…-senpi/src/extension/__fixtures__/cold-pi-tui-probe.ts1// Cold-boot probe for the pi-tui warm-up in composeOmoSenpiExtension.COMMENT
LOW…ges/omo-senpi/src/components/memory/facts-run-prune.ts1// Retention pruning for terminal facts run dirs.COMMENT
LOW…kages/omo-senpi/src/components/memory/dream-trigger.ts1// Dream trigger wiring (plan todo 12): opportunistic dream launches from idle, shutdown,COMMENT
LOW…o-senpi/src/components/memory/facts-terminal-writes.ts1// Ordered terminal writes for a facts run.COMMENT
LOWpackages/omo-senpi/src/components/memory/facts-drain.ts1// Post-success drain for the byte-capped facts pipeline.COMMENT
LOW…mo-senpi/src/components/memory/memory-notice-wiring.ts1// Shared consumer for the MCP memory tool surface (memory.tool_exposure: "search").COMMENT
LOW…ages/omo-senpi/src/components/memory/facts-oversize.ts1// Oversize classification for the byte-capped facts payload.COMMENT
LOWpackages/omo-senpi/src/components/config-watch/index.ts141 // Never emit REGISTER from inside a senpi event dispatch: rebuildWatchersCOMMENT
LOW…-senpi/src/components/task/skill-invocation-tracker.ts1import type { SkillInvocationState } from "@oh-my-opencode/senpi-task"COMMENT
LOW…omo-senpi/src/components/telemetry/model-vocabulary.ts1// Provider -> exportable model ids. The vocabulary must cover every rung a shipped builtin categoryCOMMENT
LOWpackages/omo-senpi/src/components/thread/mailbox.ts121 snapshot = await port.snapshot()COMMENT
LOWpackages/ast-grep-mcp/src/mcp-schema.test.ts1import { describe, expect, it } from "bun:test";COMMENT
LOWpackages/senpi-task/test-support/warm-lazy-runtime.ts1// Test-only warm-up for senpi-task's lazy module boundaries.COMMENT
LOWpackages/senpi-task/src/run-stats.ts101 return trueCOMMENT
LOW…s/senpi-task/src/lifecycle/single-writer-audit.test.ts1import { readdirSync, readFileSync } from "node:fs"COMMENT
LOWpackages/senpi-task/src/manager/manager-outcome.ts41// Suspension forgets the handle BEFORE its abort settles ("stale outcome tracking loses ownershipCOMMENT
LOW…ges/senpi-task/src/__adversarial__/chaos-bench.test.ts1import { afterAll, beforeAll, describe, expect, test } from "bun:test"COMMENT
LOWpackages/senpi-task/src/lazy/senpi-barrel.ts1// Lazy boundary for the @code-yeongyu/senpi engine barrel.COMMENT
LOWpackages/senpi-task/src/lazy/pi-tui.ts1// Lazy boundary for the @earendil-works/pi-tui barrel.COMMENT
LOW…ages/senpi-task/src/runners/in-process/child-loader.ts1import type { ResourceLoader } from "@code-yeongyu/senpi"COMMENT
LOWpackages/senpi-task/src/store/types.ts61 // shouldRetain(fresh) is false, atomically rename the record to <taskId>.json.expunging. TheCOMMENT
LOWpackages/utils/src/file-utils.test.ts1import { describe, it, expect, beforeAll, afterAll } from "bun:test"COMMENT
LOW…es/omo-opencode/scripts/generate-opengateway-models.ts1#!/usr/bin/env bunCOMMENT
54 more matches not shown…
Verbosity Indicators50 hits · 86 pts
SeverityFileLineSnippetContext
LOW…260816-grok-sisyphus-prompt/sisyphus-agent-before.json132 "prompt": "<agent-identity>\nYour designated identity for this session is \"Sisyphus\". This identity supersedes any pCODE
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh748 # Step 2: Start fake-openai serverCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh758 # Step 3: Create isolated sandbox and write opencode.jsoncCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh768 # Step 4: Start opencode serve (using oqa_start_server internals but with our config)COMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh860 # Step 8: Plugin-init countCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh867 # Step 9: Route provenanceCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh727 # Step 1: Record real-DB session count (read-only)COMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh798 # Step 5: Create a sessionCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh817 # Step 6: Send the split probe promptCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh899 # Step 10: Branch-count guardCOMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh914 # Step 11: Determine verdictCOMMENT
