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/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/quota)<a href="https://agentmods.dev/commands/omrikais/cctally/quota"><img src="https://agentmods.dev/badge/commands/omrikais/cctally/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 | $0.03312 |
| Opus 5 | $0.00000 | $0.01656 |
| Sonnet 5 | $0.00000 | $0.00662 |
| Haiku 4.5 | $0.00000 | $0.00331 |
Grade A, and why
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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cctally quota
Reports how much of your weekly Claude quota your usage consumes, computed from your own token history against a budget fitted from that same history, and reports whether the provider has changed the metering rate.
cctally quota
cctally quota --json
cctally quota --since 2026-08-01
cctally quota --account [email protected]
cctally quota --reset-calibration
What the fitted value is, and what it is not
The command fits one number: the effective blended weighted units per general-weekly point. Weighted units are token counts scaled by four fixed coefficients — fresh input at 1.0, output at 4.73, one-hour cache writes at 1.03 and cache reads at 0.0031 — and the fitted value is the total weighted units your history spent divided by the total meter movement it produced.
Four disclosures follow from how that value was obtained, and none of them is a caveat you can safely skip.
It is not a provider budget. It is one blended exchange rate, valid for the mixture of models and token classes your own retained history shows. It says nothing about any individual model family and it is not an Opus budget, a Sonnet budget or a plan allowance.
It is the provider's budget minus an unmeasured, workload-dependent amount. Your quota is charged for work this machine cannot see — usage from claude.ai, the desktop app, another machine, and the summarisation call a compaction makes, which carries no usage block and never reaches local session data. Every one of those raises the meter without raising the local token total, so the fitted units-per-point comes out lower than the provider's own figure by however much of that you do.
No per-family multiplier ships. Every family known to drain the general weekly meter contributes through the same four token-class coefficients. The research prototype carried a MODEL_WEIGHT_DEFAULT of 0.70 for anything it did not recognise; nothing like it ships, and an unrecognised family withholds the day instead.
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 · 150 lines · 0 tokens per session scan A 9ae5180d9851
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 3,312 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
git
Git operations with intelligent commit messages and workflow optimization.
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.