Repository Analysis

mksglu/context-mode

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

32.6 Strong AI signal View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of mksglu/context-mode, a TypeScript project with 18,916 GitHub stars. SynthScan v2.0 examined 143,714 lines of code across 442 source files, recording 1848 pattern matches distributed across 10 syntactic categories. The overall adjusted score of 32.6 places this repository in the Strong AI signal 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).

32.6
Adjusted Score
32.6
Raw Score
100%
Time Factor
2026-07-14
Last Push
18.9K
Stars
TypeScript
Language
143.7K
Lines of Code
442
Files
1.8K
Pattern Hits
2026-07-14
Scan Date
0.07
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 31MEDIUM 1495LOW 322

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 1848 distinct pattern matches across 10 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 Separators1481 hits · 4136 pts
SeverityFileLineSnippetContext
MEDIUMtests/executor.test.ts1952// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/executor.test.ts1957// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/executor.test.ts2015// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/executor.test.ts2019// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/store.test.ts1410// ── Source metadata & TTL cache ───────────────────────────────────────COMMENT
MEDIUMtests/store.test.ts1451// ── Persistent content store lifecycle ────────────────────────────────COMMENT
MEDIUMtests/store.test.ts1513// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/store.test.ts1515// ═══════════════════════════════════════════════════════════════════════════COMMENT
MEDIUMtests/store.test.ts1758// ═══════════════════════════════════════════════════════════COMMENT
MEDIUMtests/store.test.ts1760// ═══════════════════════════════════════════════════════════COMMENT
MEDIUMtests/store.test.ts1773// ═══════════════════════════════════════════════════════════COMMENT
MEDIUMtests/store.test.ts1775// ═══════════════════════════════════════════════════════════COMMENT
MEDIUMtests/store.test.ts1958// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/store.test.ts1965// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts14// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts16// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts68// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts70// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts128// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts130// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts158// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts161// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts270// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/truncate.test.ts272// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/statusline-sqlite.test.ts291// ── Slice 2: multi-adapter aggregation ───────────────────────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts18// ── Test helpers ──────────────────────────────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts41// ── Tests ─────────────────────────────────────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts63 // ── Factory ───────────────────────────────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts158 // ── #621: native plugin must run Zod preprocessing on args ────────COMMENT
MEDIUMtests/opencode-plugin.test.ts158 // ── #621: native plugin must run Zod preprocessing on args ────────COMMENT
