Fresh-thread token usage is massively inflated by enabled plugins/skills/apps in Codex Desktop

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:

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.