LOWpackages/omo-senpi/plugin/extensions/omo.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
LOW…s/omo-senpi/plugin/extensions/omo-init-deep-advisor.js2import{execFileSync as e}from"node:child_process";import{fileURLToPath as n}from"node:url";var t=[{name:"explore",descriCODE
LOWpackages/omo-senpi/plugin/extensions/omo-task.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
LOWpackages/senpi-task/src/agents/builtin/metis.ts26### Step 1: Identify Intent TypeCOMMENT
LOWpackages/senpi-task/src/agents/builtin/metis.ts35### Step 2: Validate ClassificationCOMMENT
LOW…features/builtin-commands/templates/remove-ai-slops.ts24## Step 0: Task PlanningCOMMENT
LOWpackages/omo-opencode/src/agents/metis.ts38### Step 1: Identify Intent TypeCOMMENT
LOWpackages/omo-opencode/src/agents/metis.ts47### Step 2: Validate ClassificationCOMMENT
LOWpackages/omo-opencode/src/agents/librarian.ts71### Step 1: Find Official DocumentationCOMMENT
LOWpackages/omo-opencode/src/agents/librarian.ts78### Step 2: Version Check (if version specified)COMMENT
LOWpackages/omo-opencode/src/agents/librarian.ts90### Step 3: Sitemap Discovery (understand doc structure)COMMENT
LOWpackages/omo-opencode/src/agents/librarian.ts101### Step 4: Targeted InvestigationCOMMENT
LOW…mo-opencode/src/agents/sisyphus-dynamic-prompt-role.ts30### Step 0: Verbalize Intent (BEFORE Classification)COMMENT
LOW…mo-opencode/src/agents/sisyphus-dynamic-prompt-role.ts52### Step 1: Classify Request TypeCOMMENT
LOW…mo-opencode/src/agents/sisyphus-dynamic-prompt-role.ts66### Step 2: Check for AmbiguityCOMMENT
LOW…mo-opencode/src/agents/sisyphus-dynamic-prompt-role.ts83### Step 3: Validate Before ActingCOMMENT
LOWpackages/omo-opencode/src/agents/hephaestus/gpt.ts130### Step 1: Classify Task TypeCOMMENT
LOWpackages/omo-opencode/src/agents/hephaestus/gpt.ts138### Step 2: Ambiguity Protocol (EXPLORE FIRST - NEVER ask before exploring)COMMENT
LOWpackages/omo-opencode/src/agents/hephaestus/gpt.ts154### Step 3: Validate Before ActingCOMMENT
LOW…ages/omo-opencode/src/agents/sisyphus/claude-opus-5.ts197### Step 0: Verbalize Intent (before classification)COMMENT
LOW…ages/omo-opencode/src/agents/sisyphus/claude-opus-5.ts219### Step 1: Classify Request TypeCOMMENT
LOW…ages/omo-opencode/src/agents/sisyphus/claude-opus-5.ts237### Step 2: Check for AmbiguityCOMMENT
LOW…ages/omo-opencode/src/agents/sisyphus/claude-opus-5.ts255### Step 3: Validate Before ActingCOMMENT
LOWpackages/omo-opencode/src/agents/sisyphus/default.ts194### Step 0: Verbalize Intent (BEFORE Classification)COMMENT
LOWpackages/omo-opencode/src/agents/sisyphus/default.ts216### Step 1: Classify Request TypeCOMMENT
LOWpackages/omo-opencode/src/agents/sisyphus/default.ts224### Step 2: Check for AmbiguityCOMMENT
LOWpackages/omo-opencode/src/agents/sisyphus/default.ts232### Step 3: Validate Before ActingCOMMENT
LOW…es/omo-opencode/src/agents/sisyphus/claude-opus-4-7.ts183### Step 0: Verbalize Intent (before classification)COMMENT
LOW…es/omo-opencode/src/agents/sisyphus/claude-opus-4-7.ts205### Step 1: Classify Request TypeCOMMENT
LOW…es/omo-opencode/src/agents/sisyphus/claude-opus-4-7.ts223### Step 2: Check for AmbiguityCOMMENT
