Repository Analysis

activeloopai/hivemind

Hivemind turns your traces into reusable skills across agents

9.9 Low AI signal View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of activeloopai/hivemind, a TypeScript project with 1,588 GitHub stars. SynthScan v2.0 examined 164,909 lines of code across 704 source files, recording 698 pattern matches distributed across 11 syntactic categories. The overall adjusted score of 9.9 places this repository in the Low 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).

9.9
Adjusted Score
9.9
Raw Score
100%
Time Factor
2026-08-21
Last Push
1.6K
Stars
TypeScript
Language
164.9K
Lines of Code
704
Files
698
Pattern Hits
2026-08-29
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 454LOW 244

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 698 distinct pattern matches across 11 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 Separators446 hits · 1346 pts
SeverityFileLineSnippetContext
MEDIUMtests/claude-code/pre-tool-use-baseline-cloud.test.ts242 // ── Regression coverage anchored in a real benchmark run ─────────────COMMENT
MEDIUMtests/claude-code/pre-tool-use-baseline-cloud.test.ts312 // ── writeReadCacheFile security guard ─────────────────────────────────────COMMENT
MEDIUMtests/claude-code/pre-tool-use-baseline-cloud.test.ts374 // ── /index.md fallback lives in virtual-table-query.ts only ───────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts24// ── Mock clients ──────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts139// ── fileCount ───────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts147// ── Graph VFS bridge ──────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts231// ── Goals bootstrap ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts247// ── Bootstrap null-coalescing (defensive ?? "" paths) ────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts285// ── KPIs bootstrap ──────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts299// ── Goal write routing (upsertRow → upsertGoalRow) ───────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts324// ── KPI write routing (upsertRow → upsertKpiRow) ─────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts345// ── rm goal soft-close ────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts369// ── mv goal status transition ────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts398// ── flush failure re-queue ────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts411// ── embeddings-disabled flush path ────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts424// ── virtual index with sessions section ────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts454// ── session reads (concatenation) ──────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts498// ── readFile / readFileBuffer remaining branches ──────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts532// ── metadata / unsupported ops ─────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts558// ── write guards / mkdir ───────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs-coverage.test.ts577// ── rm error paths ─────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/pre-tool-use.test.ts51// ── Read commands: fast path (direct SQL) or shell fallback ──────────────────COMMENT
MEDIUMtests/claude-code/pre-tool-use.test.ts174// ── Unsafe commands: should return guidance (not deny) ──────────────────────COMMENT
MEDIUMtests/claude-code/pre-tool-use.test.ts314// ── Deeplake CLI commands: no longer supported, should return guidance ────────COMMENT
MEDIUMtests/claude-code/pre-tool-use.test.ts340// ── Non-memory commands: should pass through (no output) ────────────────────COMMENT
