model-usage

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.

Install with Tessl CLI

npx tessl i github:qsimeon/openclaw-engaging --skill model-usage

What are skills?

3.70x

Review — 88%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Evaluation — 100%

↑ 3.70x

Agent success when using this skill

Validation — 9 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

47%

Identify Current AI Model Usage from Cost Logs

Current model cost reporting from JSON input

Criteria

Without context

With context

Uses model_usage.py script

100%

Uses --input flag

100%

Correct --provider flag

100%

Uses --mode current

100%

Correct current model identified

100%

Total cost reported

100%

Latest day cost reported

100%

Output saved to file

100%

Text output format used

100%

Daily row count present

100%

Without context: $0.2002 · 44s · 9 turns · 14 in / 2,837 out tokens

With context: $0.4540 · 1m 9s · 23 turns · 4,250 in / 4,064 out tokens

100%

93%

Generate a Claude Model Cost Breakdown Report

All-models JSON cost breakdown

Criteria

Without context

With context

Uses model_usage.py script

100%

Uses --mode all

100%

Uses --provider claude

100%

Uses --format json

100%

Uses --pretty flag

100%

Uses --input flag

100%

JSON output has mode: all

100%

JSON output has models array

20%

100%

Models sorted by cost

100%

Output saved to file

100%

Without context: $0.1887 · 44s · 11 turns · 15 in / 2,930 out tokens

With context: $0.4906 · 1m 20s · 24 turns · 606 in / 4,559 out tokens

100%

78%

Check Recent Costs for a Specific Claude Model

Time-windowed usage with model override

Criteria

Without context

With context

Uses model_usage.py script

100%

Uses --input flag

100%

Uses --days flag

100%

Uses --model flag

100%

Uses --provider claude

100%

Uses --mode current

100%

Correct model cost reported

100%

Output saved to sonnet_usage.txt

100%

report.sh contains flags

100%

Does not invoke codexbar binary

100%

Without context: $0.2741 · 1m 9s · 15 turns · 22 in / 4,749 out tokens

With context: $0.3648 · 1m 7s · 18 turns · 596 in / 3,991 out tokens

Evaluated: 3 days ago
Agent: Claude Code
Model: Unknown

Table of Contents

Identify Current AI Model Usage from Cost Logs Generate a Claude Model Cost Breakdown Report Check Recent Costs for a Specific Claude Model

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.