Skip to main content
skill CX Codex

codex-1m-context-window-setup — Codex skill: context setup

codex-1m-context-window-setup inspects Codex context settings, adjusts auto-compaction, and applies a model-aware expansion toward 500K or 1M when supported.

MIT 211 installs ★ 1,540 updated 2026-10-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add daymade/claude-code-skills --skill codex-1m-context-window-setup -a claude-code
Open on GitHub

What codex-1m-context-window-setup does

This skill reads Codex’s local context configuration and reports the current window and automatic compaction threshold. It can change the compaction limit alone, or calculate and apply an expanded window from the live model catalog, targeting the available limit rather than a remembered value.

The bundled script is scripts/codex_context_window.py. Its workflow includes show, set-compact, doctor, apply, and verify. The documented launcher uses uv, and the script needs Python 3.11+ for tomllib. Full expansion also depends on Codex support for doctor --json, debug models, and strict configuration diagnostics.

Without Python 3.11+ and uv, the documented workflow cannot run. The skill leaves model selection and unrelated Codex settings alone. A successful change applies to new CLI or Desktop sessions, not to an existing thread.

What it helps with

  • inspect Codex context-window settings
  • set an automatic compaction threshold
  • diagnose the selected model’s context limit
  • apply a model-aware context expansion
  • check the setup after a Codex update

Example prompts for the agent

  • Inspect the current Codex context settings with show.
  • Run doctor and explain whether the selected model supports the expanded window.
  • Apply the model-aware context preset, then run verify to check the result.

How to install codex-1m-context-window-setup

1Skills CLI (Vercel)

npx skills add daymade/claude-code-skills --skill codex-1m-context-window-setup -a claude-code

2Manually: put the files in place

~/.claude/skills/codex-1m-context-window-setup/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/codex-1m-context-window-setup/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about codex-1m-context-window-setup

How do I install codex-1m-context-window-setup in Codex?

Run npx skills add daymade/claude-code-skills --skill codex-1m-context-window-setup -a codex, then use .agents/skills/codex-1m-context-window-setup/SKILL.md.

What does codex-1m-context-window-setup do?

It reads Codex context settings, changes the automatic compaction limit, and can apply an expansion based on the live model catalog. doctor and verify cover model-cap diagnosis and configuration checks.

What does full context expansion require?

The workflow needs Python 3.11+, uv, and Codex commands for doctor --json, debug models, and strict configuration diagnostics. Expansion uses the current model catalog.

Source text

SKILL.md · MIT
---
name: codex-1m-context-window-setup
description: >-
  Configures and verifies an expanded, model-aware context window for OpenAI Codex CLI and Desktop.
  Use to inspect local context settings, lower or set the auto-compaction threshold, expand
  ~258K context to 500K or 1M, or repair model_context_window/model_auto_compact_token_limit.
  Not for changing the selected model or other Codex settings.
argument-hint: "[show|set-compact --tokens N|doctor|apply|verify]"
---

# Codex 1m Context Window Setup

Inspect local settings or change only automatic compaction. For full context
expansion, read Codex's current model catalog, cap the request at the model's
declared maximum, and apply the bundled expansion preset.

## Route the request

| User intent | Action |
|---|---|
| Read the current base-config window or compaction threshold | Run `show`; no Codex process or model catalog needed |
| Lower/set only automatic compaction | Run `show`, then `set-compact --tokens N` |
| Explain 258K, diagnose model limits, or preview full expansion | Run `doctor` |
| Configure/fix/raise the context window | Run `apply` |
| Confirm a prior setup is still correct after an update or model switch | Run `verify` |

Honor a user-specified threshold exactly. If the user only asks for a small
reduction, choose and state a modest reversible reduction from the observed value.
For expansion, derive attainable values from the live catalog instead of asking
the user for model limits. Running `apply` selects the full expansion preset and
replaces a custom threshold; do it only when full setup is requested.

For local reads/edits, start with the bundled commands. Do not dump config.toml,
load unrelated machine manuals, or run network/model diagnostics. Consult official
OpenAI documentation when parameter semantics or compatibility are unresolved;
it cannot establish this machine's current value. Respect host output restrictions;
if numeric output is denied, use its supported field-condition probe and keep an
unread value unknown. Do not reconstruct denied values through repeated comparisons.

## Prerequisites

Use Python 3.11+ for the script's `tomllib` dependency and uv for the documented
launcher. `show` needs no Codex executable. `set-compact` requires a Codex CLI
supporting `features list`; full expansion additionally requires `doctor --json`,
`debug models` and strict-config diagnostics. Missing expansion support does not
prevent a local read. Do not substitute another config root or guessed model data
when a required command is unavailable.

## Run the workflow

Run the bundled [configuration script](scripts/codex_context_window.py).

When this Skill loads, the host exposes its installed path. Resolve it explicitly:

- In Codex, take the directory containing `SKILL.md` from this Skill's `file:`
  entry in the current **Available skills** catalog.
- In Claude Code, use the **Base directory for this skill** shown by the Skill
  load result.

Do not search a home directory for another copy. If the host did not expose an
installed path, stop with `installed Skill path not exposed` rather than guessing.

On macOS/Linux, set that exact directory:

```bash
SKILL_DIR="/absolute/path/from-the-loaded-skill-metadata"
```

On Windows PowerShell, use the same exposed directory with forward slashes:

```powershell
$SkillDir = "C:/absolute/path/from-the-loaded-skill-metadata"
```

Execute only the branch selected under **Route the request**. In the commands
below, PowerShell users substitute `$SkillDir` for `$SKILL_DIR`.