LOW…es/omo-opencode/src/agents/sisyphus/claude-opus-4-7.ts241### Step 3: Validate Before ActingCOMMENT
LOW…ges/omo-opencode/src/agents/sisyphus/claude-fable-5.ts183### Step 0: Verbalize Intent (before classification)COMMENT
LOW…ges/omo-opencode/src/agents/sisyphus/claude-fable-5.ts205### Step 1: Classify Request TypeCOMMENT
LOW…ges/omo-opencode/src/agents/sisyphus/claude-fable-5.ts223### Step 2: Check for AmbiguityCOMMENT
LOW…ges/omo-opencode/src/agents/sisyphus/claude-fable-5.ts241### Step 3: Validate Before ActingCOMMENT
LOW…es/omo-opencode/src/agents/sisyphus/claude-opus-4-8.ts183### Step 0: Verbalize Intent (before classification)COMMENT
LOW…es/omo-opencode/src/agents/sisyphus/claude-opus-4-8.ts205### Step 1: Classify Request TypeCOMMENT
LOW…es/omo-opencode/src/agents/sisyphus/claude-opus-4-8.ts223### Step 2: Check for AmbiguityCOMMENT
LOW…es/omo-opencode/src/agents/sisyphus/claude-opus-4-8.ts241### Step 3: Validate Before ActingCOMMENT
Unused Imports78 hits · 78 pts
SeverityFileLineSnippetContext
LOW…-remove-prompt-contract-tests/classification_bundle.py1CODE
LOW…move-prompt-contract-tests/test_node_assert_scanner.py5CODE
LOW…remove-prompt-contract-tests/audit_prompt_contracts.py8CODE
LOW…17-remove-prompt-contract-tests/audit_agents_policy.py8CODE
LOW…7-remove-prompt-contract-tests/scanner_test_support.py1CODE
LOW…-remove-prompt-contract-tests/test_snapshot_scanner.py5CODE
LOW…0817-remove-prompt-contract-tests/scanner_bootstrap.py3CODE
LOW…0260817-remove-prompt-contract-tests/scanner_models.py3CODE
LOW…e-prompt-contract-tests/test_audit_prompt_contracts.py5CODE
LOW…ared-skills/skills/ast-grep/scripts/ast_grep_helper.py51CODE
LOW…skills/frontend/scripts/perfection/lighthouse-audit.py32CODE
LOW…skills/frontend/scripts/perfection/lighthouse-audit.py36CODE
LOW…s/coding-agent-sessions/scripts/find-agent-sessions.py9CODE
LOW…coding-agent-sessions/scripts/agent_sessions/jsonio.py1CODE
LOW…ons/scripts/agent_sessions/sqlite_optional_scanners.py1CODE
LOW…ng-agent-sessions/scripts/agent_sessions/transcript.py1CODE
LOW…/coding-agent-sessions/scripts/agent_sessions/codex.py1CODE
LOW…agent-sessions/scripts/agent_sessions/file_scanners.py1CODE
LOW…coding-agent-sessions/scripts/agent_sessions/claude.py1CODE
LOW…ding-agent-sessions/scripts/agent_sessions/__init__.py1CODE
LOW…/coding-agent-sessions/scripts/agent_sessions/types.py1CODE
LOW…ding-agent-sessions/scripts/agent_sessions/opencode.py1CODE
LOW…ing-agent-sessions/scripts/agent_sessions/pi_family.py1CODE
LOW…-agent-sessions/scripts/agent_sessions/kiro_scanner.py1CODE
LOW…ls/coding-agent-sessions/scripts/agent_sessions/cli.py1CODE
LOW…ent-sessions/scripts/agent_sessions/sqlite_scanners.py1CODE
LOW…ing-agent-sessions/scripts/agent_sessions/timeparse.py1CODE
LOW…agent-sessions/scripts/agent_sessions/aside_scanner.py1CODE
LOW…ding-agent-sessions/scripts/agent_sessions/scanners.py1CODE
LOW…gent-sessions/scripts/tests/test_pi_family_scanners.py8CODE
LOW…essions/scripts/tests/test_optional_sqlite_scanners.py8CODE
LOW…ng-agent-sessions/scripts/tests/test_agent_sessions.py8CODE
LOW…ding-agent-sessions/scripts/tests/test_cli_contract.py8CODE
LOW…agent-sessions/scripts/tests/test_extended_scanners.py8CODE
LOW…ing-agent-sessions/scripts/tests/test_aside_scanner.py8CODE
LOW…ills/skills/ultimate-browsing/scripts/cookie_crypto.py2CODE
LOW…lls/skills/ultimate-browsing/scripts/cookie_domains.py1CODE
LOW…kills/skills/ultimate-browsing/scripts/cookie_paths.py2CODE
LOW…ls/skills/ultimate-browsing/scripts/extract_cookies.py13CODE
LOW…ltimate-browsing/scripts/tests/test_extract_cookies.py3CODE
LOW…te-browsing/scripts/tests/test_cookie_domain_filter.py2CODE
