3 Weeks of Silent Failure: How One Missing `--model` Flag Drained My Interactive Quota Across 4 Jobs
I went from ¥100k a month as a student to ¥600k juggling side gigs, then to ¥0 after a layoff—and six months of building an autonomous Claude Code environment brought me to ¥1.2M a month in revenue. The difference wasn't working harder. It was betting on "grow the environment" instead of "do the work." Why This Setup Works Look up how to make money on the side and you'll always land on the same…
The article discusses how a missing `--model` flag in a script led to three weeks of unnoticed failure in an automated content generation setup. The setup involved using Claude Code as infrastructure rather than simply using it as a tool. The setup had four lanes running simultaneously, each performing a different task related to article generation and management.
The failure occurred because the script did not error when the `--model` flag was omitted, causing it to consume interactive session quota without any indication. This went unnoticed for three weeks, as the system only returned a single line when the quota was exhausted, which was mistakenly interpreted as normal output. The issue arose due to a gap in understanding of how Claude Code's quota structure worked, highlighting the importance of knowing how quota is shared and consumed when using AI infrastructure.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.