What changes a coding agent's behaviour: models, written rules and runtime guards over eight months of daily use of Claude Code

Companies govern coding agents with written instructions and, increasingly, with hooks that block an action when it breaks a rule. This study measures what changed the behaviour of Claude Code over eight months of daily use by one operator with no training in programming who directed many sessions at once, using 46,464 operator messages, 1.3 million agent messages and 3,411 recorded blocks. A fixed instrument applied the rules of one guard to every surviving answer, including those written before the guard existed. In the week Claude Opus 5.5 was released, it broke the operator's writing rules in 18% of first drafts and Claude Opus 5 in 57%, a gap that held within the same long-running sessions. For one language rule, a written instruction was followed by a fall that could not be distinguished from chance, and a reinforced rule with a guard by a fall to a sixth of the starting rate. Blocks roughly halved the violations that reached the operator, with no detectable effect on later drafts in the same session. Supervision accounted for a third to a half of the operator's messages throughout, while its content shifted from corrections to nudges to keep working. Agents built into the operator's own applications, each with a defined role and sharing its data with the application's interface, received more new work and less supervision than development sessions, a difference within chance. Files: the working paper (PDF) and the replication material (analysis scripts, codebook, rule patterns, the aggregated tables behind every figure, and the study design with every dated change). The operator's messages and the agent transcripts are not included because they contain client work and private correspondence. Canonical page: isaac-correa.github.io/coding-agents. Conflict of interest: the author is the operator studied and a co-founder of Hellomatik, a company that builds AI agents for businesses. Self-published, not peer reviewed.