Repository Analysis

alvinunreal/oh-my-opencode-slim

Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks

3.3 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of alvinunreal/oh-my-opencode-slim, a TypeScript project with 6,895 GitHub stars. SynthScan v2.0 examined 93,123 lines of code across 358 source files, recording 186 pattern matches distributed across 7 syntactic categories. The overall adjusted score of 3.3 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).

3.3
Adjusted Score
3.3
Raw Score
100%
Time Factor
2026-07-14
Last Push
6.9K
Stars
TypeScript
Language
93.1K
Lines of Code
358
Files
186
Pattern Hits
2026-07-14
Scan Date
0.00
HC Hit Rate

What These Metrics Mean

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

Score History

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

Severity Breakdown

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

CRITICAL 0HIGH 0MEDIUM 63LOW 123

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 186 distinct pattern matches across 7 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.

Decorative Section Separators61 hits · 166 pts
SeverityFileLineSnippetContext
MEDIUMsrc/index.ts447 // ── Health check: validate registrations ────────────────────────────COMMENT
MEDIUMsrc/index.ts480 // ── Probe jsdom (async, non-blocking) ───────────────────────────────COMMENT
MEDIUMsrc/utils/background-job-coordinator.ts36 // ── Terminal state notification (guaranteed delivery) ─────────────COMMENT
MEDIUMsrc/utils/background-job-coordinator.ts66 // ── Lifecycle policy ─────────────────────────────────────────────COMMENT
MEDIUMsrc/utils/background-job-coordinator.ts97 // ── Mutation methods (sole writer to board) ──────────────────────COMMENT
MEDIUMsrc/utils/background-job-coordinator.ts136 // ── Query methods ────────────────────────────────────────────────COMMENT
MEDIUMsrc/utils/background-job-store.ts16 // ── Mutation methods ──────────────────────────────────────────────COMMENT
MEDIUMsrc/utils/background-job-store.ts38 // ── Query methods ─────────────────────────────────────────────────COMMENT
MEDIUMsrc/utils/background-job-store.ts71 // ── Lifecycle policy ─────────────────────────────────────────────COMMENT
MEDIUMsrc/utils/background-job-board.ts529 // ── Lifecycle policy (board = no policy, always close) ───────────COMMENT
MEDIUMsrc/interview/manager.ts26 // ─── Per-session mode (upstream behavior) ───────────────────────COMMENT
MEDIUMsrc/interview/manager.ts31 // ─── Dashboard mode ─────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/document.ts12// ─── Path Utilities ──────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/document.ts95// ─── String Utilities ────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/document.ts105// ─── Markdown Document Operations ────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts31// ─── Auth Token File ────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts96// ─── Helpers ──────────────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts136// ─── Types ────────────────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts145// ─── Config ───────────────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts162// ─── Dashboard Server ─────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts285 // ─── Auth ─────────────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts312 // ─── Session Discovery ───────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts359 // ─── File Scanning ───────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts411 // ─── Failover: rebuild state from .md frontmatter ──────────────COMMENT
MEDIUMsrc/interview/dashboard.ts495 // ─── Request Handler ─────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts512 // ── Health check (no auth required) ────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts528 // ── API: settings (scan days, folders, discovery) ──────────────COMMENT