LOW…d-skills/skills/ultimate-browsing/engine/bias_check.py12CODE
LOW…skills/skills/ultimate-browsing/engine/waf_detector.py11CODE
LOW…skills/skills/ultimate-browsing/engine/waf_detector.py15CODE
LOW…d-skills/skills/ultimate-browsing/engine/validators.py12CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py7CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py7CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py7CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py7CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py8CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py9CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py9CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py10CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py11CODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py11CODE
LOW…d-skills/skills/ultimate-browsing/engine/curl_probe.py1CODE
LOW…kills/skills/ultimate-browsing/engine/result_schema.py1CODE
LOW…ared-skills/skills/ultimate-browsing/engine/summary.py1CODE
LOW…ed-skills/skills/ultimate-browsing/engine/surrogate.py18CODE
LOW…ills/skills/ultimate-browsing/engine/url_transforms.py17CODE
18 more matches not shown…
Magic Placeholder Names12 hits · 60 pts
SeverityFileLineSnippetContext
HIGH…/src/install/codex-cache-mcp-manifest.context7.test.ts22 env: { CONTEXT7_API_KEY: "<YOUR_API_KEY>", SAFE_FLAG: "1" },CODE
HIGH…/src/install/codex-cache-mcp-manifest.context7.test.ts22 env: { CONTEXT7_API_KEY: "<YOUR_API_KEY>", SAFE_FLAG: "1" },CODE
HIGH…/src/install/codex-cache-mcp-manifest.context7.test.ts40 expect(raw).not.toContain("YOUR_API_KEY")CODE
HIGH…/src/install/codex-cache-mcp-manifest.context7.test.ts88 env: { CONTEXT7_API_KEY: "YOUR_API_KEY", SAFE_FLAG: "1" },CODE
HIGH…/src/install/codex-cache-mcp-manifest.context7.test.ts103 expect(raw).not.toContain("YOUR_API_KEY")CODE
HIGH…ckages/omo-codex/src/install/codex-config-toml.test.ts230 expect(content).not.toContain("YOUR_API_KEY")CODE
HIGH…ckages/omo-codex/src/install/codex-config-toml.test.ts253 expect(content).not.toContain("YOUR_API_KEY")CODE
HIGH…ckages/omo-codex/src/install/codex-config-toml.test.ts286 expect(content).not.toContain("YOUR_API_KEY")CODE
HIGH…ckages/omo-codex/src/install/codex-config-toml.test.ts298 'args = ["-y", "@upstash/context7-mcp", "--api-key", "ctx7sk_live_example"] # replace YOUR_API_KEY in docs only'CODE
HIGH…ckages/omo-codex/src/install/codex-config-toml.test.ts317 expect(content).toContain("replace YOUR_API_KEY in docs only")CODE
HIGH…ckages/omo-codex/src/install/codex-config-toml.test.ts330 'args = ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]',CODE
HIGH…ckages/omo-codex/src/install/codex-config-toml.test.ts350 expect(content).not.toContain("YOUR_API_KEY")CODE
Hallucination Indicators2 hits · 30 pts
SeverityFileLineSnippetContext
CRITICAL…ges/senpi-task/src/__adversarial__/chaos-invariants.ts177 for (const handle of state.harness.probeEngine.inProcessRunner.allHandles.filter((entry) => entry.handle.task_id ===CODE
CRITICAL…ges/senpi-task/src/__adversarial__/chaos-invariants.ts180 for (const handle of state.harness.probeEngine.processRunner.allHandles.filter((entry) => entry.handle.task_id === iCODE
Cross-File Repetition6 hits · 30 pts
SeverityFileLineSnippetContext
HIGHpackages/omo-senpi/plugin/extensions/omo.js0*** begin patch',"*** update file: system/human/prefs/coding.md","@@","-use broad abstractions","+prefer small focused hSTRING
HIGHpackages/omo-senpi/plugin/extensions/omo-memory-mcp.js0*** begin patch',"*** update file: system/human/prefs/coding.md","@@","-use broad abstractions","+prefer small focused hSTRING