MEDIUMtests/opencode-plugin.test.ts267 // ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts277 // ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts408 // ── tool.execute.before ───────────────────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts479 // ── tool.execute.after ────────────────────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts528 // ── experimental.session.compacting ───────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts601 // ── experimental.chat.system.transform ────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts865 // ── Integration: before + after + compact ─────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts976 // ── OC-1 quorum substring overlap (#487) ────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts976 // ── OC-1 quorum substring overlap (#487) ────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts1005 // ── OC-2: chat.message hook (Z2) ──────────────────────────COMMENT
MEDIUMtests/opencode-plugin.test.ts1066 // ── OC-3: buildAutoInjection in compacting (Z3) ───────────COMMENT
MEDIUMtests/opencode-plugin.test.ts1219 // ── Integration: blocked tool flow ────────────────────COMMENT
MEDIUMtests/hook-runtime-resolution.test.ts230// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/hook-runtime-resolution.test.ts245// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/ecosystem-benchmark.ts28// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/ecosystem-benchmark.ts30// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/ecosystem-benchmark.ts50// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/ecosystem-benchmark.ts52// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/ecosystem-benchmark.ts403// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/ecosystem-benchmark.ts405// ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts61 // ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts63 // ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts126 // ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts128 // ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts192 // ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts194 // ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts262 // ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts264 // ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts311 // ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/live-benchmark-v04.ts313 // ─────────────────────────────────────────────────────COMMENT
1421 more matches not shown…
Cross-Language Confusion (JS/TS)31 hits · 202 pts
SeverityFileLineSnippetContext
HIGHtests/executor.test.ts383print(f"squares: {nums}")CODE
HIGHtests/executor.test.ts384print(f"sum: {sum(nums)}")CODE
HIGHtests/executor.test.ts397print(json.dumps({"count": len(data["users"])}))CODE
HIGHtests/executor.test.ts413print(f"rows: {len(rows)}, names: {[r['name'] for r in rows]}")CODE
HIGHtests/executor.test.ts427print(f"Found {len(errors)} errors: {errors}")CODE
HIGHtests/executor.test.ts441print(f"most common: {c.most_common(2)}")CODE
HIGHtests/executor.test.ts1036print(f"Users: {len(data['users'])}")CODE
HIGHtests/executor.test.ts1205print(f"lines: {len(lines)}")CODE
HIGHtests/executor.test.ts1206print(f"first: {lines[0]}")CODE
HIGHtests/executor.test.ts1207print(f"has_emoji: {'🔒' in FILE_CONTENT}")CODE
HIGHtests/executor.test.ts1269print(f"Users via file_path: {len(data['users'])}")CODE
HIGHtests/context-comparison.ts260print(f"Events: {len(rows)} | Users: {unique_users} | Avg latency: {avg_ms:.0f}ms")CODE
HIGHtests/context-comparison.ts261print(f"Error rate: {len(errors)}/{len(rows)} ({len(errors)/len(rows)*100:.1f}%)")CODE
HIGHtests/context-comparison.ts262print(f"Actions: {dict(actions.most_common())}")CODE
HIGHtests/context-comparison.ts263print(f"Statuses: {dict(statuses.most_common())}")CODE
HIGHtests/ecosystem-benchmark.ts395print(f"analytics — CSV Summary")CODE
HIGHtests/ecosystem-benchmark.ts396print(f"Events: {len(rows)} | Users: {unique_users} | Avg latency: {avg_ms:.0f}ms")CODE
HIGHtests/ecosystem-benchmark.ts397print(f"Actions: {dict(actions.most_common())}")CODE
HIGHtests/ecosystem-benchmark.ts398print(f"Statuses: {dict(statuses.most_common())}")CODE
HIGHtests/use-cases.ts409print(f"Analytics: {len(rows)} events from {unique_users} unique users")CODE
