manifest-buildSmart LLM Router for OpenClaw. Save up to 70% by routing every request to the right model. No coding required.
Install via ClawdBot CLI:
clawdbot install brunobuddy/manifest-buildGrade 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/mnfst/manifestAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
A company uses OpenClaw agents to handle customer inquiries across multiple channels. Manifest routes each request to the most cost-effective LLM based on complexity, saving up to 70% on API costs while tracking token usage and spending in real-time. This ensures efficient budget management and provides insights into performance metrics like latency and error rates.
An agency produces blog posts, social media content, and marketing copy for clients using OpenClaw. Manifest intelligently routes requests to appropriate models for different content tiers, monitors token consumption trends, and sets spending caps with alerts to prevent budget overruns. The dashboard helps analyze cost breakdowns by model and optimize routing strategies.
An online learning platform employs OpenClaw agents to generate personalized study materials and answer student questions. Manifest routes queries based on complexity, tracks token usage to estimate resource needs, and provides health checks to ensure reliable connectivity. This allows the platform to scale efficiently while controlling costs with real-time spending insights.
A healthcare research team uses OpenClaw to process and summarize medical literature. Manifest routes requests locally in offline mode to ensure data privacy, stores telemetry in a local SQLite database, and monitors performance metrics like latency and error rates. This enables secure, cost-effective analysis without external API dependencies.
A fintech company deploys OpenClaw agents to provide financial advice and market insights. Manifest routes complex reasoning tasks to higher-tier models and simpler queries to cost-effective ones, tracking costs and tokens to optimize spending. Agent tools allow real-time queries on usage and health, ensuring reliable service within budget limits.
Manifest offers a cloud service with a dashboard for real-time monitoring and routing, charging users a monthly subscription based on usage tiers or number of agents. Revenue comes from recurring fees, with potential upsells for advanced features like custom routing algorithms or priority support. This model targets businesses seeking predictable billing and scalable cost savings.
A free tier provides basic routing and limited dashboard access, while premium plans unlock advanced features such as detailed analytics, email alerts, and higher spending caps. Revenue is generated from upgrades, with enterprise plans offering offline local mode and Tailscale integration for enhanced security. This attracts a broad user base and converts high-value customers.
Manifest sells annual licenses to large organizations for on-premises deployment, including local mode and custom integrations. Revenue includes upfront licensing fees, ongoing support contracts, and training services. This model caters to industries with strict data privacy requirements, such as healthcare or finance, ensuring compliance and control.
💬 Integration Tip
Start with cloud setup for quick deployment and cost tracking; use local mode only if data privacy is critical, as it requires manual dashboard hosting.
Scored Apr 19, 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.
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.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.