HIGHpackages/omo-senpi/plugin/extensions/omo-task.js0*** begin patch',"*** update file: system/human/prefs/coding.md","@@","-use broad abstractions","+prefer small focused hSTRING
HIGH…mponents/ultrawork/agents/lazycodex-worker-medium.toml0role: implementation executor. you own the task end to end. make the smallest correct change that satisfies the caller'sSTRING
HIGH…/components/ultrawork/agents/lazycodex-worker-low.toml0role: implementation executor. you own the task end to end. make the smallest correct change that satisfies the caller'sSTRING
HIGH…components/ultrawork/agents/lazycodex-worker-high.toml0role: implementation executor. you own the task end to end. make the smallest correct change that satisfies the caller'sSTRING
Excessive Try-Catch Wrapping23 hits · 28 pts
SeverityFileLineSnippetContext
LOW…ared-skills/skills/ast-grep/scripts/ast_grep_helper.py185 except Exception:CODE
LOW…e-browsing/references/insane-search/tls-impersonate.md44 except Exception:CODE
LOW…e-browsing/references/insane-search/tls-impersonate.md53 except Exception:CODE
LOW…d-skills/skills/ultimate-browsing/engine/bias_check.py109 except Exception as e:CODE
LOW…skills/skills/ultimate-browsing/engine/waf_detector.py87 except Exception as e:CODE
LOW…skills/skills/ultimate-browsing/engine/waf_detector.py101 except Exception:CODE
LOW…skills/skills/ultimate-browsing/engine/waf_detector.py104 except Exception:CODE
LOW…skills/skills/ultimate-browsing/engine/waf_detector.py111 except Exception:CODE
MEDIUM…skills/skills/ultimate-browsing/engine/waf_detector.py98def _cookies_dict(resp) -> dict:CODE
MEDIUM…skills/skills/ultimate-browsing/engine/waf_detector.py108def _headers_dict(resp) -> dict:CODE
LOW…d-skills/skills/ultimate-browsing/engine/validators.py135 except Exception:CODE
LOW…d-skills/skills/ultimate-browsing/engine/validators.py142 except Exception:CODE
LOW…d-skills/skills/ultimate-browsing/engine/validators.py174 except Exception as e:CODE
LOW…d-skills/skills/ultimate-browsing/engine/validators.py258 except Exception:CODE
LOW…d-skills/skills/ultimate-browsing/engine/validators.py261 except Exception:CODE
MEDIUM…d-skills/skills/ultimate-browsing/engine/validators.py255def _extract_cookies(resp) -> dict:CODE
LOW…ed-skills/skills/ultimate-browsing/engine/surrogate.py181 except Exception as exc:CODE
LOW…ed-skills/skills/ultimate-browsing/engine/surrogate.py189 except Exception as exc:CODE
LOW…red-skills/skills/ultimate-browsing/engine/__main__.py65 except Exception as e:CODE
LOW…red-skills/skills/ultimate-browsing/engine/executor.py84 except Exception as e:CODE
LOW…-skills/skills/programming/references/python/README.md137except Exception as e:CODE
LOW…-skills/skills/programming/references/python/README.md144except Exception:CODE
LOW…-skills/skills/programming/references/python/README.md160 except Exception:CODE
Cross-Language Confusion6 hits · 25 pts
SeverityFileLineSnippetContext
HIGH…-remove-prompt-contract-tests/test_snapshot_scanner.py28expect(JSON.stringify(snapshotSubject, null, 2)).toMatchSnapshot();STRING
HIGH…skills/frontend/scripts/perfection/lighthouse-audit.py60 : undefined,CODE
HIGH…skills/frontend/scripts/perfection/lighthouse-audit.py63 : undefined,CODE
HIGH…ls/skills/ultimate-browsing/scripts/extract_cookies.py108 if (result && result.success) ok += 1;CODE
HIGH…ls/skills/ultimate-browsing/scripts/extract_cookies.py113 process.stderr.write(`${error.name || "Error"}: ${error.message || error}\n`);CODE
HIGH…kills/skills/programming/scripts/python/new-project.py168 rprint(f" cd {name} && uv sync && uv run basedpyright . && uv run ruff check .")STRING
Fake / Example Data23 hits · 23 pts
SeverityFileLineSnippetContext