HIGHtests/use-cases.ts410print(f"Avg duration: {sum(durations)/len(durations):.0f}ms (max: {max(durations)}ms)")CODE
HIGHtests/use-cases.ts411print(f"Error rate: {len(errors)}/{len(rows)} ({len(errors)/len(rows)*100:.1f}%)")CODE
HIGHtests/use-cases.ts412print(f"\\nActions: {dict(actions.most_common())}")CODE
HIGHtests/use-cases.ts413print(f"Resources: {dict(resources.most_common())}")CODE
HIGHtests/use-cases.ts414print(f"Statuses: {dict(statuses.most_common())}")CODE
HIGHtests/use-cases.ts421print(f"\\nSlowest (avg ms):")CODE
HIGHtests/use-cases.ts423 print(f" {a}: {sum(ds)/len(ds):.0f}ms")CODE
HIGHtests/benchmark.ts234print(json.dumps({"count": len(data), "sum": round(total, 2)}))CODE
HIGHtests/benchmark.ts270print(f"filtered: {len(filtered)}")CODE
HIGHtests/core/server.test.ts899print(f"msg: {data['message']}")CODE
HIGHtests/core/server.test.ts900print(f"count: {data['count']}")CODE
Over-Commented Block182 hits · 138 pts
SeverityFileLineSnippetContext
LOWvitest.config.ts21 // near-zero crashes (vs unlimited = 3.7x but 6-7 worker kills/run).COMMENT
LOWtests/statusline-sqlite.test.ts41 (process.platform === "darwin" || process.platform === "win32") ? p.toLowerCase() : pCOMMENT
LOWtests/statusline-sqlite.test.ts221 // delivered only in the stdin JSON), and the recording hooks keyCOMMENT
LOWtests/opencode-plugin.test.ts261 const output = typeof result === "string" ? result : result.output;COMMENT
LOWtests/hook-runtime-resolution.test.ts221 const r2 = resolveHookRuntime();COMMENT
LOWtests/pi-extension.test.ts341 // until they rephrased the query.COMMENT
LOWtests/pi-extension.test.ts1381 });COMMENT
LOWtests/pi-extension.test.ts1421 "ctx_fetch_and_index",COMMENT
LOWtests/pi-extension.test.ts1501 // 3. session_shutdown does not await `_mcpBridgeReady`. If shutdownCOMMENT
LOWtests/pi-extension.test.ts1621 // signal field populated when killed by signal.COMMENT
LOWtests/statusline.test.ts221COMMENT
LOWtests/runtime.test.ts881 });COMMENT
LOWtests/core/routing.test.ts421 expect(isStructurallyBounded("echo ok\nrm -rf /")).toBe(false);COMMENT
LOWtests/core/search.test.ts2541 const results = store.searchWithFallback("validator input", 5);COMMENT
LOWtests/core/search.test.ts3361COMMENT
LOWtests/core/server.test.ts1081 // PR #365 added happy-path tests above. The two tests below pin the P0COMMENT
LOWtests/core/server.test.ts1221 }COMMENT
LOWtests/core/server.test.ts1361 // Negative guard: no place in ctx_index falls back to raw `path`.COMMENT
LOWtests/core/server.test.ts1701// Behavioral coverage of the helpers themselves lives below in thisCOMMENT
LOWtests/core/server.test.ts1741// ctx_execute_file: projectRoot env cascade parity with ctx_indexCOMMENT
LOWtests/core/server.test.ts2661 expect(beforeStats).toMatch(/scope\s*===\s*["']project["']/);COMMENT
LOWtests/core/server.test.ts2681 // strict-input-validation gate then rejects the tool call before theCOMMENT
LOWtests/core/server.test.ts2721 expect(purgeBody).toMatch(/scope:\s*z\.enum\(\[["']session["'],\s*["']project["']\]\)\.optional\(\)/);COMMENT
LOWtests/core/server.test.ts3601 });COMMENT
LOWtests/core/server.test.ts3841 expect(generated).toMatch(/delete process\.env\.http_proxy/);COMMENT
LOWtests/core/server.test.ts3921 // classified. The connect-time DNS guard catches some cases, but aCOMMENT
LOWtests/core/server.test.ts4381 expect(aResults.length).toBeGreaterThan(0);COMMENT
LOWtests/core/server.test.ts4721// ─── ctx_insight helper follow-ups (#441 follow-up) ──────────────────────────COMMENT
LOWtests/core/server.test.ts5101// readNativePluginHostSettings() — checks just the plugin array for aCOMMENT
LOWtests/core/server.test.ts5201 const joined = lines.join("");COMMENT
LOWtests/core/server.test.ts5221// Fix: register an explicit empty `tools/list` handler whenever suppressionCOMMENT
LOWtests/core/server.test.ts5261 expect(listed.tools.length).toBe(0);COMMENT
