Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
steipete avatar

Model Usage

  • 3.2k installs
  • 385k repo stars
  • Updated August 3, 2026
  • steipete/clawdis

model-usage is a skill that summarizes CodexBar local cost logs by model for Codex or Claude in current or all-models modes.

About

Model Usage is a macOS-oriented skill for reading per-model AI usage costs from CodexBar local cost logs. It supports current model mode using the most recent daily row with modelBreakdowns and picking the highest-cost model, or all models mode for full summaries. Providers include codex and claude. Default input runs codexbar cost --format json --provider, while file or stdin input via --input works on any platform with exported JSON. The bundled scripts/model_usage.py handles summarization with optional --model override, text or JSON --format output, and --pretty printing. Current model logic falls back to the last entry in modelsUsed when breakdowns are missing. CodexBar CLI live reads are documented for macOS with brew cask install steipete/tap/codexbar; Linux and other platforms should pass exported JSON until a supported local install path exists. Output values are cost-only per model because CodexBar does not split tokens by model. References/codexbar-cli.md documents CLI flags and cost JSON fields for deeper inspection.

  • Summarizes CodexBar per-model costs for codex or claude providers.
  • Modes: current highest-cost model or all-models full breakdown.
  • Bundled model_usage.py supports live CLI, file, or stdin JSON input.
  • macOS live reads via codexbar cost; other platforms use --input exports.
  • Output is cost-only; CodexBar JSON does not split tokens per model.

Model Usage by the numbers

  • 3,177 all-time installs (skills.sh)
  • +156 installs in the week ending Aug 2, 2026 (Skillselion tracking)
  • Ranked #174 of 3,280 Productivity & Planning skills by installs in the Skillselion catalog
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Aug 3, 2026 (Skillselion catalog sync)
At a glance

model-usage capabilities & compatibility

Capabilities
current model and all models cost summarization · codex and claude provider selection · live codexbar cli or input file and stdin json · text and json formatted output via model_usage.p
Use cases
devops · planning
Platforms
macOS
From the docs

What model-usage says it does

Get per-model usage cost from CodexBar's local cost logs
SKILL.md
Values are cost-only per model; tokens are not split by model in CodexBar output
SKILL.md
npx skills add https://github.com/steipete/clawdis --skill model-usage

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs3.2k
repo stars385k
Security audit3 / 3 scanners passed
Last updatedAugust 3, 2026
Repositorysteipete/clawdis

How do I see per-model AI usage costs from my local CodexBar logs for Codex or Claude?

Summarize CodexBar local cost logs by model for Codex or Claude with current or full breakdowns via bundled Python script.

Who is it for?

macOS developers with CodexBar installed who want quick per-model cost breakdowns from local logs.

Skip if: Skip when you need token-level splits by model; CodexBar output is cost-only without per-model token counts.

When should I use this skill?

User asks for CodexBar cost summary, per-model usage, or current versus all-model spend breakdown.

What you get

Text or JSON summary of per-model costs from the latest daily row or full history via model_usage.py.

  • per-model cost summary text or JSON

By the numbers

  • Requires codexbar binary installed via Homebrew cask steipete/tap/codexbar
  • macOS-only per openclaw metadata os darwin constraint

Files

SKILL.mdMarkdownGitHub ↗

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.

Live CodexBar CLI invocation is currently documented for macOS only. The bundled Python summarizer is portable: if you already have exported CodexBar JSON, --input mode works anywhere Python is available.

Quick start

1. Fetch cost JSON via CodexBar CLI or pass a JSON file. 2. 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>.
  • macOS: use the bundled CodexBar CLI install path above for live local usage reads.
  • Linux/other platforms: use --input with exported CodexBar JSON until this skill documents a supported local CodexBar install path for that platform.
  • 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.

Related skills

How it compares

Pick model-usage over cloud billing dashboards when you already run CodexBar locally and want instant per-model totals from session logs without API credentials.

FAQ

Does this work off macOS?

Live codexbar CLI reads are macOS-only; use --input with exported JSON on other platforms.

How is current model chosen?

It uses the most recent daily row with modelBreakdowns and picks the highest-cost model, with --model override available.

Are token counts included per model?

No. Output values are cost-only; tokens are not split by model in CodexBar output.

Is Model Usage safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.