When my first dead-export script ran against a 3,300-file TypeScript/React/Python monorepo, it reported 2,266 dead exports. That number was completely wrong.
I had matched import { symbol } across files, which missed 1,722 symbols referenced via namespace imports (ns.helper()), JSX tags (<Widget />), or internal same-file calls, plus 648 framework entrypoint exports (index.ts, page.tsx, route.ts, sst.config.ts) and 270 barrel re-exports (export * from). And when I hashed every function body to find clones, 4,559 2-line getters and trivial wrappers collided across unrelated files.
After filtering out < 25 normalized-token functions (CLS008), framework entrypoints (CLS009), and separating same-file internal callers (CLS006) from zero-caller orphans (CLS005), I ran the corrected analyzer across all 3,300 files (4,544 non-trivial functions) and 153 local Claude Code (~/.claude/projects/**/*.jsonl) and Codex CLI (~/.codex/sessions/**/*.jsonl) transcripts.
What the 3,300-File + 153-Transcript Audit Found
-
39.0% Blind Function Additions in Agent Sessions (
CLS010/CLS011): Across153Claude Code and Codex sessions (1,813deduplicated tool calls),23of59new function definitions (39.0%) and59of132file write/patch calls (44.7%) were executed before the agent ran a singleGrep,Glob, orrgsearch in that session. -
117 Exact Structural Function Clone Groups (
CLS001/CLS002): Using Type-2 token normalization (stripping comments, collapsing strings to"STR", numbers toNUM, and non-keyword identifiers toIDon functions>= 25tokens), we found19multi-file exact clone clusters (>= 3copies) and98pairwise structural clones (2copies).-
DataWordmarkwas copy-pasted7times acrossflash.tsx,june.tsx,minimax.tsx,novel.tsx,sheep.tsx,video.tsx, andstats-shell.tsx. -
getReviewCommentContext,getUserPrompt, andsubscribeSessionEventswere duplicated acrossindex.tsandgithub.handler.ts.
-
-
370 Cross-File Duplicate Helper Names (
CLS004):370non-trivial function names (>= 25tokens) were re-implemented in 2 or more separate files (summarizein 3 files,chatin 2 files). -
163 Truly Dead Zero-Caller Orphan Exports (
CLS005) vs 381 Internal-Only Over-Exports (CLS006):381functions were exported withexporteven though they were only called inside their defining file (stripeWebhook,lakeVpc,isStableSessionSwitch), while163exported functions had0cross-file references and0internal calls (startVisualStabilityProbe,stopVisualStabilityProbe,runVisualStabilityScenario).
The Three False-Positive Traps We Fixed
-
Whole-Repo Identifier Indexing (
1,722false positives eliminated): Instead of greppingimport { foo },clonesievebuilds a per-file identifier token frequency map across the repository and compares external file hits against same-file occurrences. -
Entrypoint & Framework Convention Exclusions (
648entrypoints +270barrels skipped):CLS009excludesindex.*,main.*,cli.*, Next.js conventions (page.tsx,layout.tsx,route.ts,GET,POST,metadata,generateStaticParams), config files, andexport * frombarrels. -
25-Token Structural Floor (
4,559trivial getters skipped):CLS008requires at least25normalized tokens before running exact skeleton hashing or 4-gram Jaccard shingle comparison (CLS003).
Running clonesieve on Your Repo
I published clonesieve (v0.1.0, zero dependencies, MIT licensed) so you can run the 14-rule audit (CLS001 to CLS014) on your repository and generate a Canonical Helper Registry table for CLAUDE.md:
# Audit your repository for structural clones, duplicate helper names, and dead exports
npx clonesieve .
What rules or CLAUDE.md indexing tricks have worked best for you to keep agents from writing a 4th copy of existing helpers?

Top comments (1)
The rule that tends to hold up is one line in CLAUDE.md: before writing a new function, search the repo for an existing one and say what you found. Pair it with a short map of where the shared helpers live, one line per folder, because an agent that doesn't know the map has nothing to search for. Keeping the file short helps too: three or four hard rules usually get followed better than a long list that gets skimmed.