Anthropic · Nvidia · Federal Reserve (FED) · AI Agent · The Register
Coding agents rely on configuration files that summarize expected agent behavior
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
They include various text instructions that advise the coding agent about desired behavior and tool use.
Key facts
- Researchers affiliated with the computer science department of the Federal Institute of Minas Gerais in Brazil recently scoured some 532,000 files to build and analyze a dataset of 100 popular
- The study authors say that they found at least one of these six smells in 91 of the 100 AGENTS.md files tested
- The authors are Helio Victor F. dos Santos, Vitor Costa, Joao Eduardo Montandon, Luciana Lourdes Silva, and Marco Tulio Valente
- These results suggest that developers could benefit from catalogs and tools designed to spot configuration issues in agent configuration files," they conclude in the preprint paper, entitled
Summary
Researchers urge developers to see that less is more when it comes to instructions. If you're exposing your agent to a strong odor, it's time to clean up your instructions. Risky or poorly structured code patterns are known as "code smells," and it turns out coding agent directives can be similarly redolent, leading to wasted tokens and worse output. Researchers affiliated with the computer science department of the Federal Institute of Minas Gerais in Brazil recently scoured some 532,000 files to build and analyze a dataset of 100 popular open-source projects containing either an AGENTS.md or a CLAUDE.md file.