MEDIUMtests/claude-code/pre-tool-use.test.ts364// ── Non-Bash tools targeting memory ─────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/pre-tool-use.test.ts407// ── Path variants ───────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/pre-tool-use.test.ts435// ── Write / Edit on memory paths: deny with Bash guidance ───────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts16// ── Mock ManagedClient ────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts226// ── Helpers ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts237// ── goal/kpi namespace isolation from the generic memory table ────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts364// ── Bootstrap ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts393// ── Text reads ────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts414// ── Buffer reads ──────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts437// ── Writes ────────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts483// ── appendFile ────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts498// ── Directories ───────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts543// ── stat ──────────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts565// ── rm ────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts609// ── cp / mv ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts634// ── path resolution ───────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts657// ── prefetch ────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts800// ── Session reads: bodyless rows must not read as silent empty files ─────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts867// ── Session reads: local event cache is preferred over the fat DB read ───────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts985// ── Upsert: id stability & dates ─────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts1102// ── no-op / unsupported ops ───────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts1120// ── Virtual index.md ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts1256// ── writeFileWithMeta ────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts1299// ── readdirWithFileTypes ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/deeplake-fs.test.ts1326// ── cp recursive ─────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/cli-context.test.ts81// ── help ────────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/cli-context.test.ts101// ── login gating ────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/cli-context.test.ts112// ── output ──────────────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/grep-core.test.ts16// ── searchDocs (per-file docs search — the docs/find backend) ─────────────────COMMENT
MEDIUMtests/claude-code/grep-core.test.ts89// ── normalizeContent ────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/grep-core.test.ts505// ── buildPathFilter ─────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/grep-core.test.ts558// ── compileGrepRegex ────────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/grep-core.test.ts594// ── refineGrepMatches ───────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/grep-core.test.ts685// ── searchDeeplakeTables ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/claude-code/grep-core.test.ts840// ── grepBothTables (end-to-end convenience wrapper) ─────────────────────────COMMENT
386 more matches not shown…
Over-Commented Block145 hits · 145 pts
SeverityFileLineSnippetContext
LOWvitest.config.ts1import { defineConfig } from "vitest/config";COMMENT
LOWvitest.config.ts61 // Both are excluded from vitest because they need a live DeeplakeCOMMENT
LOWvitest.config.ts201 lines: 90,COMMENT
LOWvitest.config.ts221 //COMMENT
LOWvitest.config.ts341 // query spy. Actuals: statements 95, branches 87, functions 91, lines 98.COMMENT
LOWvitest.config.ts361 // defensive guard. Hold at 89.COMMENT
LOWvitest.config.ts401 "src/hooks/cursor/session-start.ts": { statements: 80, branches: 80, functions: 80, lines: 80 },COMMENT
LOWvitest.config.ts421 // few error-recovery branches (lock-cleanup races, log-write failuresCOMMENT
LOWvitest.config.ts441 "src/skillify/push.ts": { statements: 90, branches: 90, functions: 90, lines: 90 },COMMENT
LOWvitest.config.ts481 "src/notifications/delivery/index.ts": { statements: 90, branches: 90, functions: 90, lines: 90 },COMMENT
