Favicon of model-usage

model-usage Skill

AI Agent SkillTypeScriptOpen source

Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns. Published by openclaw in openclaw.

Decision snapshot

Is this a fit?

Best for

Developers using openclaw, Includes SKILL.md, Reusable instructions

Works with

OpenClaw

Access

Shell access

Setup

Copy skill directory

Project health

1 month ago · NOASSERTION license

Considerations

Access note: Shell access.

How to use model-usage Skill

Compatible clients

OpenClaw

What is model-usage Skill?

Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns. Published by openclaw in openclaw. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Trust signal
95/100
Maintenance signal
90/100
Adoption signal
100/100

Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement. See how SkillIndex evaluates profiles.

Key capabilities

  • Includes SKILL.md support
  • Reusable instructions support
  • Developers using openclaw

Declared skill metadata

  • Source file: skills/model-usage/SKILL.md

These fields retain source and confidence evidence from the indexed SKILL.md.

Compatibility and setup

Copy skill directoryOpenClaw
  • Install or run with Copy skill directory
  • Works with OpenClaw
  • Shell access

Requirements and access

Shell access

Security and permissions

Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.

Shell access

When to use model-usage Skill

  • Use it for developers using openclaw.

Built with

TypeScriptCopy skill directoryOpenClaw

Editorial notes

Source

  • Creator: openclaw
  • Repository: openclaw/openclaw
  • Skill file: skills/model-usage/SKILL.md

What it does

Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.

Skill instructions

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. CodexBar ships CLI builds for macOS and Linux. When codexbar is on PATH, the skill reads local usage directly; the bundled Python summarizer also accepts exported CodexBar JSON through --input 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. bash python {baseDir}/scripts/modelusage.py --provider codex --mode current python {baseDir}/scripts/modelusage.py --provider codex --mode all python {baseDir}/scripts/modelusage.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

Verified compatibility and discovery

Frequently asked questions

What is model-usage?

model-usage is a open-source AI agent skill for OpenClaw with Copy skill directory. Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.

Who is model-usage best for?

model-usage is best for reusing agent instructions, scripts, and references, openclaw users.

How do I install model-usage?

Install or run model-usage using Copy skill directory. Check model-usage for the latest setup command.

Is model-usage actively maintained?

model-usage may need a closer maintenance check before production use.

Share:

Stars
384,631
Forks
80,839
Last commit
1 month ago
Last verified
Jul 31, 2026
Metadata fetched
Jul 31, 2026
Repository age
10 months
License
NOASSERTION

Project health auto-fetched from the source repository.

Maintain this resource?

Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.

Alternatives to model-usage