Hivemind turns your traces into reusable skills across agents
This report presents the forensic synthetic code analysis of activeloopai/hivemind, a TypeScript project with 1,477 GitHub stars. SynthScan v2.0 examined 154,216 lines of code across 668 source files, recording 656 pattern matches distributed across 11 syntactic categories. The overall adjusted score of 10.1 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).
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.
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.
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.
The scanner identified 656 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.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | tests/claude-code/pre-tool-use-baseline-cloud.test.ts | 242 | // ── Regression coverage anchored in a real benchmark run ───────────── | COMMENT |
| MEDIUM | tests/claude-code/pre-tool-use-baseline-cloud.test.ts | 312 | // ── writeReadCacheFile security guard ───────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/pre-tool-use-baseline-cloud.test.ts | 374 | // ── /index.md fallback lives in virtual-table-query.ts only ─────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 24 | // ── Mock clients ────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 139 | // ── fileCount ─────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 147 | // ── Graph VFS bridge ────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 231 | // ── Goals bootstrap ───────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 247 | // ── Bootstrap null-coalescing (defensive ?? "" paths) ──────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 285 | // ── KPIs bootstrap ────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 299 | // ── Goal write routing (upsertRow → upsertGoalRow) ─────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 324 | // ── KPI write routing (upsertRow → upsertKpiRow) ───────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 345 | // ── rm goal soft-close ──────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 369 | // ── mv goal status transition ──────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 398 | // ── flush failure re-queue ──────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 411 | // ── embeddings-disabled flush path ──────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 424 | // ── virtual index with sessions section ──────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 454 | // ── session reads (concatenation) ────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 498 | // ── readFile / readFileBuffer remaining branches ────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 532 | // ── metadata / unsupported ops ───────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 558 | // ── write guards / mkdir ─────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs-coverage.test.ts | 577 | // ── rm error paths ───────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/pre-tool-use.test.ts | 51 | // ── Read commands: fast path (direct SQL) or shell fallback ────────────────── | COMMENT |
| MEDIUM | tests/claude-code/pre-tool-use.test.ts | 174 | // ── Unsafe commands: should return guidance (not deny) ────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/pre-tool-use.test.ts | 314 | // ── Deeplake CLI commands: no longer supported, should return guidance ──────── | COMMENT |
| MEDIUM | tests/claude-code/pre-tool-use.test.ts | 340 | // ── Non-memory commands: should pass through (no output) ──────────────────── | COMMENT |
| MEDIUM | tests/claude-code/pre-tool-use.test.ts | 364 | // ── Non-Bash tools targeting memory ───────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/pre-tool-use.test.ts | 407 | // ── Path variants ─────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/pre-tool-use.test.ts | 435 | // ── Write / Edit on memory paths: deny with Bash guidance ─────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 9 | // ── Mock ManagedClient ──────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 219 | // ── Helpers ─────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 230 | // ── goal/kpi namespace isolation from the generic memory table ──────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 357 | // ── Bootstrap ───────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 386 | // ── Text reads ──────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 407 | // ── Buffer reads ────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 430 | // ── Writes ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 476 | // ── appendFile ──────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 491 | // ── Directories ─────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 536 | // ── stat ────────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 558 | // ── rm ──────────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 602 | // ── cp / mv ─────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 627 | // ── path resolution ─────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 650 | // ── prefetch ──────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 793 | // ── Session reads: bodyless rows must not read as silent empty files ───────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 860 | // ── Upsert: id stability & dates ───────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 977 | // ── no-op / unsupported ops ─────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 995 | // ── Virtual index.md ───────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 1131 | // ── writeFileWithMeta ──────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 1174 | // ── readdirWithFileTypes ───────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/deeplake-fs.test.ts | 1201 | // ── cp recursive ───────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/cli-context.test.ts | 81 | // ── help ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/cli-context.test.ts | 101 | // ── login gating ──────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/cli-context.test.ts | 112 | // ── output ────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/grep-core.test.ts | 16 | // ── searchDocs (per-file docs search — the docs/find backend) ───────────────── | COMMENT |
| MEDIUM | tests/claude-code/grep-core.test.ts | 89 | // ── normalizeContent ──────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/grep-core.test.ts | 505 | // ── buildPathFilter ───────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/grep-core.test.ts | 558 | // ── compileGrepRegex ──────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/grep-core.test.ts | 594 | // ── refineGrepMatches ─────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/grep-core.test.ts | 685 | // ── searchDeeplakeTables ───────────────────────────────────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/grep-core.test.ts | 840 | // ── grepBothTables (end-to-end convenience wrapper) ───────────────────────── | COMMENT |
| MEDIUM | tests/claude-code/grep-core.test.ts | 1172 | // ───────────────────────────────────────────────────────────────────────────── | COMMENT |
| 369 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | vitest.config.ts | 1 | import { defineConfig } from "vitest/config"; | COMMENT |
| LOW | vitest.config.ts | 61 | // Both are excluded from vitest because they need a live Deeplake | COMMENT |
| LOW | vitest.config.ts | 201 | functions: 90, | COMMENT |
| LOW | vitest.config.ts | 341 | }, | COMMENT |
| LOW | vitest.config.ts | 401 | // string success branch in findHivemindOnPath() can't be deterministically | COMMENT |
| LOW | vitest.config.ts | 421 | "src/skillify/legacy-migration.ts": { statements: 90, branches: 80, functions: 90, lines: 90 }, | COMMENT |
| LOW | vitest.config.ts | 461 | "src/notifications/sources/resume-brief.ts": { statements: 90, branches: 90, functions: 90, lines: 90 }, | COMMENT |
| LOW | vitest.config.ts | 481 | // inside runGateViaStdin (settled-flag race + the unreachable error | COMMENT |
| LOW | vitest.config.ts | 501 | "src/skillify/backfill-guards.ts": { statements: 90, branches: 90, functions: 90, lines: 90 }, | COMMENT |
| LOW | vitest.config.ts | 521 | // sets all fields, so those ?? branches aren't hit — purely | COMMENT |
| LOW | vitest.config.ts | 541 | // notifications/queue and skillify/triggers. Statements + lines + | COMMENT |
| LOW | vitest.config.ts | 581 | // exercises the structured-table dispatch, the /graph/* bridge, the | COMMENT |
| LOW | harnesses/openclaw/src/index.ts | 1 | function definePluginEntry<T>(entry: T): T { return entry; } | COMMENT |
| LOW | harnesses/openclaw/src/index.ts | 101 | // top level. esbuild's stub-unused-child-process plugin (see esbuild.config.mjs) | COMMENT |