LOWvitest.config.ts501 // triggered without forking subprocesses; everything else holds at 90+.COMMENT
LOWvitest.config.ts521 "src/skillify/spawn-backfill-memory-worker.ts": { statements: 90, branches: 90, functions: 90, lines: 90 },COMMENT
LOWvitest.config.ts541 // rows for. Calibrated to actual coverage.COMMENT
LOWvitest.config.ts561 // (43 tests across extractor/snapshot/command).COMMENT
LOWharnesses/openclaw/src/index.ts1function definePluginEntry<T>(entry: T): T { return entry; }COMMENT
LOWharnesses/openclaw/src/index.ts101COMMENT
LOWharnesses/openclaw/src/index.ts321let authUrl: string | null = null;COMMENT
LOWharnesses/openclaw/src/index.ts421let skillsTable = "skills"; // lazy-created on first INSERT by the workerCOMMENT
LOWharnesses/openclaw/src/index.ts441// shape here, keyed off the bundled sibling `skillify-worker.js`. Mining isCOMMENT
LOWharnesses/openclaw/src/index.ts481 const project = channel || "openclaw";COMMENT
LOWharnesses/openclaw/src/index.ts761 // become `undefined` and fall back to defaults.COMMENT
LOWharnesses/openclaw/src/index.ts1441 // would block the agent for the full timeout before it could reply.COMMENT
LOWharnesses/openclaw/src/index.ts1581 logger.info?.(`Auto-captured ${newMessages.length} messages`);COMMENT
LOWharnesses/codex/install.sh1#!/bin/bashCOMMENT
LOWharnesses/pi/extension-source/hivemind.ts1// @ts-nocheck — distributed as raw .ts; pi's runtime loads + compiles it.COMMENT
LOWharnesses/pi/extension-source/hivemind.ts301COMMENT
LOWharnesses/pi/extension-source/hivemind.ts501 // Cases 10 / 11 — request timeout / daemon error → null.COMMENT
LOWharnesses/pi/extension-source/hivemind.ts601 }COMMENT
LOWharnesses/pi/extension-source/hivemind.ts961 releaseSummaryLock(sessionId);COMMENT
LOWharnesses/pi/extension-source/hivemind.ts1001 // src/skillify/state.ts:tryAcquireWorkerLock and releases it on exit (withCOMMENT
LOWharnesses/pi/extension-source/hivemind.ts1461 // Event shapes per pi-coding-agent/dist/core/extensions/types.d.ts:COMMENT
LOWtests/test-setup.ts1// Global vitest setup. Runs once before any test file.COMMENT
LOWtests/claude-code/pre-tool-use-baseline-cloud.test.ts241COMMENT
LOWtests/claude-code/notifications.test.ts481 const payload = JSON.parse(writes[0]);COMMENT
LOWtests/claude-code/notifications.test.ts881// ---------------------------------------------------------------------------COMMENT
LOWtests/claude-code/grep-core.test.ts1401// score scale was overpowering cosine in the UNION). The field wasCOMMENT
LOWtests/claude-code/summary-state.test.ts581COMMENT
LOWtests/claude-code/wiki-worker-plugin-version.test.ts221COMMENT
LOWtests/claude-code/skillify-state.test.ts381});COMMENT
LOWtests/claude-code/skillify-bundle-scan.test.ts101 for (const agent of AGENTS) {COMMENT
LOWtests/claude-code/session-start-setup-hook.test.ts41}));COMMENT
LOWtests/claude-code/session-start-setup-hook.test.ts321COMMENT
LOWtests/claude-code/session-start-hook.test.ts141 debugLogMock.mockReset();COMMENT
LOWtests/claude-code/session-start-hook.test.ts421 // (autoUpdate-internal failure modes — network down, missing binary,COMMENT
LOWtests/openclaw/auto-recall.test.ts141 "hivemind_search", "hivemind_read", "hivemind_index",COMMENT
LOWtests/shared/standalone-embed-client.test.ts1// Unit tests for the standalone embed client used by pi + openclaw.COMMENT
LOWtests/shared/graph/path.test.ts1import { describe, it, expect } from "vitest";COMMENT
LOWtests/shared/graph/neighborhood.test.ts1import { describe, it, expect } from "vitest";COMMENT
LOWtests/shared/graph/session-context.test.ts241 });COMMENT
LOWtests/shared/graph/tour.test.ts21 ...overrides,COMMENT
LOWtests/cli/cli-embeddings.test.ts221 // fix gates the SIGTERM on `_isDaemonAliveOnSocket` — if the UDS pathCOMMENT
LOWtests/cli/cli-install-openclaw.test.ts61 expect(existsSync(join(root, "skills", "hivemind.md"))).toBe(true);COMMENT
LOWtests/cli/cli-bundle-runtime.test.ts1import { describe, it, expect, beforeAll, afterAll } from "vitest";COMMENT
