ClawHub

Model Usage Linux

v1.0.0

Track OpenClaw AI token usage and cost per model on Linux by parsing session JSONL files. Use when asked about: token usage, API cost, how much has been spen...

⭐ 0· 981·15 current·16 all-time
by@hablabechir
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The skill name/description say it parses OpenClaw session JSONL files to report token/cost per model. The included script reads ~/.openclaw/agents/main/sessions/*.jsonl by default and computes per-model usage and cost. No unrelated dependencies, env vars, or binaries are requested — this is proportionate to the stated purpose.
✓
Instruction Scope
SKILL.md instructs running the bundled Python script and optionally specifying a sessions directory or JSON output. The script only reads session JSONL files, does not access other system config, environment variables, or network endpoints, and prints a local summary. It silently skips malformed JSON lines and uses a default sessions path; this is within expected scope.
✓
Install Mechanism
There is no install spec (instruction-only + included script). Nothing is downloaded or written to system locations by an installer. Running the script requires a local Python interpreter but no install-time network activity or package fetches are specified.
✓
Credentials
The skill requests no environment variables, no credentials, and no special config paths beyond reading the user's OpenClaw sessions directory (~/.openclaw/agents/main/sessions). This is appropriate for a local usage-reporting tool.
✓
Persistence & Privilege
The skill is not marked always: true and does not attempt to persist configuration or modify other skills. It runs as a normal user script and does not request elevated privileges or system-wide changes.
Assessment
This skill appears to be a local analyzer that reads your OpenClaw session JSONL files and prints usage/cost summaries. Before running: (1) confirm the sessions directory path is correct and contains only data you want analyzed, (2) review the included scripts/usage.py (it is short and clearly local-only), and (3) run it locally (or point it at a copy of the sessions) if you want to avoid analyzing live files. There is no network or credential access in the code, so risk is low, but avoid running arbitrary code you haven't inspected on sensitive systems.

Like a lobster shell, security has layers — review code before you run it.

latestvk974m1edwbq8fa34b7djzyhg4s81v1tp

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments