Agent skill · software engineering · steipete
codex-huge-context
Codex 1M context: direct OpenAI Responses API inference, safe Astra/Sol/Terra/Luna input headroom, Keychain delivery, and Mac fleet rollout.
Why this skill is useful
Adds detailed configuration scripts and safety protocols for managing Codex's one-million-token context that aren't available in public documentation.
What it needs
Requires openai installed locally. Requires openai account access. About 10k tokens when loaded. Last updated 2026-08-06. 6,510 stars on the source repository.
What this skill does
Codex Huge Context Use this skill when configuring, repairing, or auditing Codex's one-million-token context setup. The intended topology is a direct API inference route that preserves the normal ChatGPT login for Gmail, Calendar, and other connector OAuth: This is not an HTTP proxy. The API remains authoritative for access, actual model limits, and billing. Atomic provider and context invariant Treat the provider selector, context window, compaction threshold, and custom model catalogue as one atomic configuration. In Peter's normal ChatGPT-authenticated setup, modelprovider = "openai" selects the ChatGPT-backed route; never attach this skill's direct-API 922000 context window and 700000 compaction threshold to that route. The provider identifier alone does not determine transport: built-in openai with API-key authentication can also use the API. This skill and its preflight require the named openaiapidirect provider below so inference uses its dedicated Keychain helper while connector login stays separate. That split configuration can leave a 700,000-token compaction threshold attached to a smaller provider or model-metadata limit. Codex may also clamp the requested window, so root numbers alone do not prove the usable context. A browser- or Computer Use-heavy thread can grow past the provider's real limit before compaction, receive contextlengthexceeded, and become unable to compact because the compaction request itself no longer fits. Verify the fresh session's reported effective window as well as the files on disk. The required preflight treats this mismatch as fatal. Do not launch or resume Codex after any config writer, app settings change, model change, or fleet sync until the preflight passes. If it reports an unsafe split configuration, restore modelprovider = "openaiapidirect", restart every Codex desktop/shared app server, and start or fork a fresh thread. Resuming the failed thread preserves its recorded provider. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills steipete/codex-huge-context