LOWtests/cli/cli-update.test.ts401 expect(() => detectInstallKind("/cli.js")).not.toThrow();COMMENT
LOWtests/cli/cli-update.test.ts421 //COMMENT
LOWtests/pi/pi-extension-source.test.ts141 it("treats an empty pidfile as 'writer in progress' to avoid duplicate spawns", () => {COMMENT
LOWtests/scripts/marketplace-source-path.test.ts1import { describe, it, expect } from "vitest";COMMENT
LOW…ledge/private/infrastructure/monorepo-build-release.md201COMMENT
LOWscripts/verify-install.sh1#!/usr/bin/env bashCOMMENT
LOW.github/workflows/ci.yaml61 # 3. wiki-worker summary generation failed on Windows because theCOMMENT
85 more matches not shown…
Hyper-Verbose Identifiers70 hits · 70 pts
SeverityFileLineSnippetContext
LOWembeddings/embed-daemon.js48async function defaultImportTransformers(canonical = _importFromCanonicalSharedDeps, bare = _importFromBareSpecifier) {CODE
LOWharnesses/openclaw/src/setup-config.ts37export function isAllowlistCoveringHivemind(alsoAllow: unknown): boolean {CODE
LOWharnesses/openclaw/src/setup-config.ts58export function isPluginsAllowMissingHivemind(allow: unknown): boolean {CODE
LOWharnesses/openclaw/src/setup-config.ts83export function ensureHivemindAllowlisted(): SetupResult {CODE
LOWharnesses/openclaw/src/graph-lifecycle.ts72export function spawnOpenclawGraphPullWorker(CODE
LOWharnesses/openclaw/src/graph-lifecycle.ts101export function resetGraphPullSpawnedForTests(): void {CODE
LOWharnesses/openclaw/src/index.ts466function migrateOpenclawSkillifyLegacyStateDir(): void {CODE
LOWharnesses/openclaw/src/index.ts504function tryAcquireOpenclawSkillifyLock(projectKey: string): boolean {CODE
LOWharnesses/openclaw/src/index.ts614function spawnOpenclawSkillifyWorker(a: OpenclawSpawnArgs): boolean {CODE
LOWharnesses/pi/extension-source/hivemind.ts203async function healDriftedOrgTokenInline(creds: Creds): Promise<Creds> {CODE
LOWharnesses/pi/extension-source/hivemind.ts427function maybeCleanupOwnPlaceholderInline(): void {CODE
LOWharnesses/pi/extension-source/hivemind.ts1062function maybeTriggerPeriodicSummary(creds: Creds, sessionId: string, cwd: string): void {CODE
LOWharnesses/pi/extension-source/hivemind.ts1196function piCountLocalManifestEntries(): number {CODE
LOW…-005-cursor-skillify-bridge/qa/2026-06-13-qa-report.md85export function listLocalSkillsForPromoter(): Array<{ dirName: string; scope: "global" | "project"; path: string }> {CODE
LOWsrc/deeplake-api.ts115function maybeSignalBalanceExhausted(status: number, bodyText: string): void {CODE
LOWsrc/embeddings/standalone-embed-client.ts254function maybeCleanupOwnPlaceholder(pidPath: string): void {CODE
LOWsrc/embeddings/self-heal.ts46export function ensurePluginNodeModulesLink(opts: SelfHealOptions): SelfHealResult {CODE
LOWsrc/embeddings/disable.ts38function defaultResolveTransformers(): void {CODE
LOWsrc/embeddings/client.ts474export function isTransformersMissingError(err: string): boolean {CODE
LOWsrc/embeddings/nomic.ts87export async function defaultImportTransformers(CODE
LOWsrc/shell/grep-core.ts536export function buildPathFilterForTargets(targetPaths: string[]): string {CODE
LOWsrc/shell/grep-core.ts553export function extractRegexLiteralPrefilter(pattern: string): string | null {CODE
LOWsrc/shell/grep-core.ts586export function extractRegexAlternationPrefilters(pattern: string): string[] | null {CODE
LOWsrc/shell/grep-interceptor.ts24function resolveGrepEmbedDaemonPath(): string {CODE
LOWsrc/shell/grep-interceptor.ts44function patternIsSemanticFriendly(pattern: string, fixedString: boolean): boolean {CODE
LOWsrc/graph/extract/python.ts376function makeNodeWithExplicitLabel(relativePath: string, idName: string, label: string, kind: NodeKind, node: PyNode, exCODE
LOWsrc/graph/extract/typescript.ts675function makeNodeWithExplicitLabel(CODE
LOWsrc/utils/plugin-cache.ts29export function resolveVersionedPluginDir(bundleDir: string): {CODE
LOWsrc/utils/plugin-cache.ts197export function readCurrentVersionFromManifest(manifestPath: string): string | null {CODE
