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.
npx agentmods add commands/omrikais/cctally/codex-quotagit clone --depth 1 https://github.com/omrikais/cctallyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/omrikais/cctally/codex-quota)<a href="https://agentmods.dev/commands/omrikais/cctally/codex-quota"><img src="https://agentmods.dev/badge/commands/omrikais/cctally/codex-quota.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.03485 |
| Opus 5 | $0.00000 | $0.01742 |
| Sonnet 5 | $0.00000 | $0.00697 |
| Haiku 4.5 | $0.00000 | $0.00348 |
Grade A, and why
codex-quota scanned grade A with 0 findings 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 4d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cctally codex quota
Provider-native Codex quota history, current status, forecasts, reset blocks,
and percent-crossing breakdowns. This is a nested-only cctally extension; it
does not have a flat alias and is not a ccusage-codex drop-in.
Each result stays qualified by source root, logical limit, observed slot, and the actual native duration. cctally never sums, averages, or relabels independent quota percentages as a Claude five-hour or seven-day window.
Synopsis
cctally codex quota history [--since DATE_OR_ISO] [--until DATE_OR_ISO] [COMMON]
cctally codex quota statusline [--as-of ISO-8601] [COMMON]
cctally codex quota forecast [--as-of ISO-8601] [COMMON]
cctally codex quota blocks [--since DATE_OR_ISO] [--until DATE_OR_ISO] [COMMON]
cctally codex quota breakdown --reset-at ISO-8601 [--speed {auto,standard,fast}] [COMMON]
COMMON = [--root-key FULL_SOURCE_ROOT_KEY]
[--limit-key FULL_LOGICAL_LIMIT_KEY]
[--no-sync] [--config PATH] [--json]
Local-rollout data and freshness
These commands read quota observations retained from local Codex rollout files.
The observation is the payload.info.rate_limits object on a rollout record; a
record without that field carries no quota window and contributes nothing.
By default they first run one Codex cache sync; --no-sync reads the retained
local evidence without that sync. Either path reconciles the durable quota
projection before rendering, so a previously interrupted cache/stats update can
heal without mutating the physical observations.
freshnessSource is always "local-rollout". It is not a provider-live API
call and Codex has no OAuth refresh counterpart. Freshness uses the latest
physical local capture for an identity:
fresh— capture age is withinmax(900, min(windowMinutes * 6, 3600))seconds.stale— capture age is above that bound.future— capture is more than 300 seconds later than--as-of.unavailable— no valid capture exists.
Captures up to 300 seconds ahead are fresh for freshness but are never a
forecast baseline. Forecasting and alert qualification use only observations
at or before --as-of; a future observation cannot produce a current value or
an alert by itself.
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.
- 4d ago First seen · 258 lines · 0 tokens per session scan A be4bb6821d4a
codex-quota is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,485 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.