claude

claude is a command for coding agents from omrikais/cctally. It costs 0 tokens per session (646 once invoked), scanned A, original, Apache-2.0.

A set of offline reports for Claude usage, grouped under one command group. It can run existing `ccusage claude` commands and show daily, weekly, monthly, session, block, or status-line results.

In plain words
What is it for?
Use it to inspect Claude usage by date, session, or five-hour block, including machine-readable JSON output for scripts.
Why use it?
It gives Claude usage reports without needing an internet connection or changing familiar commands. Claude costs are estimates from transcripts, not exact billing totals.

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/claude
Clone the repo
git clone --depth 1 https://github.com/omrikais/cctally

Wrote 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.

agentmods badge for claude

README.md
[![agentmods](https://agentmods.dev/badge/commands/omrikais/cctally/claude.svg)](https://agentmods.dev/commands/omrikais/cctally/claude)
Your own site
<a href="https://agentmods.dev/commands/omrikais/cctally/claude"><img src="https://agentmods.dev/badge/commands/omrikais/cctally/claude.svg" alt="Measured on agentmods" height="20"></a>
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 646 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00646
Opus 5 $0.00000 $0.00323
Sonnet 5 $0.00000 $0.00129
Haiku 4.5 $0.00000 $0.00065

Measured 4d ago against content hash dc399b2154b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude 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.

docs/commands/claude.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude

Claude-source usage reports under a hierarchical subgroup. Drop-in for ccusage claude <cmd> — paste a ccusage claude … command verbatim and it runs offline.

Cost coverage: Claude dollar and token totals are transcript-derived lower bounds, not exact /usage billing totals.

Each leaf shares its engine with the matching flat cctally <cmd> alias — the output (table / --json / exit code) is identical. The flat forms (cctally daily, …) remain fully supported as back-compat aliases; the subgroup form is the canonical, going-forward syntax.

Synopsis

cctally claude <command> [flags]

<command> ∈ { daily, monthly, weekly, session, blocks, statusline }

Subcommands

Subcommand Same engine as Page
cctally claude daily cctally daily daily.md
cctally claude monthly cctally monthly monthly.md
cctally claude weekly cctally weekly weekly.md
cctally claude session cctally session session.md
cctally claude blocks cctally blocks blocks.md
cctally claude statusline cctally statusline statusline.md

Every flag, exit code, and output shape is exactly that of the linked flat page — there are no behavior differences. See each page for the full option reference.

Examples

cctally claude daily --since 2026-05-01
cctally claude blocks
cctally claude weekly --json
cctally claude session --breakdown

Notes

  • The subgroup mirrors ccusage's claude surface only. cctally-only Claude commands (five-hour-blocks, project, diff, range-cost, cache-report, report, forecast, percent-breakdown) are not added under claude — invoke them at the top level.
  • Bare cctally claude (no subcommand) exits non-zero with a command-required error.
  • No runtime deprecation warning is emitted by the flat forms; they are non-canonical, not deprecated.

Read the full file on GitHub · 65 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. 4d ago First seen · 65 lines · 0 tokens per session scan A dc399b2154b5

Subscribe to this mod's changes

claude is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 646 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.