Skip to content
Configuration Smells in AGENTS.md Files Waste Tokens and Reduce Agent Efficiency

Configuration Smells in AGENTS.md Files Waste Tokens and Reduce Agent Efficiency

First seen 18 Jun 2026, 00:02 UTC

Article Content

Browse articles
ThreatCluster AI
ThreatCluster June 18, 2026 at 23:54 UTC
  • Configuration smells in AGENTS.md files waste tokens and degrade agent performance.
  • Lint Leakage, Context Bloat, and Skill Leakage were found in a majority of analyzed files.
  • Developers are encouraged to limit configuration file length to improve efficiency.

Researchers from the Federal Institute of Minas Gerais analyzed 532,000 files from 100 popular open-source projects, revealing widespread 'configuration smells' in AGENTS.md and CLAUDE.md files. The study identified issues such as Lint Leakage (62% of files), Context Bloat (42%), and Skill Leakage (35%). These problems lead to inefficient token usage and hinder agent performance. Developers are advised to limit configuration files to 200 lines to enhance model coherence. The findings suggest that many developers are unaware of these inefficiencies, which can lead to increased operational costs and reduced effectiveness of coding agents.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Updated 93d ago How this analysis works

Timeline

2026-06-17
Study on AGENTS.md files published
Researchers analyzed 532,000 files from 100 open-source projects, identifying common configuration smells affecting agent performance.
Article 1 (Theregister)
2026-06-17
Configuration smells identified
The study reported Lint Leakage in 62% of files, Context Bloat in 42%, and Skill Leakage in 35%, impacting token efficiency.
Article 2 (Theregister)

More articles in this cluster (2)