Skip to main content
plugin CX Codex

codex-usage-and-resets — Claude Code plugin: features and install

codex-usage-and-resets is a Claude Code plugin that reports Codex weekly usage, pace, and reset expirations. It estimates whether the allowance will last until the next reset.

Apache-2.0 ★ 1,596 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install codex-usage-and-resets@awesome-codex-plugins
Open on GitHub

What codex-usage-and-resets does

The plugin builds a local report from Codex’s weekly allowance: usage so far, remaining capacity, saved resets, and their expiration details. It compares your current pace with a linear one and estimates whether the allowance could run out before the next scheduled reset. If usage returns to zero earlier than expected, the plugin records an observation; it does not claim to know the cause or exact reset time.

It reads limits through the local Codex App Server method account/rateLimits/read. It does not inspect authentication files or session logs, start model turns, or consume resets. You need Node.js 18 or newer, a compatible local codex executable, and ChatGPT-backed Codex authentication. Remaining usage is reported in whole percentage points, so treat it as an upper bound rather than an exact reading.

Locally, the plugin keeps one sanitized usage snapshot and at most one recent reset observation. Older records are pruned after a successful report; an unreliable comparison clears the observation chain, so later reports do not infer what happened during the gap. Invoke $cuar or ask about usage, pace, projected exhaustion, or reset expirations.

What it helps with

  • check remaining weekly Codex usage
  • compare current spending pace with a linear rate
  • estimate whether capacity will run out before the next reset
  • review saved reset count and expiration details
  • record an unexpected return to zero usage

Example prompts for the agent

  • Use $cuar to report my current Codex usage and weekly remainder.
  • Compare my current usage pace with a linear rate and estimate whether it will last until the next reset.
  • Check the saved reset count and expiration dates with $cuar.

How to install codex-usage-and-resets

Plugin marketplace

/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install codex-usage-and-resets@awesome-codex-plugins

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about codex-usage-and-resets

How do I install codex-usage-and-resets in Claude Code?

Run /plugin marketplace add hashgraph-online/awesome-codex-plugins, then /plugin install codex-usage-and-resets@awesome-codex-plugins.

What does codex-usage-and-resets do?

It reports weekly Codex usage, remaining capacity, spending pace, and saved reset expirations. It can also estimate whether current usage will exhaust capacity before the next scheduled reset.

What does the plugin need to run?

It requires Node.js 18 or newer, a compatible local codex executable, ChatGPT-backed Codex authentication, and a Codex client that can run local skills.

Source text

codex-usage-and-resets · Apache-2.0
# Codex Usage and Resets

[![CI](https://github.com/joelfarthing/codex-usage-and-resets/actions/workflows/ci.yml/badge.svg)](https://github.com/joelfarthing/codex-usage-and-resets/actions/workflows/ci.yml)
[![HOL Plugin Scanner](https://github.com/joelfarthing/codex-usage-and-resets/actions/workflows/hol-plugin-scanner.yml/badge.svg)](https://github.com/joelfarthing/codex-usage-and-resets/actions/workflows/hol-plugin-scanner.yml)

**Canonical project site:** [Codex Usage and Resets on Filament Labs](https://filamentlabs.io/CUAR/) — a visual tour, installation guidance, and field notes.

Codex Usage and Resets (CUAR) is a local Codex plugin from Filament Labs. It
turns the current Codex weekly usage window, banked reset inventory, and a tiny
local observation ledger into deterministic usage-planning facts:

- banked reset count and returned expiration details;
- used and remaining weekly usage;
- the whole-percentage precision limit, including an imminent-exhaustion
  warning when the reported remainder reaches 1%;
- pace above, below, or approximately at linear usage;
- projected exhaustion when the current average burn would exhaust capacity
  before the next scheduled reset; and
- an unexpected early return to zero used, reported conservatively as an
  observation rather than proof of the reset's cause or exact time.

CUAR uses the documented local Codex App Server
`account/rateLimits/read` method. It does not read Codex authentication files,
inspect session logs, call private ChatGPT endpoints, start a thread or model
turn, or consume a reset. CUAR is read-only toward Codex and OpenAI. Locally,
it keeps one sanitized usage snapshot and at most one recent reset observation,
ignoring and pruning either on the next successful report once it is more than
eight days old. A report that cannot form a trustworthy comparison clears the
comparison chain, so a later report cannot infer across the blind interval.

