$ loading_
Summarize CodexBar local cost logs by model for Codex or Claude.
This skill appears to be an open-source local summarization tool that processes CodexBar local cost logs or user-provided JSON, with no stated secrets or remote egress. Given it is prompt-only, open source, and widely adopted, overall risk is low, though local command invocation and file/log access still warrant minimal-privilege use.
The material explicitly states there are no required keys or environment variables. The README only describes reading local cost logs or JSON files, with no API tokens, account credentials, or other sensitive authentication requirements.
System checks indicate no remote endpoints, and the documentation does not declare sending data to external services. Inputs are described as local CodexBar CLI output or local/stdin JSON, with no explicit data egress path shown.
The README states it will by default run the local command `codexbar cost --format json --provider ...` and use a bundled Python script for summarization. This is a normal local-tool capability, and no system permissions beyond the stated function are evident.
Its function depends on reading CodexBar local cost logs or user-specified JSON files/stdin, which is limited local data access. The material does not show arbitrary directory scanning, writes to sensitive paths, or other excessive access.
The source is an open-source GitHub repository with extremely high community adoption (~377k stars), which is a strong positive trust signal. Although the license is not stated and maintenance status is unknown, the provided material shows no closed-source distribution, unclear origin, or suspicious injection indicators.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "model-usage" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/skills/model-usage/SKILL.md 2. Save it as ~/.claude/skills/model-usage/SKILL.md 3. Reload skills and tell me it's ready
Please read the local CodexBar cost logs and summarize current usage costs by model, listing total cost, call count, and share for Codex and Claude separately.
A current cost overview table grouped by model, separated for Codex and Claude.
Analyze all local CodexBar cost logs and provide a full cost breakdown by model, including cumulative cost, time range, model ranking, and unusually high-cost items.
A full cost report across all logs with model-level summaries and anomaly highlights.
Compare Codex and Claude spending in the local CodexBar logs, grouped by model, showing costs, differences, and main sources of consumption.
A comparison report showing cost differences and main spending drivers between the two model groups.
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.
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
modelBreakdowns.modelsUsed when breakdowns are missing.--model <name> when you need a specific model.codexbar cost --format json --provider <codex|claude>.--input with exported CodexBar JSON until this skill documents a supported local CodexBar install path for that platform.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
--format json --pretty).references/codexbar-cli.md for CLI flags and cost JSON fields.Create and review technical docs and agent instruction files in repositories.
Verify an OpenClaw release is fully published and working across all channels.
Fetch GitHub issues, create fixes, open PRs, and handle reviews.
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
Regenerate OpenClaw release changelog sections from Git history before releases.
Navigate Feishu knowledge bases and surface relevant wiki pages and links.
Query Claude Code usage and costs with natural-language spend analysis insights.
Track Claude Code token usage, costs, and plan limits for better control.
Search past Claude Code conversations and track usage costs inside Claude.
Coordinate Codex and local Claude Code for engineering, review, and automation workflows.
Search past Claude Code chats to recover facts, decisions, and context.
Use a local LLM to index codebases and compress Claude Code context.