prompt-token-counterCount tokens and estimate costs for 300+ LLM models. Primary use: audit OpenClaw workspace token consumption (memory, persona, skills).
Install via ClawdBot CLI:
clawdbot install Zhaobudaoyuema/prompt-token-counterGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/Zhaobudaoyuema/prompt-token-counter](https://github.com/ZhaobAudited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Developers and teams building AI agents on OpenClaw can use this skill to audit token consumption across memory, persona, and skill files, helping optimize context window usage and reduce API costs. It supports over 300 LLM models for accurate cost estimation during development and testing phases.
Businesses deploying AI applications can integrate this skill to monitor and forecast API expenses by analyzing prompt token counts in real-time. This enables budget control and resource allocation, especially for high-volume or enterprise-scale AI operations.
Organizations in regulated industries, such as legal or healthcare, can audit AI-generated content and system prompts for token usage to ensure compliance with data limits and privacy standards. It helps identify oversized files that may risk exceeding context windows.
Academics and researchers studying LLM behavior can use this skill to analyze token distributions in AI agent configurations, facilitating experiments on efficiency and performance across different models and prompt structures.
Independent AI consultants and freelancers can leverage this skill to provide clients with detailed token audits and cost breakdowns for their OpenClaw setups, offering value-added services for optimization and troubleshooting.
Offer a free basic version for token counting and cost estimation, with premium features such as advanced analytics, batch processing, and integration with cloud services for recurring subscription revenue. This model targets individual developers and small teams.
Provide enterprise licenses with dedicated support, custom integrations, and enhanced security features for large organizations. Revenue comes from annual contracts, training sessions, and priority updates tailored to business needs.
Deploy the token counter as a cloud-based API service, allowing developers to integrate it into their applications via RESTful endpoints. Monetize through usage-based pricing, such as per-request fees or monthly quotas for scalable income.
💬 Integration Tip
Integrate this skill early in the development cycle to monitor token usage from the start, ensuring cost-effective design and avoiding context window overflows in production.
Scored Apr 19, 2026
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Gemini CLI for one-shot Q&A, summaries, and generation.
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates opencla...
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates opencla...
HTML-first PDF production skill for reports, papers, and structured documents. Must be applied before generating PDF deliverables from HTML.