Repository Analysis

getagentseal/codeburn

Free, local tool to track AI coding token usage and cost across 31 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn

4.3 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of getagentseal/codeburn, a TypeScript project with 8,653 GitHub stars. SynthScan v2.0 examined 104,403 lines of code across 396 source files, recording 251 pattern matches distributed across 8 syntactic categories. The overall adjusted score of 4.3 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).

4.3
Adjusted Score
4.3
Raw Score
100%
Time Factor
2026-07-14
Last Push
8.7K
Stars
TypeScript
Language
104.4K
Lines of Code
396
Files
251
Pattern Hits
2026-07-14
Scan Date
0.03
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 11MEDIUM 63LOW 177

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 251 distinct pattern matches across 8 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 Separators62 hits · 198 pts
SeverityFileLineSnippetContext
MEDIUMtests/parser-claude-cwd.test.ts325// ── Helpers for Cowork local-agent-mode session fixtures ────────────────COMMENT
MEDIUMtests/parser.test.ts20// ── Synthetic provider state ───────────────────────────────────────────────COMMENT
MEDIUMtests/parser.test.ts72// ── OTel DB helpers ───────────────────────────────────────────────────────COMMENT
MEDIUMtests/parser.test.ts137// ── Copilot JSONL helpers ─────────────────────────────────────────────────COMMENT
MEDIUMtests/parser.test.ts155// ── Helpers ───────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/parser.test.ts172// ── Common env setup ──────────────────────────────────────────────────────COMMENT
MEDIUMtests/parser.test.ts199// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser.test.ts201// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser.test.ts230// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser.test.ts232// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser.test.ts269// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser.test.ts271// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser.test.ts297// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser.test.ts299// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser.test.ts347// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser.test.ts349// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/parser-proxy-pricing.test.ts10// ── Part A: isProxiedPath matching rule (pure) ─────────────────────────────COMMENT
MEDIUMtests/parser-proxy-pricing.test.ts118// ── Part B: end-to-end attribution through parseAllSessions ────────────────COMMENT
MEDIUMtests/sync.test.ts16// ── Discovery Doc Parser ──────────────────────────────────────────────COMMENT
MEDIUMtests/sync.test.ts83// ── PKCE ──────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/sync.test.ts110// ── Auth URL ──────────────────────────────────────────────────────────COMMENT
MEDIUMtests/sync.test.ts143// ── Scope Resolution ──────────────────────────────────────────────────COMMENT
MEDIUMtests/sync.test.ts167// ── Callback Server ──────────────────────────────────────────────────COMMENT
MEDIUMtests/sync.test.ts206// ── Config ────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/sync-ledger-otlp.test.ts22// ── Helpers ───────────────────────────────────────────────────────────COMMENT
MEDIUMtests/sync-ledger-otlp.test.ts61// ── OTLP Span/Trace ID Derivation ────────────────────────────────────COMMENT
MEDIUMtests/sync-ledger-otlp.test.ts126// ── OTLP Payload Builder ──────────────────────────────────────────────COMMENT
MEDIUMtests/sync-ledger-otlp.test.ts203// ── Batching ──────────────────────────────────────────────────────────COMMENT
MEDIUMtests/sync-ledger-otlp.test.ts231// ── Ledger ────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/sync-ledger-otlp.test.ts349// ── assertHttps (RFC 8252 §8.3) ───────────────────────────────────────COMMENT
MEDIUMtests/sync-push.test.ts17// ── Helpers ───────────────────────────────────────────────────────────COMMENT
MEDIUMtests/sync-push.test.ts84// ── Test env: isolated HOME so ledger writes go to a temp dir ─────────COMMENT