LOWtests/core/server.test.ts5321 // syntax), which is sufficient to detect forbidden tokens likeCOMMENT
LOWtests/core/server.test.ts5421 name: "cross emoji ❌",COMMENT
LOWtests/core/server.test.ts5441 // 2. Bullets MUST use markdown `- ` only. `1.`, `1-`, `* `, and `•` areCOMMENT
LOWtests/core/server.test.ts5601 // historically used inline form ("RETURNS: only your printed output.")COMMENT
LOWtests/core/server.test.ts5641// agent-facing prompt surfaces that share the same cross-LLM safety biasCOMMENT
LOWtests/core/server.test.ts5741 expect(failures).toEqual([]);COMMENT
LOWtests/core/server.test.ts5821 });COMMENT
LOWtests/core/server.test.ts5841 });COMMENT
LOWtests/core/server.test.ts5861 //COMMENT
LOWtests/core/server.test.ts5881// source form was inconsistent.COMMENT
LOWtests/core/server.test.ts5981});COMMENT
LOWtests/core/search-project-filter.test.ts361 expect(scope2).toBeUndefined();COMMENT
LOWtests/core/cli.test.ts201 // placeholder. That solved an absolute-path-bake symptom but kept theCOMMENT
LOWtests/core/cli.test.ts501 // "Native addon ABI cache missing" warning.COMMENT
LOWtests/core/cli.test.ts1041 });COMMENT
LOWtests/core/cli.test.ts1161 expect(ensureDepsIdx, "ensure-deps import statement missing").toBeGreaterThan(-1);COMMENT
LOWtests/core/cli.test.ts1261 // ── findMissingLaunchFiles — partial-install masking regression (PR #689) ──COMMENT
LOWtests/core/cli.test.ts1321 "start.mjs",COMMENT
LOWtests/core/cli.test.ts1441 //COMMENT
LOWtests/core/cli.test.ts1841 // same-user-planted symlink at .claude-plugin/plugin.json wouldCOMMENT
LOWtests/core/cli.test.ts2221 it("healPartialInstallFromMarketplace rejects deep files[] entries reached through a symlinked ancestor in the markeCOMMENT
LOWtests/core/cli.test.ts3481 }COMMENT
LOWtests/core/cli.test.ts3541COMMENT
LOWtests/core/cli.test.ts3581// prebuild-install is not on cmd.exe PATH, then dies for users withoutCOMMENT
LOWtests/core/cli.test.ts3741 // The literal "22.13" must be gone — it disagrees with hasModernSqlite().COMMENT
LOWtests/core/cli.test.ts3841COMMENT
LOWtests/core/cli.test.ts3861// Architect contract for PR #620 + slice 4:COMMENT
LOWtests/core/cli.test.ts3921 // nesting per ISSUE-609-VERDICT path examples). cli.ts usesCOMMENT
122 more matches not shown…
Hyper-Verbose Identifiers80 hits · 65 pts
SeverityFileLineSnippetContext
LOWtests/opencode-plugin.test.ts1264 async function createPluginWithRejectingLog(tempDir: string) {CODE
LOWtests/core/server.test.ts954 function spawnServerWithProjectDir(projectDirEnv: string): ChildProcess {CODE
LOWtests/core/server.test.ts6009 function spawnServerWithProjectDir(projectDirEnv: string): ChildProcess {CODE
LOWtests/plugins/openclaw.test.ts53function createMockApiWithoutRegisterHook() {CODE
LOWtests/adapters/pi-mcp-bridge.test.ts877 function extractTestTerminalEscape(str: string, pos: number): { length: number } | null {CODE
LOWtests/adapters/detect-claude-code-in-vscode.test.ts52function clearPlatformDetectionEnv() {CODE
LOWtests/adapters/codex.test.ts37function adapterWithCodexPluginRoot(pluginRoot: string): CodexAdapter {CODE
LOWtests/hooks/kiro-hooks.test.ts52function normalizeProjectPathForSessionHash(projectDir: string): string {CODE
LOWtests/hooks/kimi-hooks.test.ts47function normalizeProjectPathForSessionHash(projectDir: string): string {CODE
LOWtests/hooks/normalize-hooks-bun.test.ts46 function readEmittedPreToolUseCommand(): string {CODE
LOWtests/hooks/claude-stop.test.ts15function normalizeProjectPathForSessionHash(projectDir: string): string {CODE
LOWtests/scripts/asymmetric-drift-assert.test.ts478 "export function healSettingsEnabledPlugins() { return { healed: [] }; }",CODE
LOWtests/session/real-bytes-stats.test.ts667 function seedSessionWithProjectDir(CODE
LOWsrc/executor.ts82export function buildPowerShellScriptContent(code: string): string {CODE
LOWsrc/lifecycle.ts119export function lifecycleGuardIntervalForEnv(CODE