LOW…idence/omo-senpi-adapter/memory-v2/task-19/palace.html284<script type="application/json" id="omo-palace-data">{"metadata":{"identity":"palace-agent","headSha":"c6770a6ed566a69a2CODE
LOW…overy/opencode-source-qa-reused-internal-fix-debug.txt93 options: {apiKey: "fake-key", baseURL: $base_url, timeout: 30000},CODE
LOW…vidence/20260820-pr6611-recovery/opencode-source-qa.sh54 options: {apiKey: "fake-key", baseURL: $base_url, timeout: 30000},CODE
LOW…11-recovery/opencode-source-qa-first-key-fix-debug.txt93 options: {apiKey: "fake-key", baseURL: $base_url, timeout: 30000},CODE
LOW…r6611-recovery/opencode-source-qa-generation-debug.txt98 options: {apiKey: "fake-key", baseURL: $base_url, timeout: 30000},CODE
LOW…e/20260820-pr6611-seven-blockers/opencode-source-qa.sh54 options: {apiKey: "fake-key", baseURL: $base_url, timeout: 30000},CODE
LOW…vidence/20260818-fix-6990-permission-task/qa-driver.sh48 "apiKey": "fake-key",CODE
LOW.omo/evidence/20260724-sisyphus-opus5-prompt/qa-run.sh55 "apiKey": "fake-key",CODE
LOWtests/hashline/test-edge-cases.ts707 fileContent: ["placeholder", "tail"].join("\n"),CODE
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh207 "apiKey": "fake-key",CODE
LOW.agents/skills/opencode-qa/scripts/lsp-e2e.sh1481 options: { apiKey: "fake-key", baseURL: `http://127.0.0.1:${port}/v1`, timeout: 30000 },CODE
LOW…ore/src/features/builtin-skills/agent-browser/SKILL.md327agent-browser fill @e1 "user@example.com"CODE
LOW…e/src/features/builtin-skills/skills/playwright-cli.ts45playwright-cli fill e5 "user@example.com"CODE
LOW…e/src/features/builtin-skills/skills/playwright-cli.ts220playwright-cli fill e1 "user@example.com"CODE
LOWpackages/omo-senpi/plugin/extensions/omo-task.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
LOW…/omo-senpi/src/components/memory/palace/people.test.ts40 expect(jane?.displayName).toBe("Jane Doe")CODE
LOW…enpi/src/components/memory/commands/people-ask.test.ts104 displayName: "Jane Doe",CODE
LOW…es/senpi-task/src/tools/task/argument-normalization.ts6const PROVIDER_PADDING_PROMPTS = new Set(["unused", "placeholder", "not used", "n/a"])CODE
LOWpackages/web/DESIGN.md299- Lorem ipsum or "John Doe" placeholders.CODE
LOWpackages/web/DESIGN.md299- Lorem ipsum or "John Doe" placeholders.CODE
LOW…ode/src/features/builtin-skills/agent-browser/SKILL.md327agent-browser fill @e1 "user@example.com"CODE
LOW…x/plugin/components/ulw-loop/test/quality-gate.test.ts194 expect(error.message).toContain("placeholder");CODE
LOW…red-skills/skills/frontend/references/design/README.md197- **Don't load nothing and just freestyle.** That produces the exact "generic AI SaaS slop" — purple-blue gradient backgCODE
Self-Referential Comments8 hits · 23 pts
SeverityFileLineSnippetContext
MEDIUM…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
MEDIUM.agents/skills/codex-qa/scripts/lib/common.sh71# Create an isolated CODEX_HOME and project dir, export the env that keeps theCOMMENT
MEDIUM.agents/skills/opencode-qa/scripts/lib/common.sh67# Create an isolated XDG sandbox so a spawned opencode never touches the realCOMMENT
MEDIUM…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo-memory-mcp.js3import{dirname as e,resolve as t}from"node:path";import{pathToFileURL as r}from"node:url";function n(e){return"object"==CODE
MEDIUMpackages/omo-senpi/plugin/extensions/omo-task.js2import{createRequire as e}from"node:module";var t=Object.defineProperty,n=e=>e;function r(e,t){this[e]=n.bind(null,t)}vaCODE
MEDIUM…kages/omo-senpi/src/components/memory/tool-metadata.ts57 "# Create a block with starting text",CODE
Example Usage Blocks10 hits · 15 pts
SeverityFileLineSnippetContext