MEDIUMtests/sync-push.test.ts102// ── collectUnsentCalls ────────────────────────────────────────────────COMMENT
MEDIUMtests/sync-push.test.ts147// ── sendBatches: success path ─────────────────────────────────────────COMMENT
MEDIUMtests/sync-push.test.ts180// ── sendBatches: partial success ──────────────────────────────────────COMMENT
MEDIUMtests/sync-push.test.ts210// ── sendBatches: error paths ──────────────────────────────────────────COMMENT
MEDIUMtests/sync-push.test.ts364// ── MAX_PER_PUSH safety valve ─────────────────────────────────────────COMMENT
MEDIUMtests/sync-push.test.ts373// ── parseRetryAfterMs ─────────────────────────────────────────────────COMMENT
MEDIUMtests/session-cache.test.ts77// ── emptyCache ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/session-cache.test.ts87// ── loadCache / saveCache ──────────────────────────────────────────────COMMENT
MEDIUMtests/session-cache.test.ts161// ── computeEnvFingerprint ──────────────────────────────────────────────COMMENT
MEDIUMtests/session-cache.test.ts192// ── fingerprintFile ────────────────────────────────────────────────────COMMENT
MEDIUMtests/session-cache.test.ts250// ── reconcileFile ──────────────────────────────────────────────────────COMMENT
MEDIUMtests/session-cache.test.ts333// ── mergeCallByDedupKey ────────────────────────────────────────────────COMMENT
MEDIUMtests/session-cache.test.ts358// ── deep validation (loadCache) ────────────────────────────────────────COMMENT
MEDIUMtests/session-cache.test.ts542// ── cleanupOrphanedTempFiles ───────────────────────────────────────────COMMENT
MEDIUMmac/Scripts/build-local.sh2# ============================================================================COMMENT
MEDIUMmac/Scripts/build-local.sh4# ============================================================================COMMENT
MEDIUMmac/Scripts/build-local.sh6# ---------------COMMENT
MEDIUMmac/Scripts/build-local.sh27# ----------------------------------------------------------------------------COMMENT
MEDIUMsrc/parser.ts1741// ── Cache Conversion ───────────────────────────────────────────────────COMMENT
MEDIUMsrc/parser.ts1894// ── Cache-Aware Parsing Helpers ────────────────────────────────────────COMMENT
MEDIUMsrc/session-cache.ts9// ── Types ──────────────────────────────────────────────────────────────COMMENT
MEDIUMsrc/session-cache.ts83// ── Constants ──────────────────────────────────────────────────────────COMMENT
MEDIUMsrc/session-cache.ts132// ── Cache Dir ──────────────────────────────────────────────────────────COMMENT
MEDIUMsrc/session-cache.ts142// ── Env Fingerprint ────────────────────────────────────────────────────COMMENT
MEDIUMsrc/session-cache.ts152// ── Load / Save ────────────────────────────────────────────────────────COMMENT
MEDIUMsrc/session-cache.ts294// ── File Fingerprinting ────────────────────────────────────────────────COMMENT
MEDIUMsrc/session-cache.ts329// ── Reconciliation ─────────────────────────────────────────────────────COMMENT
MEDIUMsrc/session-cache.ts366// ── Dedup Merge ────────────────────────────────────────────────────────COMMENT
2 more matches not shown…
Hyper-Verbose Identifiers130 hits · 130 pts
SeverityFileLineSnippetContext
LOWtests/optimize.test.ts93function projectWithContextSessions(sessions: TestSession[], project = 'app'): ProjectSummary {CODE
LOWtests/optimize.test.ts569function projectWithLowWorthSessions(sessions: TestSession[], project = 'app'): ProjectSummary {CODE
LOWtests/optimize.test.ts830function projectWithReliabilityTurns(turns: LowWorthTurn[], project = 'app'): ProjectSummary {CODE
LOWtests/optimize.test.ts1081 function checkAllPasteFixesHaveDestination(findings: WasteFinding[]) {CODE
LOWtests/parser-large-session.test.ts66function messageFirstLargeAssistantLine(sessionId: string, timestamp: string, messageId: string): string {CODE
LOWtests/providers/cursor-bubble-dedup.test.ts103async function updateAssistantBubbleTokens(dbPath: string, inputTokens: number, outputTokens: number): Promise<void> {CODE