MEDIUMsrc/interview/dashboard.ts584 // ── Dashboard UI ───────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts629 // ── API: list sessions (auth required) ──────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts649 // ── API: list files (auth required) ─────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts660 // ── Auth gate for mutation endpoints ───────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts666 // ── API: register session ──────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts699 // ── API: create interview ──────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts747 // ── API: SSE stream (browser → dashboard, real-time push) ────────COMMENT
MEDIUMsrc/interview/dashboard.ts804 // ── API: push state (session → dashboard) ──────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts948 // ── API: submit answers (browser → dashboard) ──────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts1002 // ── API: submit block comment (browser → dashboard) ────────────COMMENT
MEDIUMsrc/interview/dashboard.ts1081 // ── API: submit chat message (browser → dashboard) ──────────────COMMENT
MEDIUMsrc/interview/dashboard.ts1190 // ── API: nudge agent (browser → dashboard) ────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts1239 // ── API: get nudge action (session polls, auth required) ──────COMMENT
MEDIUMsrc/interview/dashboard.ts1269 // ── Interview page ─────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts1287 // ── 404 ────────────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts1291 // ─── Server Lifecycle ────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts1370 // ─── Public API ──────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts1476// ─── Health Probe (for session processes) ─────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard.ts1499// ─── Try Become Dashboard (with jitter retry) ─────────────────────────COMMENT
MEDIUMsrc/interview/dashboard-manager.ts44 // ── Timer-based fallback for nudge/answer polling ─────────────COMMENT
MEDIUMsrc/interview/dashboard-manager.ts77 // ── We ARE the dashboard ────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard-manager.ts132 // ── We're a SESSION ─────────────────────────────────────────COMMENT
MEDIUMsrc/interview/dashboard-manager.ts225 // ── Client Poll Implementations (polls dashboard server) ──────────COMMENT
MEDIUMsrc/interview/dashboard-manager.ts460// ─── Helpers ──────────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/types.ts21// ─── Zod Schemas (for validating untrusted LLM output) ─────────────COMMENT
MEDIUMsrc/interview/types.ts38// ─── Interfaces ─────────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/ui.ts15// ─── Shared client-side helpers ────────────────────────────────────COMMENT
MEDIUMsrc/interview/ui.ts45// ─── Shared styles ─────────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/ui.ts115// ─── Dashboard brand image ─────────────────────────────────────────COMMENT
MEDIUMsrc/interview/ui.ts1391 // ── Completed-mode helpers ───────────────────────────────────COMMENT
MEDIUMsrc/interview/ui.ts1589 // ── TOC Sidebar ──────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/ui.ts1625 // ── Chat Panel ───────────────────────────────────────────────COMMENT
MEDIUMsrc/interview/ui.ts1965 // ── Real-time updates via SSE ─────────────────────────────────COMMENT
1 more matches not shown…
Hyper-Verbose Identifiers100 hits · 104 pts
SeverityFileLineSnippetContext
LOWscripts/verify-release-artifact.ts88function verifyDistHasNoLeakedPaths() {CODE
LOWsrc/index.ts510 function resolveTuiVariantForModel(CODE
LOWsrc/tools/preset-manager.ts43 async function handleCommandExecuteBefore(CODE
