@ryan_nookpi/pi-extension-codex-fast-mode

Codex fast mode extension for pi.

Packages

Package details

extension

Install @ryan_nookpi/pi-extension-codex-fast-mode from npm and Pi will load the resources declared by the package manifest.

npm repohome report
$ pi install npm:@ryan_nookpi/pi-extension-codex-fast-mode
Package
@ryan_nookpi/pi-extension-codex-fast-mode
Version
0.2.9
Published
Oct 24, 2026
Downloads
707/mo · 155/wk
Author
ryan_nookpi
License
MIT
Types
extension
Size
9.3 KB
Dependencies
0 dependencies · 2 peers
Pi manifest JSON
{
  "extensions": [
    "./index.ts"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

@ryan_nookpi/pi-extension-codex-fast-mode

codex-fast-mode: Toggles a faster, terser Codex setup per session with /codex-fast.

This extension helps pi use OpenAI Codex in a faster, lower-verbosity mode.

It is intended for openai-codex with the supported gpt-5.6 variants, gpt-6-astra, gpt-6-luna, gpt-6-sol, and gpt-6.1-sol, when you want quick execution and shorter responses.

Install

pi install npm:@ryan_nookpi/pi-extension-codex-fast-mode

Great for

  • prioritizing speed over long explanations
  • keeping Codex responses concise
  • toggling a faster Codex setup per session

Usage

/codex-fast on
/codex-fast off
/codex-fast status

Notes

  • Target models: openai-codex / gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-6-astra, gpt-6-luna, gpt-6-sol, and gpt-6.1-sol. gpt-5.4 and gpt-5.5 are no longer targeted.
  • Command descriptions and status messages abbreviate the list as gpt-5.6, gpt-6, gpt-6.1-sol; matching still uses the exact model IDs above.
  • This extension does not register models. All target models are in Pi SDK 1.0.1; availability still depends on your account and workspace.
  • OpenAI documents Fast mode usage at 2.5x the Standard rate for included subscription limits and 2x for purchased credits and Enterprise pay-as-you-go usage. These are billing multipliers, not speed increases.
  • Pi SDK 1.4.0 removed openai-codex/gpt-5.5 because the Codex backend rejects it for ChatGPT accounts, so this extension no longer targets it.
  • It always applies text.verbosity=low.
  • When fast mode is enabled, it also injects service_tier=priority into the ChatGPT Codex backend request. Do not substitute the Codex CLI config value fast without verifying backend support.
  • Live requests with Pi SDK 1.0.1 succeeded for all four targeted GPT-6 models with priority and low verbosity. The backend returned service_tier=default, so this confirms request acceptance, not actual priority scheduling or a speed increase.
  • The setting is stored locally and persists across sessions.

References