PulseAugur
EN
LIVE 18:04:28

Developer finds 39% of agent code written without search

By PulseAugur Editorial · [1 sources] ·

A developer audited a large monorepo and found that 39% of new functions and 44.7% of file write/patch operations in agent sessions were executed without the agent first searching for existing code. The audit also identified 117 groups of structurally identical functions and 370 duplicate helper function names across different files. Additionally, the analysis revealed 163 truly dead exports and 381 functions that were exported but only used internally within their own files. AI

IMPACT Highlights potential inefficiencies in AI agent code generation and suggests improvements for developer tools.

RANK_REASON Developer-authored analysis of code duplication and agent behavior, published on a developer platform. [lever_c_demoted from research: ic=1 ai=0.7]

Read on dev.to — Claude Code tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Developer finds 39% of agent code written without search

How we ranked this

Signal score
28 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Developer-authored analysis of code duplication and agent behavior, published on a developer platform. [lever_c_demoted from research: ic=1 ai=0.7]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — Claude Code tag TIER_1 English(EN) · Prince Jain ·

    Auditing 3,300 Files and 153 Claude Code & Codex Logs: Why 39.0% of Agent Functions Are Written Without Searching the Repo

    <p>When my first dead-export script ran against a 3,300-file TypeScript/React/Python monorepo, it reported <code>2,266</code> dead exports. That number was completely wrong.</p> <p>I had matched <code>import { symbol }</code> across files, which missed <code>1,722</code> symbols …

RELATED ENTITIES

RELATED TOPICS