LOWsrc/tools/smartfetch/network.ts76export function canUseCanonicalCacheAlias(baseUrl: string, aliasUrl: string) {CODE
LOWsrc/tools/smartfetch/network.ts458function parseFilenameFromContentDisposition(value: string | null) {CODE
LOWsrc/tools/smartfetch/secondary-model.ts39function findPreferredOpenCodeConfigPath(baseDir: string) {CODE
LOWsrc/tools/smartfetch/secondary-model.ts59async function readEffectiveOpenCodeConfig(directory: string) {CODE
LOWsrc/tools/smartfetch/secondary-model.ts75export async function readSecondaryModelFromConfig(directory: string) {CODE
LOWsrc/tools/smartfetch/secondary-model.ts299export async function runSecondaryModelWithFallback(CODE
LOWsrc/tools/smartfetch/utils.ts229export function buildRedirectResultMessage(CODE
LOWsrc/tools/smartfetch/utils.ts344export function inferCanonicalUrlFromText(content: string, finalUrl: string) {CODE
LOWsrc/tools/smartfetch/utils.ts355export function extractHeadingsFromMarkdown(content: string) {CODE
LOWsrc/multiplexer/shared.ts24export function buildOpencodeAttachCommand(CODE
LOWsrc/multiplexer/shared.ts42export function resolveHostOpencodeBinary(CODE
LOWsrc/multiplexer/session-manager.ts82export function resetMultiplexerSessionManagerState(): void {CODE
LOWsrc/config/schema.ts328function rejectOrchestratorPromptOnOrchestrator(CODE
LOWsrc/config/loader.ts161function validateFinalImageRouting(CODE
LOWsrc/config/runtime-preset.ts29export function setActiveRuntimePresetWithPrevious(name: string | null): void {CODE
LOWsrc/config/strip-orchestrator-model.ts21export function applyOrchestratorModelConfig(input: {CODE
LOWsrc/agents/permissions.ts13export function createReadOnlyAgentPermission(): AgentPermission {CODE
LOWsrc/agents/index.ts50function getPrimaryModelFromOverride(CODE
LOWsrc/agents/index.ts64function getActivePresetPrimaryModel(CODE
LOWsrc/agents/index.ts228function buildCustomAgentDefinition(CODE
LOWsrc/utils/internal-initiator.ts9export function createInternalAgentTextPart(text: string): {CODE
LOWsrc/utils/agent-variant.ts72export function createDisplayNameMentionRewriter(CODE
LOWsrc/utils/councillor-models.ts19export function normalizeCouncillorModels(CODE
LOWsrc/utils/task.ts20export function parseTaskIdFromTaskOutput(output: string): string | undefined {CODE
LOWsrc/utils/task.ts91export function parseTaskResultFromOutput(output: string): string | undefined {CODE
LOWsrc/cli/install.ts148export async function configureBackgroundSubagents(CODE
LOWsrc/cli/install.ts288function handleOptionalCompanionResult(result: ConfigMergeResult): void {CODE
LOWsrc/cli/config-io.ts164function getPinnedVersionFromConfig(): string | undefined {CODE
LOWsrc/cli/config-io.ts202function getVersionFromPackageRoot(packageRoot: string): string | undefined {CODE
LOWsrc/cli/config-io.ts215function getOpenCodePluginCacheDir(version?: string): string {CODE
LOWsrc/cli/config-io.ts224function writeOpenCodePluginCacheManifest(CODE
LOWsrc/cli/config-io.ts253function removeOpenCodePluginCacheArtifacts(cacheDir: string): void {CODE
LOWsrc/cli/config-io.ts262function verifyOpenCodePluginCache(cacheDir: string): ConfigMergeResult | null {CODE
LOWsrc/cli/config-io.ts438export async function addPluginToOpenCodeConfig(): Promise<ConfigMergeResult> {CODE
LOWsrc/cli/config-io.ts485export async function addPluginToOpenCodeTuiConfig(): Promise<ConfigMergeResult> {CODE
LOWsrc/cli/background-subagents.ts12export function isBackgroundSubagentsEnabled(CODE
LOWsrc/cli/background-subagents.ts28export function detectBackgroundSubagentsTarget(CODE
LOWsrc/cli/background-subagents.ts47export function getBackgroundSubagentsBlock(targetPath: string): string {CODE
LOWsrc/cli/background-subagents.ts56export function manualBackgroundSubagentsInstructions(options?: {CODE
LOWsrc/cli/background-subagents.ts84export function upsertBackgroundSubagentsBlock(CODE
