What is the current model logic?

The current model is determined from the most recent daily row with modelBreakdowns; the model with the highest cost in that row is reported. If breakdowns are missing, it falls back to the last entry in modelsUsed. You can override with --model to target a specific model.

What inputs does it accept?

Inputs are CodexBar cost JSON, provided via file, stdin, or the CLI default output. You can pipe or redirect the JSON into the summarizer as needed.

What outputs are produced and how can I use them?

Outputs are per-model cost values. The default is human-readable text; you can request JSON with --format json --pretty for automation. Note that CodexBar output does not split tokens by model.

Model Usage

Verified

@JustAskNudge

npx machina-cli add skill @JustAskNudge/model-usage-skill --openclaw

Files (1)

SKILL.md

2.2 KB

Model usage

Overview

Get per-model usage cost from CodexBar's local cost logs. Supports "current model" (most recent daily entry) or "all models" summaries for Codex or Claude.

TODO: add Linux CLI support guidance once CodexBar CLI install path is documented for Linux.

Quick start

Fetch cost JSON via CodexBar CLI or pass a JSON file.
Use the bundled script to summarize by model.

python {baseDir}/scripts/model_usage.py --provider codex --mode current
python {baseDir}/scripts/model_usage.py --provider codex --mode all
python {baseDir}/scripts/model_usage.py --provider claude --mode all --format json --pretty

Current model logic

Uses the most recent daily row with modelBreakdowns.
Picks the model with the highest cost in that row.
Falls back to the last entry in modelsUsed when breakdowns are missing.
Override with --model <name> when you need a specific model.

Inputs

Default: runs codexbar cost --format json --provider <codex|claude>.
File or stdin:

codexbar cost --provider codex --format json > /tmp/cost.json
python {baseDir}/scripts/model_usage.py --input /tmp/cost.json --mode all
cat /tmp/cost.json | python {baseDir}/scripts/model_usage.py --input - --mode current

Output

Text (default) or JSON (--format json --pretty).
Values are cost-only per model; tokens are not split by model in CodexBar output.

References

Read references/codexbar-cli.md for CLI flags and cost JSON fields.

Source

git clone https://clawhub.ai/JustAskNudge/model-usage-skillView on GitHub

Overview

Get per-model usage cost from CodexBar's local logs for Codex or Claude. It supports reporting the current (most recent) model or a full breakdown across all models, and can output in text or JSON for automation. Triggered when model-level usage data is requested or when you need a scriptable per-model summary from codexbar cost JSON.

How This Skill Works

The tool reads CodexBar cost data, selecting the current model from the latest daily row with modelBreakdowns or falling back to the last entry in modelsUsed if breakdowns are missing. You can override with --model to target a specific model. Outputs can be plain text or JSON via --format json --pretty for easy integration.

When to Use It

When you need per-model usage/cost data from CodexBar
When you require a scriptable per-model summary from codexbar cost JSON
When you want the current (most recent) model's cost
When you need a full all-model cost breakdown for comparison
When testing or benchmarking by forcing a specific model with --model

Quick Start

Step 1: Fetch cost JSON via codexbar cost or provide a JSON file
Step 2: Run the summarizer, e.g., python {baseDir}/scripts/model_usage.py --provider codex --mode all
Step 3: Output as JSON with --format json --pretty for automation, or view text by default

Best Practices

Use current mode for live costs and all mode for a complete breakdown
Specify provider codex or claude to match your data source
Output JSON (--format json --pretty) when feeding pipelines or dashboards
Provide input via file or stdin to fit into automation workflows
Rely on the modelBreakdowns logic first, with fallback to modelsUsed if breakdowns are missing

Example Use Cases

Billing a Codex-based service and needing the current model cost for chargeback
CI job comparing per-model costs across Codex and Claude models
Script exporting per-model costs to a monitoring dashboard
Weekly cost review by model for budgeting and optimization
Testing model cost differences by forcing a specific model with --model

Frequently Asked Questions

Add this skill to your agents