About model-usage
model-usage is a skill for summarizing local CodexBar CLI cost usage by model for Codex or Claude. It can report the most recent model or a full model breakdown.
Key features
- 01Summarize usage by model
- 02Report the most recent model
- 03Break down usage across models
- 04Use CodexBar cost JSON in scripts
Use cases
- 01Review the latest model used by Codex or Claude
- 02Compare usage across models
- 03Generate a per-model summary from CodexBar cost JSON
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ cowork-os/ cowork-os --skill model-usageAfter installing, type/model-usagein Claude Code to confirm it loaded.
Bundled filesscripts/model_usage.py
Details
From the project READMEModel-usage
Purpose
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Routing
- Use when: Use when the user asks to use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current most recent model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
- Do not use when: Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
- Outputs: Outcome from Model-usage: task-specific result plus concrete action notes.
- Success criteria: Returns concrete actions and decisions matching the requested task, with no fabricated tool-side behavior.
Trigger Examples
Positive
- Use the model-usage skill for this request.
- Help me with model-usage.
- Use when the user asks to use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current most recent model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
- Model-usage: provide an actionable result.
Negative
- Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
- Do not use model-usage for unrelated requests.
- This request is outside model-usage scope.
- This is conceptual discussion only; no tool workflow is needed.
Runtime Prompt
- Current runtime prompt length: 1495 characters.
- Runtime prompt is defined directly in
../model-usage.json.
Comments
Markdown supported