LOWsrc/cli/install-claude.ts133function isBrokenHivemindHookEntry(h: HookEntry): boolean {CODE
LOWsrc/cli/install-claude.ts160export function cleanupBrokenSettingsHooks(): { removed: number; events: string[] } {CODE
LOWsrc/cli/install-codex.ts125function isForeignHivemindHookEntry(entry: unknown, pluginDir: string = PLUGIN_DIR): boolean {CODE
LOWsrc/cli/install-codex.ts190function reportForeignHivemindHooks(existing: Record<string, unknown>): void {CODE
LOWsrc/cli/skillify-spec.ts212export function renderSubcommandUsageBlock(): string {CODE
LOWsrc/skillify/local-manifest.ts97export function countLocalManifestEntries(path: string = LOCAL_MANIFEST_PATH): number {CODE
LOWsrc/skillify/legacy-cap-migration.ts263export function migrateLegacyCappedInstalls(): LegacyCapResult {CODE
LOWsrc/skillify/unpull.ts255function decideTargetForManifestEntry(CODE
LOWsrc/skillify/existing-skills.ts97export function renderExistingSkillsBlock(cwd: string, charCap: number): ExistingSkillsBlock {CODE
LOWsrc/skillify/scope-promotion.ts22export function isCrossAuthorMergeVerdict(args: {CODE
LOWsrc/skillify/pending-memory-manifest.ts100export function readPendingMemoryManifest(CODE
LOWsrc/skillify/pending-memory-manifest.ts123export function writePendingMemoryManifest(CODE
LOWsrc/skillify/pull.ts157export function isMissingContributorsColumnError(message: string | undefined): boolean {CODE
LOWsrc/hooks/wiki-worker-spawn.ts64export function buildTrailingPromptInvocation(bin: string, flags: string[], prompt: string): ClaudeInvocation {CODE
LOWsrc/hooks/wiki-worker-spawn.ts88export function buildStdinPromptInvocation(bin: string, flags: string[], prompt: string): ClaudeInvocation {CODE
LOWsrc/hooks/wiki-worker-spawn.ts105export function buildClaudeStdinInvocation(claudeBin: string, prompt: string): ClaudeInvocation {CODE
LOWsrc/hooks/virtual-table-query.ts248export async function listVirtualPathRowsForDirs(CODE
LOWsrc/hooks/bash-command-compiler.ts139export function hasUnsupportedRedirection(segment: string): boolean {CODE
LOWsrc/hooks/bash-command-compiler.ts187function isValidPipelineHeadTailStage(stage: string): boolean {CODE
LOWsrc/hooks/bash-command-compiler.ts413export async function executeCompiledBashCommand(CODE
LOWsrc/hooks/capture.ts262function maybeTriggerPeriodicSummary(sessionId: string, cwd: string, config: Config): void {CODE
LOWsrc/hooks/session-event-cache.ts45export function sessionEventCacheDisabled(): boolean {CODE
LOWsrc/hooks/session-event-cache.ts93export function pruneStaleSessionEventCaches(CODE
LOWsrc/hooks/session-queue.ts450export function tryAcquireSessionDrainLock(CODE
LOWsrc/hooks/session-queue.ts597function isEnsureSessionsTableRetryable(error: unknown): boolean {CODE
LOWsrc/hooks/session-queue.ts629export function clearSessionWriteDisabled(CODE
LOWsrc/hooks/session-queue.ts658function getSessionWriteDisabledPath(queueDir: string, sessionsTable: string): string {CODE
LOWsrc/hooks/version-check.ts63export function readFreshCachedLatestVersion(CODE
LOWsrc/hooks/grep-direct.ts36function patternIsSemanticFriendly(pattern: string, fixedString: boolean): boolean {CODE
LOWsrc/hooks/pre-tool-use.ts128function buildRetryGuidanceDecision(toolName: string): ClaudePreToolDecision {CODE
LOWsrc/hooks/cursor/capture.ts223function maybeTriggerPeriodicSummary(sessionId: string, cwd: string, config: Config): void {CODE
10 more matches not shown…
Structural Annotation Overuse15 hits · 28 pts
SeverityFileLineSnippetContext
LOWtests/claude-code/skillify-pull.test.ts1103 // Step 1: pre-pulled state — SKILL.md on disk + manifest entryCOMMENT
LOWtests/claude-code/skillify-pull.test.ts1113 // Step 2: install codex (creates the marker dir the detector keys on).COMMENT
LOWtests/claude-code/skillify-pull.test.ts1116 // Step 3: re-pull. Action will be "skipped" because local versionCOMMENT
LOWtests/claude-code/session-summary.test.ts286 // Step 1: create initial placeholder (session-start)COMMENT
LOWtests/claude-code/session-summary.test.ts298 // Step 2: simulate session-end uploading a completed summaryCOMMENT