| LOW | harnesses/openclaw/src/index.ts | 421 | let kpisTable = "hivemind_kpis"; // lazy-created by hivemind_kpi_add tool | COMMENT |
| LOW | harnesses/openclaw/src/index.ts | 441 | // "one openclaw session at a time", subsequent agent_ends within the same | COMMENT |
| LOW | harnesses/openclaw/src/index.ts | 481 | // but anchored on the openclaw channel string instead of a filesystem cwd. | COMMENT |
| LOW | harnesses/openclaw/src/index.ts | 741 | COMMENT | |
| LOW | harnesses/openclaw/src/index.ts | 1361 | const hook = (event: string, handler: (event: Record<string, unknown>) => Promise<unknown>) => { | COMMENT |
| LOW | harnesses/openclaw/src/index.ts | 1421 | }); | COMMENT |
| LOW | harnesses/openclaw/src/index.ts | 1561 | // become candidates for skill mining. Lock-protected, fire-and-forget, | COMMENT |
| LOW | harnesses/codex/install.sh | 1 | #!/bin/bash | COMMENT |
| LOW | harnesses/pi/extension-source/hivemind.ts | 1 | // @ts-nocheck — distributed as raw .ts; pi's runtime loads + compiles it. | COMMENT |
| LOW | harnesses/pi/extension-source/hivemind.ts | 261 | return json.rows.map((r) => Object.fromEntries(json.columns!.map((c, i) => [c, r[i]]))); | COMMENT |
| LOW | harnesses/pi/extension-source/hivemind.ts | 461 | // Cases 10 / 11 — request timeout / daemon error → null. | COMMENT |
| LOW | harnesses/pi/extension-source/hivemind.ts | 521 | logHm(`autopull: spawn threw (swallowed): ${e?.message ?? e}`); | COMMENT |
| LOW | harnesses/pi/extension-source/hivemind.ts | 801 | detached: true, | COMMENT |
| LOW | harnesses/pi/extension-source/hivemind.ts | 841 | // src/skillify/state.ts:tryAcquireWorkerLock and releases it on exit (with | COMMENT |
| LOW | tests/test-setup.ts | 1 | // Global vitest setup. Runs once before any test file. | COMMENT |
| LOW | tests/claude-code/pre-tool-use-baseline-cloud.test.ts | 241 | COMMENT | |
| LOW | tests/claude-code/notifications-primary-banner.test.ts | 261 | COMMENT | |
| LOW | tests/claude-code/notifications.test.ts | 481 | describe("enqueueNotification cross-process safety", () => { | COMMENT |
| LOW | tests/claude-code/grep-core.test.ts | 1401 | // score scale was overpowering cosine in the UNION). The field was | COMMENT |
| LOW | tests/claude-code/skillify-pull.test.ts | 841 | // Sequence we're guarding against: | COMMENT |
| LOW | …s/claude-code/skillify-session-start-injection.test.ts | 281 | expect(src).toMatch(/function spawnOpenclawSkillifyWorker\b/); | COMMENT |
| LOW | tests/claude-code/summary-state.test.ts | 581 | COMMENT | |
| LOW | tests/claude-code/wiki-worker-plugin-version.test.ts | 221 | // | COMMENT |
| LOW | tests/claude-code/skillify-state.test.ts | 381 | }); | COMMENT |
| LOW | tests/claude-code/skillify-bundle-scan.test.ts | 101 | for (const agent of AGENTS) { | COMMENT |
| LOW | tests/claude-code/session-start-hook.test.ts | 141 | debugLogMock.mockReset(); | COMMENT |
| LOW | tests/claude-code/session-start-hook.test.ts | 421 | // (autoUpdate-internal failure modes — network down, missing binary, | COMMENT |
| LOW | tests/openclaw/auto-recall.test.ts | 141 | "hivemind_search", "hivemind_read", "hivemind_index", | COMMENT |
| LOW | tests/codex/codex-capture-hook.test.ts | 281 | // UserPromptSubmit / PostToolUse are the only types the codex | COMMENT |
| LOW | tests/codex/codex-session-start-setup-hook.test.ts | 221 | // they belong to: src/cli/update.ts (registry fetch) and the autoupdate | COMMENT |
| LOW | tests/shared/standalone-embed-client.test.ts | 1 | // Unit tests for the standalone embed client used by pi + openclaw. | COMMENT |
| LOW | tests/shared/graph/path.test.ts | 1 | import { describe, it, expect } from "vitest"; | COMMENT |
| LOW | tests/shared/graph/neighborhood.test.ts | 1 | import { describe, it, expect } from "vitest"; | COMMENT |
| LOW | tests/shared/graph/session-context.test.ts | 241 | }); | COMMENT |
| LOW | tests/shared/graph/tour.test.ts | 21 | ...overrides, | COMMENT |
| LOW | tests/cli/cli-embeddings.test.ts | 221 | // fix gates the SIGTERM on `_isDaemonAliveOnSocket` — if the UDS path | COMMENT |
| LOW | tests/cli/cli-install-openclaw.test.ts | 61 | expect(existsSync(join(root, "skills", "hivemind.md"))).toBe(true); | COMMENT |
| LOW | tests/cli/cli-bundle-runtime.test.ts | 1 | import { describe, it, expect, beforeAll, afterAll } from "vitest"; | COMMENT |
