agent-token-usageSummarize daily LLM token usage per OpenClaw agent from trajectory logs, showing input, output, cache reads/writes, total, and optional billable token estima...
Install via ClawdBot CLI:
clawdbot install symbolstar/agent-token-usageGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://www.apple.com/DTDs/PropertyList-1.0.dtdUses known external API (expected, informational)
raw.githubusercontent.comAudited May 21, 2026 · audit v1.0
Generated Oct 2, 2026
An engineering team running dozens of OpenClaw agents needs to know which agents consume the most LLM tokens each day to catch runaway loops or bloated context windows. They use this skill's CLI to get a ranked per-agent token table by UTC or local date.
A company reselling agent-based automation wants a billable-equivalent token estimate per customer agent before invoicing. They run the CLI with --billable to weight cache reads and writes, producing a defensible usage report each day.
A manager wants a one-click token usage view embedded directly in the OpenClaw Control UI, next to Search. They install the optional header button via apply-ui.sh and check today's per-agent breakdown in a modal during standups.
A performance engineer investigates why certain agents burn 100x more tokens than sessions_list suggests, by reading canonical session logs and comparing input vs cacheRead distribution. The skill reveals whether high token counts come from cheap cache reads or expensive raw input.
After switching model providers, teams use this skill to re-baseline per-agent token consumption and detect anomalies in cacheWrite and output ratios. Historically accurate session-log parsing lets them validate that provider-side accounting matches internal numbers.
The CLI ships free with the OpenClaw ecosystem, while advanced UI features like the Control UI button and launchd auto-refresh offer convenience. Revenue comes indirectly through ecosystem growth and paid support or hosting.
Token attribution is packaged as a paid observability module for multi-agent platforms needing per-tenant cost transparency. It integrates CSV/JSON exports and dashboards for billing reconciliation.
Teams pay for expert setup of token accounting pipelines, timezone-aware bucketing, and reconciliation with provider invoices. The skill serves as a starting point for custom analytics engagements.
💬 Integration Tip
Run the zero-setup Python CLI first to validate per-agent numbers, then optionally install the Control UI button with apply-ui.sh for daily visibility; re-run apply-ui.sh after any openclaw update to keep the patched bundle working.
Scored Oct 2, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...
AI agent for finance search agent tasks