LOWtests/providers/antigravity.test.ts37function createCurrentAntigravityCliDb(dbPath: string, fixture: CurrentCliFixture): void {CODE
LOWtests/providers/copilot.test.ts50function transcriptAssistantMessage(opts: { messageId: string; content?: string; reasoningText?: string; toolCallIds?: sCODE
LOWdocs/design/codeburn-mcp-plan.md148export async function buildMenubarPayloadForRange(CODE
LOWsrc/compare-stats.ts188export function computeCategoryComparison(projects: ProjectSummary[], modelA: string, modelB: string): CategoryComparisoCODE
LOWsrc/day-aggregator.ts29export function aggregateProjectsIntoDays(projects: ProjectSummary[]): DailyEntry[] {CODE
LOWsrc/antigravity-statusline.ts121export async function installAntigravityStatusLineHook(force = false): Promise<'installed' | 'already-installed'> {CODE
LOWsrc/antigravity-statusline.ts145export async function uninstallAntigravityStatusLineHook(): Promise<'removed' | 'restored' | 'not-installed'> {CODE
LOWsrc/parser.ts1914function getOrCreateProviderSection(cache: SessionCache, provider: string): ProviderSection {CODE
LOWsrc/parser.ts1914function getOrCreateProviderSection(cache: SessionCache, provider: string): ProviderSection {CODE
LOWsrc/parser.ts1923function cachedFileNeedsProviderReparse(providerName: string, sourcePath: string, cached: CachedFile): boolean {CODE
LOWsrc/parser.ts83async function resolveCanonicalProjectPath(cwd: string): Promise<{ path: string; isWorktree: boolean }> {CODE
LOWsrc/parser.ts496function findJsonContainerEndBuffer(source: Buffer, start: number, open: number, close: number, limit = source.length): CODE
LOWsrc/parser.ts521function findJsonValueBoundsBuffer(source: Buffer, start: number, limit = source.length): BufferJsonValueBounds | null {CODE
LOWsrc/parser.ts552function findObjectFieldValueBuffer(source: Buffer, objectStart: number, objectEnd: number, field: string): BufferJsonVaCODE
LOWsrc/parser.ts616function readJsonNumberFieldBuffer(source: Buffer, objectBounds: BufferJsonValueBounds | null, field: string): number | CODE
LOWsrc/parser.ts660function extractLargeToolBlocksBuffer(source: Buffer, contentBounds: BufferJsonValueBounds | null): ToolUseBlock[] {CODE
LOWsrc/parser.ts707function extractLargeUserTextBuffer(source: Buffer, contentBounds: BufferJsonValueBounds | null): string | undefined {CODE
LOWsrc/parser.ts741function extractLargeAddedNamesBuffer(source: Buffer, attachmentBounds: BufferJsonValueBounds | null): string[] {CODE
LOWsrc/parser.ts824function getTopLevelRawJsonStringField(head: string, field: string): string | null {CODE
LOWsrc/parser.ts1004function extractBashCommandsFromContent(content: ContentBlock[]): string[] {CODE
LOWsrc/parser.ts1040function extractClaudeCacheCreation(usage: AssistantMessageContent['usage']): { totalTokens: number; oneHourTokens: numbCODE
LOWsrc/parser.ts1152export function dedupeStreamingMessageIds(entries: JournalEntry[]): JournalEntry[] {CODE
LOWsrc/parser.ts1771async function canonicalizeProviderCallProject(call: ParsedProviderCall): Promise<ParsedProviderCall> {CODE
LOWsrc/parser.ts1818function providerCallsToCachedTurns(calls: ParsedProviderCall[]): CachedTurn[] {CODE
LOWsrc/parser.ts1942function warnProviderReadFailureOnce(providerName: string, err: unknown): void {CODE
LOWsrc/parser.ts2393export function filterProjectsByClaudeConfigSource(projects: ProjectSummary[], sourceId: string): ProjectSummary[] {CODE
LOWsrc/parser.ts2407export function filterProjectsByDateRange(projects: ProjectSummary[], dateRange: DateRange): ProjectSummary[] {CODE
LOWsrc/plan-usage.ts28export function computePeriodFromResetDay(resetDay: number | undefined, today: Date): { periodStart: Date; periodEnd: DaCODE
LOWsrc/export.ts313async function clearCodeburnExportFolder(path: string): Promise<void> {CODE
LOWsrc/menubar-installer.ts73export function resolveMenubarReleaseAssets(release: ReleaseResponse): ResolvedAssets {CODE
LOWsrc/menubar-installer.ts88export function resolveLatestMenubarReleaseAssets(releases: ReleaseResponse[]): ResolvedAssets {CODE
LOWsrc/menubar-installer.ts104export function resolveVersionedMenubarReleaseAssets(cliVersion: string): ResolvedAssets {CODE
