### What version of the Codex App are you using (From “About Codex” dialog)? 26….415.32059 (1789) ### What subscription do you have? Plus ### What platform is your computer? Darwin 25.3.0 arm64 arm ### What issue are you seeing? Codex Desktop appears to include a large enabled-capability prompt surface in fresh-thread requests even when those capabilities are not actually used. I tested this repeatedly with a brand-new thread and a one-word prompt: `test`. The fresh-thread token baseline changed dramatically depending on how many plugins/skills/apps were enabled: - with a more normal enabled setup, the first real reply turn was around `21k-24k` input tokens - after removing nearly everything, it dropped to around `10.9k` input - with plugins `0`, skills `0`, it stabilized around `6.9k` input This strongly suggests enabled plugins/skills/apps are materially inflating prompt size even when they are not actually invoked. Reproduction I tested a brand-new thread each time with the same tiny prompt: ```text test ### What steps can reproduce the bug? 1. Open Codex Desktop on macOS. 2. Start a brand-new thread in a brand-new untitled Desktop folder project. 3. Send a one-word prompt: `test`. 4. Check token usage in the local Codex log database: `~/.codex/logs_2.sqlite`. 5. Repeat the same fresh-thread `test` while progressively disabling plugins/skills/apps. 6. Compare the estimated input tokens for the first real reply turn. Observed results from my tests: - Earlier enabled setup on a fresh thread: - main reply turn: estimated input around `24.2k-24.4k`, total around `32.1k` - title-generation pass: estimated input around `20.1k`, total around `24.9k` - After removing `Superpowers` only: - main reply turn: estimated input around `21.3k`, total around `29.1k` - title-generation pass: estimated input around `18.8k`, total around `23.6k` - After removing almost everything, leaving only GitHub + Google Drive plugins/apps plus remaining local/system skills: - main reply turn: estimated input around `10.9k`, total around `17.5k` - title-generation pass: estimated input around `8.5k`, total around `11.9k` - Final stripped-down baseline with: - Plugins: `0` - Skills: `0` - Apps toggled off Run 1: - main reply turn: estimated input `6942`, total `14319` - title-generation pass: estimated input `4494`, total `8803` Run 2: - main reply turn: estimated input `6954`, total `14336` - title-generation pass: estimated ### What is the expected behavior? A fresh-thread one-word prompt like `test` should have a small and fairly stable token baseline. Enabled plugins/skills/apps should not add a large token cost unless they are actually invoked for that turn. A title-generation side pass also should not consume several thousand input tokens for a trivial thread. ### Additional information This new issue is about hidden prompt/context inflation and unusually high fresh-thread token usage. I also saw malformed or weird auto-generated thread titles during some of these tests. The final clean tests were run in a brand-new untitled Desktop folder project, so this was not just a huge old-thread-history problem. This bug has burned usage much faster than expected, which is why I’m reporting it separately.