### `show` and `set-compact`

Use the same resolved script path on either platform:

```bash
uv run --no-project python "$SKILL_DIR/scripts/codex_context_window.py" show --json
uv run --no-project python "$SKILL_DIR/scripts/codex_context_window.py" set-compact --tokens 400000 --json
uv run --no-project python "$SKILL_DIR/scripts/codex_context_window.py" show --json
```

Choose `--tokens` from the current request, not this example. `show` emits only
the numeric settings, the config path and evidence status; a missing value is null,
not a guessed default.
It does not inspect profile or command-line overrides.

`set-compact` preserves the context-window setting, profiles, comments and existing
formatting; inserting a missing key may add a separating newline. It rejects
nonpositive/out-of-range tokens and thresholds
above an explicitly configured window. When the window is absent, leave it absent;
model-derived runtime caps remain unverified. Before a changed write, back up the
original and check for concurrent edits. Write atomically, run the local
`codex features list` configuration-load check with captured output, and read back
the target. Restore the original on validation failure unless a concurrent edit
makes that unsafe. A no-op creates no backup. Do not echo diagnostic bodies that
may contain unrelated configuration. Use `show` afterward as independent readback.

### `doctor`

Run first for full expansion or model-cap diagnosis:

```bash
uv run --no-project python "$SKILL_DIR/scripts/codex_context_window.py" doctor --json
```

It is read-only and reports:

- selected model resolved by Codex;
- catalog default, model maximum, and usable percentage;
- recommended raw window, usable window, and preset compaction point;
- current base-config values and whether `apply` is needed;
- exact `$CODEX_HOME/config.toml` target.

If Codex cannot return a live model catalog, stop the expansion path. Do not
substitute remembered model limits, API marketing numbers, or a bundled default.
Local `show`/`set-compact` remain independent of catalog availability.

### `apply`

Run only after `doctor` succeeds:

```bash
uv run --no-project python "$SKILL_DIR/scripts/codex_context_window.py" apply --json
```

The script:

1. Re-reads the live model contract.
2. Changes only the top-level `model_context_window` and
   `model_auto_compact_token_limit` keys.
3. Creates a content-addressed backup only when bytes will change.
4. Uses an atomic same-directory replace and refuses to overwrite a concurrently
   changed config.
5. Runs Codex strict-config diagnostics; a failure restores the exact prior bytes.
6. Reads the written file back and reports the values that future sessions will use.

Existing sessions do not grow in place. After success, tell the user to start a new
CLI thread or restart/open a new Codex Desktop thread.

### `verify`

Run after Codex upgrades, default-model changes, or on a newly configured machine.
It exits non-zero when the current base config no longer equals the model-aware
expansion preset. A deliberate custom threshold can differ from that preset; this
is not proof that the saved threshold is invalid. Use `show` for its current base value.

```bash
uv run --no-project python "$SKILL_DIR/scripts/codex_context_window.py" verify --json
```

## Report the outcome

For a threshold-only change, report previous → saved tokens, backup path when
changed, local configuration-load result and independent readback. Keep
`session_adoption: unverified` until the actual consumer supplies evidence. Ask
the user to start a new CLI thread or restart/open a new Desktop thread that reads
this base config; do not claim the running thread changed. Profile and `-c`
overrides can still supersede it.

For expansion, copy exact values from script output. Include:

- model slug;
- configured raw window;
- usable window shown to the session;
- automatic compaction threshold;
- whether the model capped the 1M request;
- config and backup paths;
- `restart_required: true` after a changed apply.

## Refuse scope expansion

This Skill does not:

- change the selected model, reasoning effort, service tier, sandbox, approvals,
  plugins, MCP servers, browser/computer-use settings, or shell aliases;
- edit profile-specific config files or override per-command `-c` flags;
- claim the current running thread was expanded;
- force 1M when the selected model declares a smaller maximum;
- fall back to stale or guessed model metadata.

Read [references/context_window_contract.md](references/context_window_contract.md)
when diagnosing model caps, usable-window display, or compaction semantics.

© daymade · MIT · daymade/claude-code-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set102

The whole set →
read-codex-history read-codex-history — a skill for Codex, Claude Code, Cursor, GitHub Copilot and Gemini CLI that reads, searches and exports local OpenAI Codex session history without resuming any prior task. CX Codex +1 221installs prior-work-retrieval prior-work-retrieval is a Claude Code skill that surfaces and inspects past project deliverables before creating new components. Activates on explicit reuse requests. CX Codex +1 218installs continue-claude-code-work continue-claude-code-work restores interrupted Claude Code work from session history, identifies unfinished requests, and selects the next verified action. CX Codex +1 216installs interaction-design-board The interaction-design-board skill builds several clickable HTML prototypes of one interface into a Design Board where you pick a variant or request a remix before the agent touches production code. CX Codex +1 213installs lark-cli-router lark-cli-router routes Feishu, Lark, and Doubao tasks to version-matched guides in lark-cli. Helps agents manage docs, calendar entries, and chat tasks safely. CX Codex +1 210installs excalidraw-use excalidraw-use lays existing images out on an Excalidraw scene in a grid, shoots Vite/React slides to separate images, and reads a .excalidraw file for broken pictures. CX Codex +1 187installs meme-creator The meme-creator skill tracks moving objects in a clip and places logos, avatars, or stickers over them, then exports MP4 and GIF files. Use it to make a reaction meme from footage. CX Codex +1 174installs agent-web-search-setup agent-web-search-setup — a skill for Claude Code and other platforms diagnoses and fixes web search when proxies return empty responses. CX Codex +1 162installs

Project sponsors

Companies that keep this analytics open