LOWsrc/security.ts426export function readToolPermissionPatterns(CODE
LOWsrc/security.ts766export function evaluateProjectContainment(CODE
LOWsrc/security.ts834function extractPythonSubprocessListArgs(code: string): string[] {CODE
LOWsrc/server.ts89function resolveCodexRuntimePluginRoot(fallbackRoot: string): string {CODE
LOWsrc/server.ts114function getRuntimeAwarePackageRoot(platformId?: PlatformId): string {CODE
LOWsrc/server.ts156export function shouldSuppressMcpToolsForNativePluginHost(CODE
LOWsrc/server.ts167function readNativePluginHostSettings(platform: PlatformId): Record<string, unknown> | null {CODE
LOWsrc/server.ts186function settingsHasContextModePlugin(settings: Record<string, unknown> | null | undefined): boolean {CODE
LOWsrc/server.ts191function settingsHasLegacyContextModeMcp(settings: Record<string, unknown> | null | undefined): boolean {CODE
LOWsrc/server.ts218export function emitSuppressionDiagnostic(CODE
LOWsrc/server.ts272export function registerEmptyToolsListHandler(target: McpServer = server): void {CODE
LOWsrc/server.ts367export function sanitizeSchemaForStrictClients(node: unknown): unknown {CODE
LOWsrc/server.ts387export function installStrictClientSchemaCompat(target: McpServer = server): void {CODE
LOWsrc/server.ts465export function resolveSessionIdFromSessionDB(opts?: {CODE
LOWsrc/server.ts576function configDirEnvForSessionSegments(segments: string[]): string | undefined {CODE
LOWsrc/server.ts1456export function buildBatchNodeOptionsPrefix(shellPath: string, preloadPath: string): string {CODE
LOWsrc/server.ts3900function patchPiLifetimeFromStatsFiles(lifetime: ReturnType<typeof getLifetimeStats>, sessionsDir: string): void {CODE
LOWsrc/util/project-dir.ts91export function resolveProjectDirFromTranscript(opts: {CODE
LOWsrc/util/claude-config.ts40export function resolveClaudeGlobalSettingsPath(CODE
LOWsrc/util/claude-config.ts74export function resolveAdapterGlobalSettingsPaths(CODE
LOWsrc/util/plugin-cache-integrity.ts120export function checkPluginCacheIntegritySync(CODE
LOWsrc/util/plugin-cache-integrity.ts165export async function ensurePluginCacheIntegrityLoaded(): Promise<void> {CODE
LOWsrc/search/ctx-search-schema.ts62export function buildCtxSearchInputSchema(isSharedMode: boolean) {CODE
LOWsrc/adapters/base.ts52export function resolveContextModeDataRoot(CODE
LOWsrc/adapters/detect.ts44function claudeCodeHasContextModePlugin(): boolean {CODE
LOWsrc/adapters/types.ts469export function isInProcessPluginPlatform(p: string | undefined): boolean {CODE
LOWsrc/adapters/openclaw/plugin.ts90function buildOpenClawSkillLikeGuidance(skillMarkdown: string): string {CODE
LOWsrc/adapters/openclaw/plugin.ts279function getOrCreateDB(projectDir: string): OpenClawSessionDB {CODE
LOWsrc/adapters/codex/index.ts164export function parseCodexContextModePluginRoot(raw: string): string | null {CODE
LOWsrc/adapters/codex/index.ts195function hasDeprecatedCodexHooksFeature(raw: string): boolean {CODE
LOWsrc/adapters/codex/index.ts205function hasStandaloneContextModeMcp(raw: string): boolean {CODE
LOWsrc/adapters/omp/plugin.ts110function ensureMcpServerRegistered(): void {CODE
LOWsrc/adapters/omp/plugin.ts149function getOrCreateDB(projectDir: string): SessionDB {CODE
LOWsrc/adapters/pi/mcp-bridge.ts87export function resolveJsRuntimeForBridge(deps: ResolveDeps = {}): string | null {CODE
LOWsrc/adapters/pi/mcp-bridge.ts324function createContextModeCallRenderer(toolName: string) {CODE
LOWsrc/adapters/pi/mcp-bridge.ts335function createContextModeResultRenderer(toolName: string) {CODE
LOWsrc/adapters/pi/extension.ts212function getOrCreateDB(projectDir: string): SessionDB {CODE
LOWsrc/adapters/antigravity-cli/index.ts36export function antigravityCliMcpConfigPath(): string {CODE
LOWsrc/adapters/antigravity-cli/index.ts58function antigravityCliPluginMcpPath(): string {CODE
LOWsrc/adapters/antigravity-cli/index.ts61function antigravityCliPluginHooksPath(): string {CODE
LOWsrc/adapters/antigravity-cli/index.ts119function matcherCoversAgyPreToolUse(matcher: unknown): boolean {CODE
LOWsrc/adapters/kimi/index.ts193function buildKimiHookFromRegistration(CODE
LOWsrc/adapters/opencode/plugin.ts216function systemHasRoutingInstructions(system: string[]): boolean {CODE
LOWsrc/session/snapshot.ts437function buildRecentMessagesSection(userPromptEvents: StoredEvent[]): string {CODE
LOWsrc/session/extract.ts609function extractCommitMessageFromCommand(cmd: string): string | null {CODE
20 more matches not shown…
Verbosity Indicators26 hits · 43 pts
SeverityFileLineSnippetContext
LOWtests/store.test.ts102 // Step 1: Create a DB with the OLD schema (4-column FTS5)COMMENT
LOWtests/store.test.ts148 // Step 2: Open with ContentStore — migration should triggerCOMMENT
LOWtests/store.test.ts151 // Step 3: Verify migration happened — new columns existCOMMENT
LOWtests/util/postinstall-heal.test.ts432 // Step 1: cpSync the clean placeholder file from tmpdir → real pluginCOMMENT
LOWtests/util/postinstall-heal.test.ts442 // Step 2: normalize against the REAL pluginRoot — this is the cli.tsCOMMENT
LOWtests/session/session-extract.test.ts2271 // Step 1: Error occursCOMMENT
LOWtests/session/session-extract.test.ts2281 // Step 2: Successful same-tool callCOMMENT
LOWtests/session/session-pipeline.test.ts40 // Step 1: Extract events from multiple tool callsCOMMENT
LOWtests/session/session-pipeline.test.ts68 // Step 2: Insert all events into DBCOMMENT
LOWtests/session/session-pipeline.test.ts73 // Step 3: Build snapshot from stored eventsCOMMENT
LOWtests/session/session-pipeline.test.ts77 // Step 4: Upsert resumeCOMMENT
LOWtests/session/session-pipeline.test.ts80 // Step 5: Verify resume XML structureCOMMENT
LOWtests/session/session-pipeline.test.ts85 // Step 6: Verify XML wrapperCOMMENT
LOWtests/session/session-pipeline.test.ts89 // Step 8: Verify resume consumed lifecycleCOMMENT
LOWsrc/cli.ts1258 // Step 0: Sync the marketplace clone (#418).COMMENT
LOWsrc/cli.ts1300 // Step 1: Pull latest from GitHubCOMMENT
LOWsrc/cli.ts1360 // Step 2: Install dependencies + buildCOMMENT
LOWsrc/cli.ts1376 // Step 3: Update in-placeCOMMENT
LOWsrc/cli.ts1874 // Step 3: Backup settings — adapter-awareCOMMENT
LOWsrc/cli.ts1889 // Step 4: Configure hooks — adapter-awareCOMMENT
LOWsrc/cli.ts1903 // Step 5: Set hook script permissions — adapter-awareCOMMENT
LOWsrc/cli.ts1928 // Step 6: ReportCOMMENT
LOWsrc/cli.ts1947 // Step 7: Run doctorCOMMENT
LOWsrc/store.ts1348 // Step 0: Auto-refresh stale file-backed sources before searchingCOMMENT
LOWsrc/store.ts1359 // Step 1: RRF fusion (porter OR + trigram OR → merge)COMMENT
LOWsrc/store.ts1367 // Step 2: Fuzzy correction → RRF re-runCOMMENT
Structural Annotation Overuse26 hits · 43 pts
SeverityFileLineSnippetContext
LOWtests/store.test.ts102 // Step 1: Create a DB with the OLD schema (4-column FTS5)COMMENT
LOWtests/store.test.ts148 // Step 2: Open with ContentStore — migration should triggerCOMMENT
LOWtests/store.test.ts151 // Step 3: Verify migration happened — new columns existCOMMENT
LOWtests/util/postinstall-heal.test.ts432 // Step 1: cpSync the clean placeholder file from tmpdir → real pluginCOMMENT
LOWtests/util/postinstall-heal.test.ts442 // Step 2: normalize against the REAL pluginRoot — this is the cli.tsCOMMENT
LOWtests/session/session-extract.test.ts2271 // Step 1: Error occursCOMMENT
LOWtests/session/session-extract.test.ts2281 // Step 2: Successful same-tool callCOMMENT
LOWtests/session/session-pipeline.test.ts40 // Step 1: Extract events from multiple tool callsCOMMENT
LOWtests/session/session-pipeline.test.ts68 // Step 2: Insert all events into DBCOMMENT
LOWtests/session/session-pipeline.test.ts73 // Step 3: Build snapshot from stored eventsCOMMENT
LOWtests/session/session-pipeline.test.ts77 // Step 4: Upsert resumeCOMMENT
LOWtests/session/session-pipeline.test.ts80 // Step 5: Verify resume XML structureCOMMENT
