← Back to Skills Marketplace
161
Downloads
1
Stars
0
Active Installs
5
Versions
Install in OpenClaw
/install claude-usage-analyzer
Description
Analyze Claude Code token usage. Shows where tokens went, which projects cost most, and how to reduce waste. Use when user asks about token usage, costs, or...
README (SKILL.md)
Claude Usage Analyzer
Analyze your Claude Code token usage by parsing local session logs.
Data access
- Reads
~/.claude/projects/*/*.jsonl(local Claude Code session logs) - Runs offline, no network access, no API keys, no credentials
- Open source: https://github.com/SingggggYee/claude-usage-analyzer
Usage
Requires the claude-usage-analyzer CLI to be pre-installed. See https://github.com/SingggggYee/claude-usage-analyzer for installation instructions.
claude-usage-analyzer
More commands:
claude-usage-analyzer report --days 7(last 7 days)claude-usage-analyzer sessions(top sessions by cost)claude-usage-analyzer session \x3Cid>(per-turn breakdown)claude-usage-analyzer --json(machine-readable output)
Usage Guidance
This skill intends to parse your local Claude session logs at ~/.claude/projects/*/*.jsonl and run a local CLI. Before installing or invoking it: (1) confirm the claude-usage-analyzer CLI source on the linked GitHub repo and review its code/install instructions; (2) inspect ~/.claude files for sensitive data you don't want parsed or exposed; (3) prefer manually running the CLI locally first to see what it does and what it outputs; (4) be aware that SKILL.md claims 'no network access' but installing the CLI or running it could use the network — verify network behavior; (5) note the registry metadata does not declare the config path or required binary — ask the publisher to correct metadata or provide an install spec before proceeding.
Capability Analysis
Type: OpenClaw Skill
Name: claude-usage-analyzer
Version: 1.0.3
The skill bundle acts as a wrapper for the `claude-usage-analyzer` CLI tool, designed to analyze local Claude Code session logs. The instructions in `SKILL.md` and metadata in `_meta.json` are consistent with the stated purpose of reporting token usage and costs. No evidence of malicious intent, data exfiltration, or prompt injection was found; the requested access to `~/.claude/projects/` is necessary for the tool's functionality.
Capability Assessment
Purpose & Capability
The skill claims to analyze Claude Code session logs, which reasonably requires reading files under ~/.claude/projects/*.jsonl and a small CLI. However the registry metadata declares no required config paths and no required binaries while SKILL.md lists ~/.claude/projects/*/*.jsonl and requires the 'claude-usage-analyzer' CLI — this mismatch is inconsistent and unexplained.
Instruction Scope
SKILL.md explicitly directs the agent to read local Claude session logs at ~/.claude/projects/*/*.jsonl and run a local CLI. Reading those local logs is coherent with the stated purpose, but the skill will access potentially sensitive local data; SKILL.md also asserts 'no network access' but provides a GitHub link for the CLI, so network activity could occur during CLI installation or if the CLI itself phones home.
Install Mechanism
This is instruction-only with no install spec in the registry. SKILL.md requires a preinstalled 'claude-usage-analyzer' CLI and points to a GitHub repo for installation; the registry should have declared this dependency. Lack of an install spec is low technical risk but increases ambiguity about what will be installed and from where.
Credentials
The skill requests no environment variables or credentials, which is proportionate for an offline, local-log analyzer.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent agent-wide privileges. It does not modify other skills or system-wide settings per the provided files.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install claude-usage-analyzer - After installation, invoke the skill by name or use
/claude-usage-analyzer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
Fix metadata declaration for security
scan
v1.0.2
Fix display name
v1.0.1
Update links from ccwhy to claude-usage-analyzer
v0.2.0
Declare config paths and binary dependency explicitly. Remove inline install instructions to resolve security scan flags.
v0.1.0
Initial release as claude-usage-analyzer
Metadata
Frequently Asked Questions
What is Claude Usage Analyzer?
Analyze Claude Code token usage. Shows where tokens went, which projects cost most, and how to reduce waste. Use when user asks about token usage, costs, or... It is an AI Agent Skill for Claude Code / OpenClaw, with 161 downloads so far.
How do I install Claude Usage Analyzer?
Run "/install claude-usage-analyzer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Claude Usage Analyzer free?
Yes, Claude Usage Analyzer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Claude Usage Analyzer support?
Claude Usage Analyzer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Claude Usage Analyzer?
It is built and maintained by SingYee (@singggggyee); the current version is v1.0.3.
More Skills