LOWsrc/cli/background-subagents.ts102export function writeBackgroundSubagentsBlock(targetPath: string): void {CODE
LOWsrc/cli/skills.ts35export function getSkillPermissionsForAgent(CODE
LOWsrc/cli/paths.ts5function getDefaultOpenCodeConfigDir(): string {CODE
LOWsrc/cli/paths.ts13function getCustomOpenCodeConfigDir(): string | undefined {CODE
LOWsrc/cli/paths.ts89export function getExistingLiteConfigPath(): string {CODE
LOWsrc/interview/document.ts21export function createInterviewDirectoryPath(CODE
LOWsrc/interview/document.ts52export function resolveExistingInterviewPath(CODE
LOWsrc/interview/dashboard.ts335 async function discoverSessionDirectories(): Promise<void> {CODE
LOWsrc/interview/ui.ts1241 function updateActiveQuestionFocus() {CODE
LOWsrc/interview/interview.test.ts60function extractInterviewIdFromLastPrompt(promptMock: {CODE
LOWsrc/interview/service.ts637 async function handleCommandExecuteBefore(CODE
LOWsrc/interview/session-server.ts7export function createPerSessionInterviewServer(CODE
LOWsrc/hooks/auto-update-checker/checker.ts238export function getCurrentRuntimePackageJsonPath(CODE
LOWsrc/hooks/auto-update-checker/checker.ts406export async function getLatestCompatibleVersion(CODE
LOWsrc/hooks/auto-update-checker/checker.ts460async function getCompatibleFromDistTags(CODE
LOWsrc/hooks/auto-update-checker/skill-sync.ts551export function syncBundledSkillsFromPackage(CODE
LOWsrc/hooks/auto-update-checker/index.ts28export function createAutoUpdateCheckerHook(CODE
40 more matches not shown…
Structural Annotation Overuse20 hits · 30 pts
SeverityFileLineSnippetContext
LOWdocs/installation.md148### Step 1: Check OpenCode InstallationCOMMENT
LOWdocs/installation.md156### Step 2: Run the InstallerCOMMENT
LOWdocs/installation.md191### Step 3: Authenticate with ProvidersCOMMENT
LOWdocs/installation.md200### Step 4: Verify InstallationCOMMENT
LOWsrc/skills/codemap/SKILL.md18### Step 1: Check for Existing StateCOMMENT
LOWsrc/skills/codemap/SKILL.md30### Step 2: Initialize (Only if no state exists)COMMENT
LOWsrc/skills/codemap/SKILL.md55### Step 3: Detect Changes (If state already exists)COMMENT
LOWsrc/skills/codemap/SKILL.md78### Step 4: Finalize Repository Atlas (Root Codemap)COMMENT
LOWsrc/skills/codemap/SKILL.md86### Step 5: Register Codemap in AGENTS.mdCOMMENT
LOWsrc/skills/clonedeps/SKILL.md18### Step 1: Check Existing StateCOMMENT
LOWsrc/skills/clonedeps/SKILL.md32### Step 2: Ask Librarian for the Clone PlanCOMMENT
LOWsrc/skills/clonedeps/SKILL.md88### Step 3: Verify and Confirm the PlanCOMMENT
LOWsrc/skills/clonedeps/SKILL.md103### Step 4: Update Ignore FilesCOMMENT
LOWsrc/skills/clonedeps/SKILL.md133### Step 5: Clone Sources ManuallyCOMMENT
LOWsrc/skills/clonedeps/SKILL.md168### Step 6: Write Local StateCOMMENT
LOWsrc/skills/clonedeps/SKILL.md206### Step 7: Register Dependency Source in AGENTS.mdCOMMENT
LOWsrc/skills/simplify/SKILL.md76### Step 1: Understand Before TouchingCOMMENT
LOWsrc/skills/simplify/SKILL.md90### Step 2: Look for Simplification OpportunitiesCOMMENT
LOWsrc/skills/simplify/SKILL.md104### Step 3: Apply Changes IncrementallyCOMMENT
LOWsrc/skills/simplify/SKILL.md116### Step 4: Verify the ResultCOMMENT
AI Slop Vocabulary1 hit · 3 pts
SeverityFileLineSnippetContext
MEDIUMsrc/interview/parser.ts120 // A robust heuristic to escape literal carriage returns/newlines inside JSON string valuesCOMMENT
Modern AI Meta-Vocabulary1 hit · 2 pts
SeverityFileLineSnippetContext
MEDIUMAGENTS.md71│ ├── council/ # Council manager (multi-LLM session orchestration)CODE
Over-Commented Block2 hits · 2 pts
SeverityFileLineSnippetContext
LOWsrc/index.ts601 // ForegroundFallbackManager via the event hook.COMMENT
LOWsrc/agents/index.ts161 if (Array.isArray(override.model)) {COMMENT
Overly Generic Function Names1 hit · 0 pts
SeverityFileLineSnippetContext
LOWsrc/interview/dashboard.ts497 async function handleRequest(CODE