LOWsrc/menubar-installer.ts122export function shouldFallbackToReleaseApi(status: number): boolean {CODE
LOWsrc/menubar-installer.ts126export function formatGitHubReleaseLookupError(status: number, headers?: HeaderGetter): string {CODE
LOWsrc/menubar-installer.ts138function isMissingDirectAssetError(err: unknown): boolean {CODE
LOWsrc/menubar-installer.ts299async function resolvePersistentCodeburnPath(): Promise<string> {CODE
LOWsrc/usage-aggregator.ts167export async function buildMenubarPayloadForRange(periodInfo: PeriodInfo, opts: AggregateOpts = {}): Promise<MenubarPaylCODE
LOWsrc/models.ts81function applyBuiltinPriceOverrides(pricing: Map<string, ModelCosts>): Map<string, ModelCosts> {CODE
LOWsrc/models.ts373function priceOverrideRatePerToken(usdPerMillion: number | undefined): number | null {CODE
LOWsrc/models.ts403function getSortedPriceOverrideKeys(): string[] {CODE
LOWsrc/models.ts410function getLowercasePriceOverrideIndex(): Map<string, ModelCosts> {CODE
LOWsrc/models.ts438function getPriceOverrideCaseInsensitive(canonical: string, withPrefix: string): ModelCosts | null {CODE
LOWsrc/models.ts469export function calculateLocalModelSavings(CODE
LOWsrc/models.ts499export function getLocalModelSavingsConfigHash(): string {CODE
LOWsrc/models.ts506export function getPriceOverridesConfigHash(): string {CODE
LOWsrc/models.ts591function stripKnownPricingVariantSuffix(model: string): string | null {CODE
LOWsrc/models.ts747function shouldWarnAboutUnknownModel(name: string): boolean {CODE
LOWsrc/persistent-codeburn.ts12export function buildPersistentCodeburnLookupPath(existingPath = process.env.PATH ?? ''): string {CODE
LOWsrc/persistent-codeburn.ts38export async function resolvePersistentCodeburnPathFromPath(CODE
LOWsrc/persistent-codeburn.ts55export function resolvePersistentCodeburnPathFromWhichOutput(CODE
LOWsrc/optimize.ts701 function getOrInit(server: string): ServerAcc {CODE
LOWsrc/optimize.ts1032function estimateMcpProfileColdSchemaCost(CODE
LOWsrc/optimize.ts1071function collectMcpProjectProfiles(CODE
LOWsrc/optimize.ts1280function collectReliabilityCapabilities(turn: ProjectSummary['sessions'][number]['turns'][number]): Map<string, CapabiliCODE
70 more matches not shown…
Cross-Language Confusion (JS/TS)10 hits · 70 pts
SeverityFileLineSnippetContext
HIGHsrc/act/optimize-apply.ts129 print(chalk.dim('\n No appliable config-class fixes for this period.'))CODE
HIGHsrc/act/optimize-apply.ts133 print()CODE
HIGHsrc/act/optimize-apply.ts137 print(renderApplyList(appliable, manual, costRate))CODE
HIGHsrc/act/optimize-apply.ts140 print(chalk.dim(' Dry run: nothing was changed.\n'))CODE
HIGHsrc/act/optimize-apply.ts153 print(chalk.yellow(` Skipped ${fp.finding.id}: CLAUDE.md edits are not applied with --yes; use the interactive piCODE
HIGHsrc/act/optimize-apply.ts161 print(chalk.dim(' Nothing applied.\n'))CODE
HIGHsrc/act/optimize-apply.ts174 print()CODE
HIGHsrc/act/optimize-apply.ts178 print(` Applied ${chalk.bold(shortId(record.id))} ${record.description}`)CODE
HIGHsrc/act/optimize-apply.ts179 print(chalk.dim(` Undo anytime: codeburn act undo ${shortId(record.id)}`))CODE
HIGHsrc/act/optimize-apply.ts185 print()CODE
Over-Commented Block44 hits · 42 pts
SeverityFileLineSnippetContext
LOWtests/parser-proxy-merge.test.ts1import { mkdtemp, mkdir, rm, writeFile } from 'fs/promises'COMMENT
LOWtests/otel-cache-aggregation.test.ts1// Regression test for the OTel multi-conversation cache overwrite bug.COMMENT
LOWtests/currency-rounding.test.ts1import { describe, it, expect, beforeEach, afterEach } from 'vitest'COMMENT
LOWtests/kiro-cache-invalidation.test.ts1// Regression test for the Kiro stale-cache path (#618, #619).COMMENT
LOWtests/providers/cursor-bubble-dedup.test.ts1import { describe, it, expect, beforeEach, afterEach } from 'vitest'COMMENT
LOWtests/providers/copilot.test.ts701 })COMMENT
LOWtests/providers/copilot.test.ts1141 expect(calls).toHaveLength(1)COMMENT
LOWtests/setup/env-isolation.ts1// Vitest setup file: isolates every test from the developer's shell environment.COMMENT
LOW…ests/CodeBurnMenubarTests/DataClientProcessTests.swift81 provider: .lingtaiTui,COMMENT