## Requirements

- Node.js 18 or newer
- a compatible local `codex` executable
- ChatGPT-backed Codex authentication
- a Codex client able to run local plugin skills

The same packaged skill and CLI are intended for Codex in the ChatGPT desktop
app, the Codex VS Code extension, and Codex CLI.

## Installation

Install from [the direct Codex Usage and Resets listing in the OpenAI Plugins
Directory](https://chatgpt.com/plugins/plugins_6a6920fb32b48191b80cb783761d4cd5):
open it and choose **Install plugin**. The directory copy is a reviewed,
versioned snapshot and does not automatically track this repository.

## Use

Invoke `$cuar` or ask Codex about current Codex usage, linear pace, projected
exhaustion, banked reset expirations, or whether an unexpected reset was
observed. CUAR's machine report is deterministic; the model explains what the
facts mean for planned work without recalculating its fields. OpenAI reports
usage in whole percentage points, so CUAR treats displayed remaining usage as
an upper bound rather than an exact measurement.

CUAR is independently developed and is not developed, supported, or endorsed
by OpenAI. Reset observation cannot rule out an account switch or every
coincident banked-reset change. Current observations and projections do not
promise future unscheduled resets.

## Validation and trust

The public repository runs its portable test suite on macOS and Linux across
supported Node.js versions. A separate
[HOL Guard](https://github.com/hashgraph-online/hol-guard) workflow scans the
plugin on pull requests and `main`, requires a score of at least 80, and fails
on any high-or-critical finding. Both workflows use read-only repository
permissions. They do not receive Marketplace credentials, upload SARIF, or
submit or publish the plugin.

Passing automated checks is reproducible project evidence, not certification,
endorsement, or Marketplace acceptance by OpenAI, HOL, Cisco, or any other
party.

The July 28, 2026 CUAR 0.1.1 pre-publication run used HOL Guard
`plugin-scanner` 2.0.1116 against both the public source and extracted release
ZIP. Both produced:

- `public-marketplace` policy: **PASS**;
- score: **97/100 — A, Excellent**;
- critical, high, medium, and low findings: **zero**;
- HOL runtime verification: **PASS**; and
- Cisco skill scanning: completed with the balanced policy and no elevated
  findings.

The two remaining notices are informational schema differences. HOL scores an
absent optional screenshot field as invalid; CUAR does not invent screenshots.
Cisco recommends a per-skill license field, while Codex skill authoring permits
only `name` and `description` frontmatter. The repository and plugin manifest
declare Apache-2.0.

## Privacy, security, and support

See [PRIVACY.md](./PRIVACY.md), [SECURITY.md](./SECURITY.md), and
[SUPPORT.md](./SUPPORT.md).

© Filament Labs · Apache-2.0 · hashgraph-online/awesome-codex-plugins

Similar plugins

All plugins for Notes, tasks and projects →

From the same set391

The whole set →
core-learning core-learning structures study sessions around Socratic questioning, Feynman teach-back, and spaced recall to deliver working projects. CX Codex ★ 1,596repo stars context-guard context-guard is a Claude Code and Codex plugin that preserves requirements and verification evidence in long Codex tasks. It restores open items after context compaction and checks evidence before marking work complete. CX Codex ★ 1,596repo stars codex-attachment-manager codex-attachment-manager is a Claude Code plugin that manages image history in Codex tasks. It selects attachments for the next message and searches them by description. CX Codex ★ 1,596repo stars codex-claude-council codex-claude-council asks Claude and ChatGPT the same question, then lets them debate across multiple rounds until both reach agreement. CX Codex ★ 1,596repo stars codex-tui-proof codex-tui-proof is a Claude Code plugin for checking terminal UIs in Codex's browser with keyboard input and screenshots. It runs from a TUI validation request. CX Codex ★ 1,596repo stars codex-tasklist codex-tasklist is a plugin for Codex CLI that creates a live task panel, saves state to SQLite, and switches to tmux when native terminal panels are unavailable. CX Codex ★ 1,596repo stars codex-skin-pack-installer The codex-skin-pack-installer plugin stages and checks public-safe Codex skin packs from GitHub releases. Use it when a custom background, artwork, and a visible restore path matter. CX Codex ★ 1,596repo stars codex-rg-guard codex-rg-guard is a Claude Code plugin that narrows broad repository searches through a budgeted MCP tool. It selects files before returning bounded line matches. CX Codex ★ 1,596repo stars

Project sponsors

Companies that keep this analytics open