xergAudit and reduce AI agent runtime spend in dollars. Use for AI costs, agent spend, token waste, runtime attribution, detector coverage, and FinOps. Works with OpenClaw, Hermes, QM, Claude Code, Cursor, and generic event ingest.
Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://xerg.ai/pilotAudited Apr 17, 2026 · audit v1.0
Generated May 9, 2026
A company running multiple OpenClaw agents on a single server wants to identify which agents are wasting money through retries or loops. Using xerg audit --remote, they can see dollar-based waste categories and pinpoint the most expensive agents.
A DevOps team integrates xerg into their CI pipeline to enforce cost gates. They run xerg audit --push --fail-above-waste-rate 0.25 so that deployments fail if waste exceeds 25% of total spend, ensuring cost efficiency before code reaches production.
A company switches from GPT-4 to a cheaper model for their AI workflows. They run xerg audit --compare to see the dollar impact, confirming that the change reduced waste in the 'candidate-downgrade' category.
An organization with agents deployed on multiple VPS and Railway services needs a unified cost view. They configure ~/.xerg/remotes.json and run xerg audit --remote-config to aggregate spend and waste across all environments.
A healthcare company must audit workflow costs without sending sensitive data externally. They run xerg audit locally, outputting JSON for integration with their own analytics, and only push anonymized summaries.
Xerg's core auditing functionality is free and runs entirely locally. Users can audit unlimited workflows without any account or payment, paying only for optional cloud features like result pushing.
Xerg offers a cloud API where users can push audit results for cross-agent dashboards and historical trending. Revenue comes from subscription tiers based on number of agents and data retention.
For large enterprises, Xerg provides priority support, custom integrations, and on-premise deployment options. Revenue is generated through annual contracts and professional services.
💬 Integration Tip
Start with 'xerg doctor' to verify data sources, then run 'xerg audit' for a quick cost overview. For CI, add 'xerg audit --push --fail-above-waste-usd 100' as a pre-deployment step.
Scored Jul 6, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.