LOW…/CodeBurnMenubarTests/MenubarPeriodSettingsTests.swift61 @Test("non-today periods render compact and regular suffixes")COMMENT
LOWmac/Scripts/build-local.sh1#!/usr/bin/env bashCOMMENT
LOWmac/Sources/CodeBurnMenubar/CodeBurnApp.swift941 // Tahoe an accessory app activating while a popover anchors toCOMMENT
LOWmac/Sources/CodeBurnMenubar/Data/CLIClaudeConfig.swift1import FoundationCOMMENT
LOWmac/Sources/CodeBurnMenubar/Data/DataClient.swift121 private static func runCLI(subcommand: [String]) async throws -> ProcessResult {COMMENT
LOW…urces/CodeBurnMenubar/Data/ClaudeCredentialStore.swift1import FoundationCOMMENT
LOW…urces/CodeBurnMenubar/Data/ClaudeCredentialStore.swift201 /// (a hardcoded company-style identifier) while Claude Code 2.1.x writesCOMMENT
LOWmac/Sources/CodeBurnMenubar/Data/QuotaSummary.swift21 /// Display label for the user's plan (e.g. "Max 20x", "Pro Lite"). ShownCOMMENT
LOWsrc/main.ts241 const totalCacheWrite = sessions.reduce((s, sess) => s + sess.totalCacheWriteTokens, 0)COMMENT
LOWsrc/cursor-cache.ts1import { readFile, writeFile, mkdir, rename, stat, unlink } from 'fs/promises'COMMENT
LOWsrc/parser.ts61 const normalized = projectPath.trim().replace(/\\/g, '/').replace(/\/+$/, '')COMMENT
LOWsrc/parser.ts1981// event loop every YIELD_EVERY items so the OS scheduler gets regular breakCOMMENT
LOWsrc/parser.ts2481 }COMMENT
LOWsrc/models.ts521 })COMMENT
LOWsrc/models.ts661}COMMENT
LOWsrc/models.ts701// resolve AFTER table hits and so cannot prove the $0 was intentional; aCOMMENT
LOWsrc/config.ts41 // Map raw local-model names (e.g. "llama3.1:8b") to the paid model we wouldCOMMENT
LOWsrc/content-utils.ts1/// Normalize a message's `content` into an array of content blocks.COMMENT
LOWsrc/providers/cursor.ts101/// does NOT carry a workspace path on the bubble itself. The mapping livesCOMMENT
LOWsrc/providers/codebuff.ts321// the same `chatId` can legitimately appear under each channel rootCOMMENT
LOWsrc/providers/copilot.ts1// =============================================================================COMMENT
LOWsrc/providers/copilot.ts21// "github.copilot.chat.otel.enabled": true,COMMENT
LOWsrc/providers/copilot.ts41// CODEBURN_COPILOT_GLOBAL_STORAGE_DIR — Override VS Code globalStorageCOMMENT
LOWsrc/providers/copilot.ts881 deduplicationKey: dedupKey,COMMENT
LOWsrc/providers/copilot.ts1041 const val = Buffer.from(raw.slice(start, start + len), 'latin1').toString('utf8')COMMENT
LOWsrc/providers/copilot.ts1161 // round) must NOT fall back to Markdown — that would bill the user's promptCOMMENT
LOWsrc/providers/copilot.ts1301 seenReplies.add(dedupeKey)COMMENT
LOWsrc/providers/copilot.ts1741 // on-disk store dir name). Normally each turn is grouped by its own tab GUID.COMMENT
LOWsrc/providers/grok.ts1import { readdir, stat } from 'fs/promises'COMMENT
LOWsrc/providers/codex.ts41 read_dir: 'Glob',COMMENT
LOWsrc/providers/codex.ts121// Cap how many bytes we'll read while looking for the first newline. RealCOMMENT
LOWsrc/providers/codex.ts581 const totalTokens = inputTokens + cachedInputTokens + outputTokens + reasoningTokensCOMMENT
LOWsrc/guard/usage.ts1import { mkdir, readFile, stat, writeFile } from 'fs/promises'COMMENT
LOWsrc/guard/hooks.ts1// ===========================================================================COMMENT
LOWsrc/guard/hooks.ts21// systemMessage.COMMENT
Synthetic Comment Markers1 hit · 8 pts
SeverityFileLineSnippetContext
HIGHsrc/context-tree.ts527// Claude Code stores an AI-generated session name as "ai-title" entries (theCOMMENT
Fake / Example Data2 hits · 2 pts
SeverityFileLineSnippetContext
LOWtests/parser.test.ts353 await writeFile(synthFile, 'placeholder')CODE
LOWtests/parser.test.ts384 await writeFile(synthFile, 'placeholder')CODE
Modern AI Meta-Vocabulary1 hit · 2 pts
SeverityFileLineSnippetContext
MEDIUMdocs/providers/mux.md3[coder/mux](https://github.com/coder/mux) — Coder's desktop/CLI app for parallel agentic development. Mux makes its own CODE
Example Usage Blocks1 hit · 2 pts
SeverityFileLineSnippetContext
LOWmac/Scripts/package-app.sh5# Usage:COMMENT