LOWlibrary/knowledge/private/ai/wiki-summary-workers.md53### Step 1: fetch session eventsCOMMENT
LOWlibrary/knowledge/private/ai/wiki-summary-workers.md67### Step 2: check for an existing summaryCOMMENT
LOWlibrary/knowledge/private/ai/wiki-summary-workers.md71### Step 3: run the gate promptCOMMENT
LOWlibrary/knowledge/private/ai/wiki-summary-workers.md85### Step 4: embed and uploadCOMMENT
LOWlibrary/knowledge/private/ai/skillify-pipeline.md46### Step 1: fetch candidate sessionsCOMMENT
LOWlibrary/knowledge/private/ai/skillify-pipeline.md55### Step 2: extract prompt/answer pairsCOMMENT
LOWlibrary/knowledge/private/ai/skillify-pipeline.md59### Step 3: build and run the gate promptCOMMENT
LOWlibrary/knowledge/private/ai/skillify-pipeline.md82### Step 4: write the skill fileCOMMENT
LOWlibrary/knowledge/private/ai/skillify-pipeline.md93### Step 5: record to the Deeplake skills tableCOMMENT
LOWsrc/commands/graph.ts578 // Step 8: after the snapshot is fresh on disk, refresh docs IF the userCOMMENT
Modern AI Meta-Vocabulary5 hits · 14 pts
SeverityFileLineSnippetContext
MEDIUMREADME.md255[Claude Cowork](https://support.claude.com/en/articles/11503834) is Anthropic's agentic assistant inside the Claude DeskCODE
MEDIUMtests/cli/install-helpers.test.ts326 // Both stale bodies gone; the surviving scaffold is exactly the user'sCOMMENT
MEDIUMtests/cli/install-helpers.test.ts407 // Exact remainder: both blocks removed, user scaffold intact.COMMENT
MEDIUMsrc/cli/install-cowork.ts8// Cowork is Anthropic's agentic desktop assistant, hosted inside theCOMMENT
MEDIUMsrc/cli/util.ts130 // claude_cowork — Anthropic's agentic desktop assistant, hosted in theCOMMENT
Verbosity Indicators6 hits · 12 pts
SeverityFileLineSnippetContext
LOWtests/claude-code/skillify-pull.test.ts1103 // Step 1: pre-pulled state — SKILL.md on disk + manifest entryCOMMENT
LOWtests/claude-code/skillify-pull.test.ts1113 // Step 2: install codex (creates the marker dir the detector keys on).COMMENT
LOWtests/claude-code/skillify-pull.test.ts1116 // Step 3: re-pull. Action will be "skipped" because local versionCOMMENT
LOWtests/claude-code/session-summary.test.ts286 // Step 1: create initial placeholder (session-start)COMMENT
LOWtests/claude-code/session-summary.test.ts298 // Step 2: simulate session-end uploading a completed summaryCOMMENT
LOWsrc/commands/graph.ts578 // Step 8: after the snapshot is fresh on disk, refresh docs IF the userCOMMENT
AI Slop Vocabulary3 hits · 8 pts
SeverityFileLineSnippetContext
MEDIUM…s/claude-code/skillify-session-start-injection.test.ts294 // source order — robust to unrelated code landing between them, unlike aCOMMENT
MEDIUMsrc/shell/grep-interceptor.ts147 // before giving up to the in-memory fallback. Keeps behavior robust whenCOMMENT
MEDIUMsrc/graph/git-hook-install.ts35 "# mkdir is robust against first-run: $HOME/.hivemind may not exist yet,",CODE
Fake / Example Data3 hits · 3 pts
SeverityFileLineSnippetContext
LOW…sts/claude-code/shell-bundle-sql-trace-silence.test.ts48 HIVEMIND_TOKEN: "fake-token-for-trace-test",CODE
LOWlibrary/qa/security/2026-06-12-security-audit.md108- `"orgName": "Acme Inc"` - standard placeholderCODE
LOW…brary/knowledge/private/security/credential-storage.md74 "orgName": "Acme Inc",CODE
Overly Generic Function Names3 hits · 3 pts
SeverityFileLineSnippetContext
LOWtests/shared/graph/python.test.ts18 "def run():\n return helper()\n\ndef helper():\n return 1\n\nclass Service:\n def start(self):\n rCODE
LOWtests/shared/graph/python.test.ts32 "def run():\n return helper()\n\ndef helper():\n return 1\n\nclass Service:\n def start(self):\n rCODE
LOWsrc/dashboard/serve.ts56function handleRequest(html: string) {CODE
Example Usage Blocks1 hit · 2 pts
SeverityFileLineSnippetContext
LOWscripts/verify-install.sh12# Usage:COMMENT
Redundant / Tautological Comments1 hit · 2 pts
SeverityFileLineSnippetContext
LOW.github/workflows/release.yaml72 # Check if release exists, Set outputs) read the post-bump state.COMMENT