Yesterday OpenAI shipped the GPT-5.6 family (Sol, Terra, Luna) and folded Codex into a unified ChatGPT desktop app. Within hours, the loudest thread on X was not about benchmarks. It was a developer on the $200/month Codex plan reporting he now hits his 5-hour usage window with just one or two agents running Sol, a setup that was comfortable on GPT-5.5.
OpenAI claims roughly 54% better token efficiency for coding in this generation. Developers are discovering the opposite problem in practice: stronger models invite heavier consumption. An agent that runs longer eats the efficiency gain in raw volume, and every plan (OpenAI's 5-hour windows, Anthropic's limit windows, Cursor's credits) still caps you the same way. Tokens in, tokens out.
Here is the uncomfortable take: most of the tokens your coding agent burns are spent on context you did not need to send. Re-exploring the repo it explored yesterday. Re-reading a 900-line CLAUDE.md on every turn. Carrying a whole conversation into a task that needed three files. A bigger plan does not fix that. It just raises the ceiling on the same waste.
There is a second signal worth taking seriously. Claude Code shipped a /checkup command two days ago that scans for exactly this: unused skills, oversized CLAUDE.md files, config bloat. When the tool vendor starts shipping hygiene tooling, the waste is no longer a niche complaint: even the vendor is telling you your setup is burning tokens it does not need.
