codex-huge-context

A configuration guide for giving Codex access to a very large context window through the OpenAI Responses API. Context means the amount of conversation and code the model can consider in one request, while Keychain stores the API authentication securely.

In plain words
What is it for?
Use it to configure, repair, or audit the one-million-token setup, preserve normal ChatGPT login for connectors such as Gmail and Calendar, and roll the configuration out across Macs.
Why use it?
It prevents incompatible provider and context settings that could make Codex expect more input than the selected service accepts, especially during long or image-heavy sessions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/steipete/agent-scripts/codex-huge-context
Any agent
npx skills add steipete/agent-scripts --skill codex-huge-context
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-scripts

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,816 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.02816
Opus 5 $0.00020 $0.01408
Sonnet 5 $0.00008 $0.00563
Haiku 4.5 $0.00004 $0.00282

Measured yesterday against content hash c8d33e0a2d6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-huge-context scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/preflight.rb, scripts/preflight.test.rb), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

The root section of `~/.codex/config.toml` needs:
skills/codex-huge-context/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

Codex inference -> Keychain auth helper -> https://api.openai.com/v1/responses
Codex connectors -> normal ChatGPT login in auth.json

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. Never combine model_provider = "openai" with the direct-API 922000 context window and 700000 compaction threshold. The built-in openai route is the ChatGPT-backed provider, not the million-token direct Responses API route.

That split configuration makes Codex advertise about 875,900 usable tokens to itself and postpone compaction until 700,000 tokens even though the selected provider can reject the request much earlier. A browser- or Computer Use-heavy thread can therefore grow past the provider's real limit without a single compaction, receive context_length_exceeded, and become unable to compact because the compaction request itself no longer fits.

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 model_provider = "openai_api_direct", restart every Codex desktop/shared app server, and start or fork a fresh thread. Resuming the failed thread preserves its recorded provider.

Safe input window

GPT-5.6 Sol exposes a 1,050,000-token total context window and can produce up to 128,000 output tokens. Codex does not set a smaller output budget on normal Responses API turns, so the catalogue must describe the safe input allowance rather than the raw total:

Read the full file on GitHub · 174 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 174 lines · 40 tokens per session scan B c8d33e0a2d6e

Subscribe to this mod's changes

codex-huge-context is a skill published in the GitHub repository steipete/agent-scripts (6,580 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 2,816 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens