首页 › 龙虾技能列表 › OpenClaw Model Usage — 技能工具

OpenClaw Model Usage — 技能工具

v1.2.1

Inspect local OpenClaw model usage directly from session logs. Use when asked for the current model, recent model usage, usage breakdown by model, token tota...

0· 112·0 当前·0 累计
by @ranasalalali (Rana Salal Ali)·MIT-0
下载技能包
License
MIT-0
最后更新
2026/4/2
安全扫描
VirusTotal
无害
查看报告
OpenClaw
安全
high confidence
This skill is internally consistent: it reads local OpenClaw session JSONL/index files to produce local summaries and an HTML dashboard, and it does not request credentials or reach out to external endpoints.
评估建议
This skill appears to do what it says: parse local OpenClaw session JSONL files and build local summaries and an HTML dashboard. Before installing/running: (1) confirm you have Python 3.12+ available (the package requires it), (2) be aware it will read files under ~/.openclaw/agents by default (so don't run it if those logs are sensitive or you don't want local analysis), (3) the dashboard is written locally (--out path) and is self-contained (no external scripts), and (4) no credentials or netw...
详细分析 ▾
✓ 用途与能力
Name/description match the code and instructions: the package includes a Python CLI and script that parse ~/.openclaw/agents/*/sessions/*.jsonl and sessions.json to produce usage summaries and an optional local HTML dashboard. Nothing requested (env vars, binaries, config paths) is unrelated to this purpose.
✓ 指令范围
SKILL.md and the CLI are scoped to reading local session JSONL and sessions.json files, producing summaries and a self-contained HTML file. The instructions explicitly direct the agent to use a local root (default ~/.openclaw/agents) and warn not to use test fixtures for production. There are no instructions to collect or transmit data to external endpoints.
✓ 安装机制
No install spec is provided (instruction-only at registry level) and the project bundles Python scripts and a CLI implementation. This is low-risk: nothing is fetched from external URLs and no archive extraction or remote installs are present in the metadata. Running the tool requires a local Python runtime (pyproject requires >=3.12).
✓ 凭证需求
The skill requires no environment variables, credentials, or special config paths beyond reading local OpenClaw logs. The requested file access (user home ~/.openclaw/agents) is coherent with the described functionality. No unrelated secrets or external service keys are requested.
✓ 持久化与权限
The skill is not forced-always (always:false) and does not modify other skills or global agent configuration. It writes output only when asked (e.g., --out for dashboard) and otherwise performs read-only analysis of local logs.
安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

运行时依赖

无特殊依赖

版本

latestv1.2.12026/3/27

Clarify live dashboard usage and mark fixtures as development-only

● 无害

安装命令 点击复制

官方npx clawhub@latest install openclaw-model-usage
镜像加速npx clawhub@latest install openclaw-model-usage --registry https://cn.clawhub-mirror.com

技能文档

Use this skill to inspect local OpenClaw model usage directly from session JSONL files.

When to use

Use this skill when the user asks for:

  • the current / most recent model in use
  • recent model usage
  • usage summaries by provider/model
  • token totals by model
  • cost summaries by model when available
  • per-agent or per-session usage
  • session/subagent rollups
  • daily model usage summaries
  • a compact summary plus an optional HTML dashboard

What it does

This skill provides a local-first replacement for external model-usage workflows.

It reads OpenClaw session logs directly and does not depend on CodexBar.

Preferred usage

Start with a short human-readable summary:

python {baseDir}/scripts/model_usage.py
python {baseDir}/scripts/model_usage.py overview
python {baseDir}/scripts/model_usage.py top-agents
python {baseDir}/scripts/model_usage.py top-sessions

Generate the HTML dashboard from real local logs when the user wants a richer artifact:

python {baseDir}/scripts/model_usage.py dashboard --root ~/.openclaw/agents --out dist/dashboard.html --title "OpenClaw Usage Dashboard"

Recommended response pattern:

  • return a short human-readable summary first
  • optionally generate and attach the HTML dashboard for richer inspection on phone/desktop

JSON output

python {baseDir}/scripts/model_usage.py overview --json --pretty
python {baseDir}/scripts/model_usage.py sessions --json --pretty
python {baseDir}/scripts/model_usage.py subagents --json --pretty
python {baseDir}/scripts/model_usage.py rows --limit 20 --json --pretty

Inputs

Default real source:

~/.openclaw/agents

Important:

  • use the real local OpenClaw log root for user-facing summaries and dashboards
  • do not use tests/fixtures_root unless you are intentionally running development tests
  • fixture roots generate sample/test output, not the user's real usage report

References

If you need field-level sourcing details, read:

  • references/discovery.md
数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制

了解定制服务