| LOW | tests/cli/cli-update.test.ts | 401 | expect(() => detectInstallKind("/cli.js")).not.toThrow(); | COMMENT |
| LOW | tests/cli/cli-update.test.ts | 421 | // | COMMENT |
| LOW | tests/pi/pi-extension-source.test.ts | 101 | COMMENT | |
| LOW | tests/scripts/marketplace-source-path.test.ts | 1 | import { describe, it, expect } from "vitest"; | COMMENT |
| LOW | …ledge/private/infrastructure/monorepo-build-release.md | 201 | COMMENT | |
| LOW | scripts/verify-install.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | .github/workflows/ci.yaml | 61 | # 3. wiki-worker summary generation failed on Windows because the | COMMENT |
| LOW | .github/workflows/ci.yaml | 121 | # `actions/checkout` — and several bundle-scan tests under | COMMENT |
| 65 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | embeddings/embed-daemon.js | 48 | async function defaultImportTransformers(canonical = _importFromCanonicalSharedDeps, bare = _importFromBareSpecifier) { | CODE |
| LOW | harnesses/openclaw/src/setup-config.ts | 37 | export function isAllowlistCoveringHivemind(alsoAllow: unknown): boolean { | CODE |
| LOW | harnesses/openclaw/src/setup-config.ts | 58 | export function isPluginsAllowMissingHivemind(allow: unknown): boolean { | CODE |
| LOW | harnesses/openclaw/src/setup-config.ts | 83 | export function ensureHivemindAllowlisted(): SetupResult { | CODE |
| LOW | harnesses/openclaw/src/graph-lifecycle.ts | 70 | export function spawnOpenclawGraphPullWorker( | CODE |
| LOW | harnesses/openclaw/src/graph-lifecycle.ts | 93 | export function resetGraphPullSpawnedForTests(): void { | CODE |
| LOW | harnesses/openclaw/src/index.ts | 464 | function migrateOpenclawSkillifyLegacyStateDir(): void { | CODE |
| LOW | harnesses/openclaw/src/index.ts | 502 | function tryAcquireOpenclawSkillifyLock(projectKey: string): boolean { | CODE |
| LOW | harnesses/openclaw/src/index.ts | 609 | function spawnOpenclawSkillifyWorker(a: OpenclawSpawnArgs): boolean { | CODE |
| LOW | harnesses/pi/extension-source/hivemind.ts | 165 | async function healDriftedOrgTokenInline(creds: Creds): Promise<Creds> { | CODE |
| LOW | harnesses/pi/extension-source/hivemind.ts | 387 | function maybeCleanupOwnPlaceholderInline(): void { | CODE |
| LOW | harnesses/pi/extension-source/hivemind.ts | 900 | function maybeTriggerPeriodicSummary(creds: Creds, sessionId: string, cwd: string): void { | CODE |
| LOW | harnesses/pi/extension-source/hivemind.ts | 1023 | function piCountLocalManifestEntries(): number { | CODE |
| LOW | …-005-cursor-skillify-bridge/qa/2026-06-13-qa-report.md | 85 | export function listLocalSkillsForPromoter(): Array<{ dirName: string; scope: "global" | "project"; path: string }> { | CODE |
| LOW | src/deeplake-api.ts | 81 | function maybeSignalBalanceExhausted(status: number, bodyText: string): void { | CODE |
| LOW | src/embeddings/standalone-embed-client.ts | 252 | function maybeCleanupOwnPlaceholder(pidPath: string): void { | CODE |
| LOW | src/embeddings/self-heal.ts | 46 | export function ensurePluginNodeModulesLink(opts: SelfHealOptions): SelfHealResult { | CODE |
| LOW | src/embeddings/disable.ts | 38 | function defaultResolveTransformers(): void { | CODE |
| LOW | src/embeddings/client.ts | 470 | export function isTransformersMissingError(err: string): boolean { | CODE |
| LOW | src/embeddings/nomic.ts | 87 | export async function defaultImportTransformers( | CODE |
| LOW | src/shell/grep-core.ts | 536 | export function buildPathFilterForTargets(targetPaths: string[]): string { | CODE |
| LOW | src/shell/grep-core.ts | 553 | export function extractRegexLiteralPrefilter(pattern: string): string | null { | CODE |
| LOW | src/shell/grep-core.ts | 586 | export function extractRegexAlternationPrefilters(pattern: string): string[] | null { | CODE |
| LOW | src/shell/grep-interceptor.ts | 24 | function resolveGrepEmbedDaemonPath(): string { | CODE |
| LOW | src/shell/grep-interceptor.ts | 44 | function patternIsSemanticFriendly(pattern: string, fixedString: boolean): boolean { | CODE |
| LOW | src/graph/extract/python.ts | 376 | function makeNodeWithExplicitLabel(relativePath: string, idName: string, label: string, kind: NodeKind, node: PyNode, ex | CODE |
| LOW | src/graph/extract/typescript.ts | 675 | function makeNodeWithExplicitLabel( | CODE |
| LOW | src/utils/plugin-cache.ts | 29 | export function resolveVersionedPluginDir(bundleDir: string): { | CODE |
