codex

A set of commands for viewing Codex usage reports and quota information. It includes daily, monthly, session, and weekly views, with results available as tables or JSON.

In plain words
What is it for?
Use it to inspect Codex usage by day, month, session, or week, and to run related project, date-range, cache, and cost reports.
Why use it?
It makes it easier to check how much Codex has been used and review costs or usage over different time periods.

Command

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 commands/omrikais/cctally/codex
Clone the repo
git clone --depth 1 https://github.com/omrikais/cctally
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,962 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 $0.00000 $0.01962
Opus 5 $0.00000 $0.00981
Sonnet 5 $0.00000 $0.00392
Haiku 4.5 $0.00000 $0.00196

Measured 2d ago against content hash 6946a33277ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex 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 2d ago.

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.

default) reads `service_tier` from `~/.codex/config.toml`. See the relevant
docs/commands/codex.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex

Codex (OpenAI) usage reports and native quota views under a hierarchical subgroup. daily/monthly/session are drop-ins for ccusage codex <cmd> — paste a ccusage codex … command verbatim and it runs offline. weekly is a cctally extension (upstream has no ccusage codex weekly).

The four accounting leaves share their engine with the matching flat cctally codex-<cmd> alias — the output (table / --json / exit code) is identical. The flat codex-* forms remain fully supported as back-compat aliases (drop-ins for the standalone ccusage-codex binary); the subgroup form is the canonical, going-forward syntax for the hierarchical ccusage codex … surface. The provider-aware leaves below pin the matching shared command to Codex instead.

Provider-aware analytics

Alongside the existing Codex compatibility reports, the codex subgroup pins the five shared analytics leaves to the Codex provider:

cctally codex project
cctally codex diff
cctally codex range-cost
cctally codex cache-report
cctally codex report

These are fixed-source aliases for the corresponding flat commands with --source codex; they intentionally do not accept a contradictory --source flag. The parallel cctally claude {project,diff,range-cost,cache-report,report} forms pin Claude. There is no cctally all subgroup: use the flat command with --source all, which always renders Claude then Codex instead of blending provider-native rows.

Use cctally codex cache-report for Codex token reuse (inclusive input, cached input, non-cached input, reasoning-inclusive output, and native cost), not a Claude cache-hit rate. Use cctally codex report for independent native quota-window/logical-limit series; it never turns them into a single Codex or cross-provider weekly percentage.

The older codex-daily, codex-monthly, codex-weekly, and codex-session commands remain their existing accounting-report family. Their ordinary terminal/JSON/empty output is unchanged; they now also accept read-only --config PATH and the share output flags documented in share.md.

Read the full file on GitHub · 136 lines

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. 2d ago First seen · 136 lines · 0 tokens per session scan B 6946a33277ae

Subscribe to this mod's changes

codex is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,962 tokens. 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 2026-08-31.