LOW.agents/skills/codex-qa/scripts/lsp-e2e.sh10# Usage:COMMENT
LOW.agents/skills/opencode-qa/scripts/sse-hook-probe.sh30# Usage:COMMENT
LOW.agents/skills/opencode-qa/scripts/db-session-by-id.sh5# Usage:COMMENT
LOW…s/skills/opencode-qa/scripts/serve-wake-split-probe.sh14# Usage:COMMENT
LOW.agents/skills/opencode-qa/scripts/tui-smoke.sh14# Usage:COMMENT
LOW…gents/skills/opencode-qa/scripts/db-session-by-name.sh6# Usage:COMMENT
LOW…gents/skills/opencode-qa/scripts/db-session-by-text.sh18# Usage:COMMENT
LOW.agents/skills/opencode-qa/scripts/lsp-e2e.sh9# Usage:COMMENT
LOW.agents/skills/opencode-qa/scripts/export-roundtrip.sh9# Usage:COMMENT
LOW.agents/skills/opencode-qa/scripts/server-smoke.sh12# Usage:COMMENT
Deep Nesting15 hits · 15 pts
SeverityFileLineSnippetContext
LOW…ared-skills/skills/ast-grep/scripts/ast_grep_helper.py161CODE
LOW…ared-skills/skills/ast-grep/scripts/ast_grep_helper.py625CODE
LOW…coding-agent-sessions/scripts/agent_sessions/jsonio.py43CODE
LOW…ding-agent-sessions/scripts/agent_sessions/opencode.py34CODE
LOW…ding-agent-sessions/scripts/agent_sessions/opencode.py268CODE
LOW…ls/coding-agent-sessions/scripts/agent_sessions/cli.py32CODE
LOW…ls/coding-agent-sessions/scripts/agent_sessions/cli.py141CODE
LOW…d-skills/skills/ultimate-browsing/engine/bias_check.py139CODE
LOW…skills/skills/ultimate-browsing/engine/waf_detector.py115CODE
LOW…-skills/skills/ultimate-browsing/engine/fetch_chain.py34CODE
LOW…ls/programming/scripts/python/check-no-excuse-rules.py143CODE
LOW…ls/programming/scripts/python/check-no-excuse-rules.py199CODE
LOW…ls/programming/scripts/python/check-no-excuse-rules.py373CODE
LOW…ills/programming/scripts/rust/check-no-excuse-rules.py150CODE
LOWpackages/omo-native/test/pty-signal-qa.py65CODE
TODO Padding6 hits · 8 pts
SeverityFileLineSnippetContext
LOW…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md95- `// TODO: implement caching` - should NOT be flaggedCODE
LOW…eration-1/eval-5/without_skill/outputs/code-changes.md331 { line: 3, text: "// TODO: implement caching" },CODE
LOW…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
LOW…ation-1/eval-5/without_skill/outputs/execution-plan.md95- `// TODO: implement caching` - should NOT be flaggedCODE
LOW…eration-1/eval-5/without_skill/outputs/code-changes.md331 { line: 3, text: "// TODO: implement caching" },CODE
Redundant / Tautological Comments5 hits · 8 pts
SeverityFileLineSnippetContext
LOW…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
LOW…/skills/work-with-pr-workspace/iteration-1/review.html717 const APP_DATA = {"skill_name": "work-with-pr", "workspace_dir": "/Users/yeongyu/local-workspaces/omo/.opencode/skilCODE
LOW…ls/programming/scripts/python/check-no-excuse-rules.py404 # Check if body contains assert_never callCOMMENT
LOW…ls/programming/scripts/python/check-no-excuse-rules.py447 # Check if all arguments are string literals or f-stringsCOMMENT
LOW.github/workflows/sisyphus-agent.yml354 # Check if PR or Issue and get titleCOMMENT
Modern Structural Boilerplate3 hits · 3 pts
SeverityFileLineSnippetContext
LOW…ing-agent-sessions/scripts/agent_sessions/pi_family.py12__all__ = ["scan_gajae_code", "scan_oh_my_pi", "scan_senpi"]CODE
LOW…ding-agent-sessions/scripts/agent_sessions/scanners.py77__all__ = ["DEFAULT_PLATFORMS", "PLATFORM_SCANNERS", "scan", "scan_claude", "scan_codex", "scan_gajae_code", "scan_oh_myCODE
LOW…red-skills/skills/ultimate-browsing/engine/__init__.py13__all__ = [CODE
Overly Generic Function Names1 hit · 1 pts
SeverityFileLineSnippetContext
LOW…/src/features/opencode-runtime-skills/source-server.ts71 function handleRequest(request: Request): Response | Promise<Response> {CODE