| LOW | src/utils/plugin-cache.ts | 197 | export function readCurrentVersionFromManifest(manifestPath: string): string | null { | CODE |
| LOW | src/cli/install-claude.ts | 133 | function isBrokenHivemindHookEntry(h: HookEntry): boolean { | CODE |
| LOW | src/cli/install-claude.ts | 160 | export function cleanupBrokenSettingsHooks(): { removed: number; events: string[] } { | CODE |
| LOW | src/cli/install-codex.ts | 125 | function isForeignHivemindHookEntry(entry: unknown, pluginDir: string = PLUGIN_DIR): boolean { | CODE |
| LOW | src/cli/install-codex.ts | 190 | function reportForeignHivemindHooks(existing: Record<string, unknown>): void { | CODE |
| LOW | src/cli/skillify-spec.ts | 212 | export function renderSubcommandUsageBlock(): string { | CODE |
| LOW | src/skillify/local-manifest.ts | 97 | export function countLocalManifestEntries(path: string = LOCAL_MANIFEST_PATH): number { | CODE |
| LOW | src/skillify/unpull.ts | 255 | function decideTargetForManifestEntry( | CODE |
| LOW | src/skillify/existing-skills.ts | 97 | export function renderExistingSkillsBlock(cwd: string, charCap: number): ExistingSkillsBlock { | CODE |
| LOW | src/skillify/scope-promotion.ts | 22 | export function isCrossAuthorMergeVerdict(args: { | CODE |
| LOW | src/skillify/pending-memory-manifest.ts | 100 | export function readPendingMemoryManifest( | CODE |
| LOW | src/skillify/pending-memory-manifest.ts | 123 | export function writePendingMemoryManifest( | CODE |
| LOW | src/skillify/pull.ts | 157 | export function isMissingContributorsColumnError(message: string | undefined): boolean { | CODE |
| LOW | src/hooks/wiki-worker-spawn.ts | 61 | export function buildTrailingPromptInvocation(bin: string, flags: string[], prompt: string): ClaudeInvocation { | CODE |
| LOW | src/hooks/wiki-worker-spawn.ts | 83 | export function buildStdinPromptInvocation(bin: string, flags: string[], prompt: string): ClaudeInvocation { | CODE |
| LOW | src/hooks/wiki-worker-spawn.ts | 96 | export function buildClaudeStdinInvocation(claudeBin: string, prompt: string): ClaudeInvocation { | CODE |
| LOW | src/hooks/virtual-table-query.ts | 248 | export async function listVirtualPathRowsForDirs( | CODE |
| LOW | src/hooks/bash-command-compiler.ts | 139 | export function hasUnsupportedRedirection(segment: string): boolean { | CODE |
| LOW | src/hooks/bash-command-compiler.ts | 187 | function isValidPipelineHeadTailStage(stage: string): boolean { | CODE |
| LOW | src/hooks/bash-command-compiler.ts | 413 | export async function executeCompiledBashCommand( | CODE |
| LOW | src/hooks/capture.ts | 226 | function maybeTriggerPeriodicSummary(sessionId: string, cwd: string, config: Config): void { | CODE |
| LOW | src/hooks/session-event-cache.ts | 45 | export function sessionEventCacheDisabled(): boolean { | CODE |
| LOW | src/hooks/session-event-cache.ts | 93 | export function pruneStaleSessionEventCaches( | CODE |
| LOW | src/hooks/session-queue.ts | 267 | export function tryAcquireSessionDrainLock( | CODE |
| LOW | src/hooks/session-queue.ts | 403 | function isEnsureSessionsTableRetryable(error: unknown): boolean { | CODE |
| LOW | src/hooks/session-queue.ts | 435 | export function clearSessionWriteDisabled( | CODE |
| LOW | src/hooks/session-queue.ts | 464 | function getSessionWriteDisabledPath(queueDir: string, sessionsTable: string): string { | CODE |
| LOW | src/hooks/version-check.ts | 63 | export function readFreshCachedLatestVersion( | CODE |
| LOW | src/hooks/grep-direct.ts | 36 | function patternIsSemanticFriendly(pattern: string, fixedString: boolean): boolean { | CODE |
| LOW | src/hooks/pre-tool-use.ts | 127 | function buildRetryGuidanceDecision(toolName: string): ClaudePreToolDecision { | CODE |
| LOW | src/hooks/cursor/capture.ts | 210 | function maybeTriggerPeriodicSummary(sessionId: string, cwd: string, config: Config): void { | CODE |
| LOW | src/hooks/codex/capture.ts | 166 | function maybeTriggerPeriodicSummary(sessionId: string, cwd: string, config: Config): void { | CODE |
| 6 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | tests/claude-code/skillify-pull.test.ts | 851 | // Step 1: pre-pulled state — SKILL.md on disk + manifest entry | COMMENT |
| LOW⚡ | tests/claude-code/skillify-pull.test.ts | 861 | // Step 2: install codex (creates the marker dir the detector keys on). | COMMENT |
| LOW⚡ | tests/claude-code/skillify-pull.test.ts | 864 | // Step 3: re-pull. Action will be "skipped" because local version | COMMENT |
