Skip to content
Skills Library
AI & agents · Analysis

model-usage

/model-usage

Summarize per-model usage cost from local CodexBar cost JSON. Use when you need current-model or all-model cost breakdowns for Codex or Claude usage.

Licence
MIT
Last repository change
28.08.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
4
Scripts
1
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 28.08.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/model_usage.py

What it does and when to use it

Summarize per-model usage cost from local CodexBar cost JSON. Use when you need current-model or all-model cost breakdowns for Codex or Claude usage.

Original author description

Summarize per-model usage cost from local CodexBar cost JSON. Use when you need current-model or all-model cost breakdowns for Codex or Claude usage.

How it works

  1. Workflow
  2. Current Model Summary
  3. Full Model Breakdown
  4. File/Stdin Input
  5. Guardrails
  6. Scope Boundary
  7. References
Original SKILL.md headings · 55 lines, 176 words
SKILL.md preview
---
name: model-usage
description: Summarize per-model usage cost from local CodexBar cost JSON. Use when you need current-model or all-model cost breakdowns for Codex or Claude usage.
---

# Model Usage

Use this skill to report model-level usage cost from local CodexBar data.

## Workflow

1. Load cost data from `codexbar cost --format json` or from a saved JSON file.
2. Choose `current` for the most recent model signal, or `all` for aggregate breakdown.
3. Emit text or JSON output for downstream planning docs.
4. Feed this output into `usage-watcher` and `skill-cost-credit-governor` when needed.

## Current Model Summary

```bash
python3 "$CODEX_HOME/skills/model-usage/scripts/model_usage.py" \
  --provider codex \
  --mode current
```

## Full Model Breakdown

```bash
python3 "$CODEX_HOME/skills/model-usage/scripts/model_usage.py" \
  --provider codex \
  --mode all \
  --format json \
  --pretty
```

## File/Stdin Input

```bash
python3 "$CODEX_HOME/skills/model-usage/scripts/model_usage.py" \
  --provider claude \
  --input /tmp/codexbar-cost.json \
  --mode all
```

## Guardrails

- Use local input only in this lane.
- Do not commit raw usage exports that include personal metadata.
- Keep derived summaries in JSON/text artifacts under `.tmp/` for reproducible review.

## Scope Boundary

Use this skill only for model-level usage summarization.

Do not use this skill for billing exports, payment actions, or account mutation.

## References

- `references/codexbar-cli.md`
Files in this package (4)
  • SKILL.md 1 KB
  • agents/openai.yaml 1 KB
  • references/codexbar-cli.md 1 KB
  • scripts/model_usage.py 10 KB

Versions

RepositoryScoreLicence
This page · grtninja/skill-arbiter100MIT
cowork-os/cowork-os100MIT

Database snapshot: 13.11.2026 · package version 3a559f8c5f1d (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100cost-tracking
    Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date.
  • 100cost-tracking
    Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date.
  • 100cost-tracking
    Track and report OpenAI Codex token usage, spending, and budgets from a local cost-tracking database. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by project, tool, session, or date.
  • 100cost-tracking
    Track and report Claude Code token usage, spending, and budgets from a local cost-tracking database. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by project, tool, session, or date.
  • 100tokenmeter
    Open the Tokenmeter dashboard, a local web page that tracks token usage, cost, rate-limit windows and cache misses for every prompt in Claude Code, Codex and Copilot CLI. Use when the user asks about token usage, token spend, cost per prompt or per commit, cache hit rate, usage…
  • 100cost-estimate
    Estimate the cost of a task before starting it. Analyzes task complexity, predicts token usage, and compares cost across all Claude models. Use when user says 'estimate cost', 'how much will this cost', 'cost estimate', or '/cost-estimate'.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.