LOWtests/session/session-pipeline.test.ts85 // Step 6: Verify XML wrapperCOMMENT
LOWtests/session/session-pipeline.test.ts89 // Step 8: Verify resume consumed lifecycleCOMMENT
LOWsrc/cli.ts1258 // Step 0: Sync the marketplace clone (#418).COMMENT
LOWsrc/cli.ts1300 // Step 1: Pull latest from GitHubCOMMENT
LOWsrc/cli.ts1360 // Step 2: Install dependencies + buildCOMMENT
LOWsrc/cli.ts1376 // Step 3: Update in-placeCOMMENT
LOWsrc/cli.ts1874 // Step 3: Backup settings — adapter-awareCOMMENT
LOWsrc/cli.ts1889 // Step 4: Configure hooks — adapter-awareCOMMENT
LOWsrc/cli.ts1903 // Step 5: Set hook script permissions — adapter-awareCOMMENT
LOWsrc/cli.ts1928 // Step 6: ReportCOMMENT
LOWsrc/cli.ts1947 // Step 7: Run doctorCOMMENT
LOWsrc/store.ts1348 // Step 0: Auto-refresh stale file-backed sources before searchingCOMMENT
LOWsrc/store.ts1359 // Step 1: RRF fusion (porter OR + trigram OR → merge)COMMENT
LOWsrc/store.ts1367 // Step 2: Fuzzy correction → RRF re-runCOMMENT
Modern AI Meta-Vocabulary8 hits · 28 pts
SeverityFileLineSnippetContext
MEDIUMtests/core/search.test.ts247 content: "# Microservices\n\nThe containerized orchestration platform manages deployments.\n\n" +CODE
MEDIUMtests/core/search.test.ts248 "# Monitoring\n\nPrometheus collects containerized metrics from orchestration layer.\n\n" +CODE
MEDIUMtests/core/search.test.ts249 "# Scaling\n\nHorizontal pod autoscaling uses containerized orchestration policies.",CODE
MEDIUMtests/adapters/kiro.test.ts229 // ── Slice Kiro-3 (Z9) reverted: NO scaffold deploy ────────COMMENT
MEDIUMtests/adapters/kiro.test.ts230 // Initial v1.0.107 SE pass deployed a 10-file generic SDD scaffold (mirror ofCOMMENT
MEDIUM.claude/skills/context-mode-ops/SKILL.md251### refs/ — Platform Evidence Base (anti-hallucination ground truth)COMMENT
MEDIUMsrc/search/flood-guard.ts9 * Issue #769: a parallel multi-agent fan-out (Claude Code Task/Workflow)COMMENT
MEDIUMsrc/session/analytics.ts297 * #1 Context Savings Total — bytes kept out of context window.COMMENT
AI Slop Vocabulary4 hits · 14 pts
SeverityFileLineSnippetContext
MEDIUMtests/stale-detection.test.ts62 writeFileSync(filePath, "# Database Guide\n\nPostgreSQL connection pooling best practices for production workloads."CODE
MEDIUMtests/session/session-extract.test.ts795 // expressed as a robust universal-rule detector (issue #535). They areCOMMENT
MEDIUM.github/workflows/tier2-e2e-smoke.yml3# Tier-1 (mock harness, no LLM, free) lives in tests/pi-extension.test.ts andCOMMENT
MEDIUMsrc/adapters/pi/extension.ts331// The robust signal is Pi's agent lifecycle itself. `before_agent_start` firesCOMMENT
Fake / Example Data8 hits · 6 pts
SeverityFileLineSnippetContext
LOWtests/store.test.ts1198 `Paragraph ${i + 1}. ${"Lorem ipsum dolor sit amet. ".repeat(20)}`CODE
LOWtests/store.test.ts1198 `Paragraph ${i + 1}. ${"Lorem ipsum dolor sit amet. ".repeat(20)}`CODE
LOWtests/core/search.test.ts1797 const padding = preamble.padEnd(2000, " Lorem ipsum dolor sit amet.");CODE
LOWtests/core/search.test.ts1797 const padding = preamble.padEnd(2000, " Lorem ipsum dolor sit amet.");CODE
LOWtests/core/search.test.ts2595 "Lorem ipsum dolor sit amet. The cache invalidation pipeline runs on every write.",CODE
LOWtests/core/search.test.ts2595 "Lorem ipsum dolor sit amet. The cache invalidation pipeline runs on every write.",CODE
LOWtests/core/search.test.ts2600 "Lorem ipsum dolor sit amet. The invalidation step is followed by a cache flush.",CODE
LOWtests/core/search.test.ts2600 "Lorem ipsum dolor sit amet. The invalidation step is followed by a cache flush.",CODE
Excessive Try-Catch Wrapping2 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUMtests/context-comparison.ts261print(f"Error rate: {len(errors)}/{len(rows)} ({len(errors)/len(rows)*100:.1f}%)")CODE
MEDIUMtests/use-cases.ts411print(f"Error rate: {len(errors)}/{len(rows)} ({len(errors)/len(rows)*100:.1f}%)")CODE