| LOW | tests/claude-code/session-summary.test.ts | 286 | // Step 1: create initial placeholder (session-start) | COMMENT |
| LOW | tests/claude-code/session-summary.test.ts | 298 | // Step 2: simulate session-end uploading a completed summary | COMMENT |
| LOW | library/knowledge/private/ai/wiki-summary-workers.md | 53 | ### Step 1: fetch session events | COMMENT |
| LOW | library/knowledge/private/ai/wiki-summary-workers.md | 67 | ### Step 2: check for an existing summary | COMMENT |
| LOW | library/knowledge/private/ai/wiki-summary-workers.md | 71 | ### Step 3: run the gate prompt | COMMENT |
| LOW | library/knowledge/private/ai/wiki-summary-workers.md | 85 | ### Step 4: embed and upload | COMMENT |
| LOW⚡ | library/knowledge/private/ai/skillify-pipeline.md | 46 | ### Step 1: fetch candidate sessions | COMMENT |
| LOW⚡ | library/knowledge/private/ai/skillify-pipeline.md | 55 | ### Step 2: extract prompt/answer pairs | COMMENT |
| LOW⚡ | library/knowledge/private/ai/skillify-pipeline.md | 59 | ### Step 3: build and run the gate prompt | COMMENT |
| LOW | library/knowledge/private/ai/skillify-pipeline.md | 82 | ### Step 4: write the skill file | COMMENT |
| LOW | library/knowledge/private/ai/skillify-pipeline.md | 93 | ### Step 5: record to the Deeplake skills table | COMMENT |
| LOW⚡ | src/commands/graph.ts | 578 | // Step 8: after the snapshot is fresh on disk, refresh docs IF the user | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | README.md | 239 | [Claude Cowork](https://support.claude.com/en/articles/11503834) is Anthropic's agentic assistant inside the Claude Desk | CODE |
| MEDIUM | tests/cli/install-helpers.test.ts | 326 | // Both stale bodies gone; the surviving scaffold is exactly the user's | COMMENT |
| MEDIUM | tests/cli/install-helpers.test.ts | 407 | // Exact remainder: both blocks removed, user scaffold intact. | COMMENT |
| MEDIUM | src/cli/install-cowork.ts | 8 | // Cowork is Anthropic's agentic desktop assistant, hosted inside the | COMMENT |
| MEDIUM | src/cli/util.ts | 130 | // claude_cowork — Anthropic's agentic desktop assistant, hosted in the | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | tests/claude-code/skillify-pull.test.ts | 851 | // Step 1: pre-pulled state — SKILL.md on disk + manifest entry | COMMENT |
| LOW⚡ | tests/claude-code/skillify-pull.test.ts | 861 | // Step 2: install codex (creates the marker dir the detector keys on). | COMMENT |
| LOW⚡ | tests/claude-code/skillify-pull.test.ts | 864 | // Step 3: re-pull. Action will be "skipped" because local version | COMMENT |
| LOW | tests/claude-code/session-summary.test.ts | 286 | // Step 1: create initial placeholder (session-start) | COMMENT |
| LOW | tests/claude-code/session-summary.test.ts | 298 | // Step 2: simulate session-end uploading a completed summary | COMMENT |
| LOW⚡ | src/commands/graph.ts | 578 | // Step 8: after the snapshot is fresh on disk, refresh docs IF the user | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | src/shell/grep-interceptor.ts | 147 | // before giving up to the in-memory fallback. Keeps behavior robust when | COMMENT |
| MEDIUM | src/graph/git-hook-install.ts | 35 | "# mkdir is robust against first-run: $HOME/.hivemind may not exist yet,", | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …sts/claude-code/shell-bundle-sql-trace-silence.test.ts | 48 | HIVEMIND_TOKEN: "fake-token-for-trace-test", | CODE |
| LOW | library/qa/security/2026-06-12-security-audit.md | 108 | - `"orgName": "Acme Inc"` - standard placeholder | CODE |
| LOW | …brary/knowledge/private/security/credential-storage.md | 74 | "orgName": "Acme Inc", | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | tests/shared/graph/python.test.ts | 18 | "def run():\n return helper()\n\ndef helper():\n return 1\n\nclass Service:\n def start(self):\n r | CODE |
| LOW | tests/shared/graph/python.test.ts | 32 | "def run():\n return helper()\n\ndef helper():\n return 1\n\nclass Service:\n def start(self):\n r | CODE |
| LOW | src/dashboard/serve.ts | 56 | function handleRequest(html: string) { | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | scripts/verify-install.sh | 12 | # Usage: | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | .github/workflows/release.yaml | 72 | # Check if release exists, Set outputs) read the post-bump state. | COMMENT |