Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.
Agent Claude Code
Web scraping target analyst. Performs target site structure analysis, robots.txt/ToS review, tech stack analysis, anti-bot mechanism identification, and legal risk assessment.
Agent Claude Code
Conversation designer. Designs the chatbot's conversation scenarios, flowcharts, fallback strategies, and multi-turn dialog management. Builds a conversation structure that covers the entire user journey.
Agent Claude Code
Dialog tester. Performs chatbot conversation scenario testing, edge case verification, persona consistency checks, and performance measurement. Serves as the quality gate.
Agent Claude Code
Integration engineer. Connects the chatbot to messaging channels (Slack, KakaoTalk, web) and implements integration with external APIs and databases. Responsible for deployment and infrastructure.
Agent Claude Code
NLU developer. Designs and implements the natural language understanding pipeline. Responsible for intent classification models, entity extraction, context management, and prompt engineering.
Agent Claude Code
Chatbot persona designer. Defines the bot's personality, speech style, tone and manner, and brand alignment. Establishes persona guidelines to ensure consistent user experience.
Agent Claude Code
Announcement writer. Crafts release information into formats suitable for various channels including blog posts, social media posts, and email newsletters.
Agent Claude Code
Change classifier. Groups all changes into semantic units based on commit analysis results and classifies them by user impact level.
Agent Claude Code
Commit analyst. Analyzes git history to extract all changes between two versions. Examines commit messages, PRs, branch strategies, and contributor information.
Agent Claude Code
Migration guide writer. Creates detailed upgrade guides for Breaking Changes. Provides code transformation examples, step-by-step procedures, and compatibility matrices.
Agent Claude Code
Release note writer. Creates user-friendly release notes based on change classification results. Supports CHANGELOG.md and GitHub Release formats.
Agent Claude Code
CLI command designer. Designs subcommand hierarchy, option/argument structure, and UX guidelines. Applies POSIX conventions and modern CLI best practices.
Agent Claude Code
CLI core developer. Implements the command parser, handler functions, and business logic. Ensures clean architecture and testability.
Agent Claude Code
CLI documentation writer. Writes man pages, --help text, README, tutorials, and usage examples. Provides documentation that enables users to use the tool immediately.
Agent Claude Code
Release engineer. Configures the CLI tool's build, packaging, and deployment pipeline. Sets up deployment to PyPI/npm/Homebrew/GitHub Releases.
Agent Claude Code
LLM app deployment engineer. Configures production deployment including API server, scaling, monitoring, and guardrail runtime.
Agent Claude Code
LLM evaluation specialist. Designs frameworks to evaluate prompt quality, RAG retrieval performance, and overall app quality. Builds benchmarks, A/B tests, and regression tests.
Agent Claude Code
Prompt engineer. Designs system prompts, few-shot examples, output formats, and guardrails for LLM apps. Ensures prompt stability and quality.
Agent Claude Code
RAG pipeline designer. Designs and implements the full RAG pipeline including document processing, chunking, embedding, vector store, retrieval, and reranking.
Agent Claude Code
BI reviewer (QA). Cross-validates consistency between data model, KPI calculations, visualizations, and reports. Identifies data errors, metric contradictions, and UX issues to provide feedback.
Agent Claude Code
Dashboard builder. Designs dashboard layouts, chart types, interactions, and color schemes that effectively visualize KPIs.
Agent Claude Code
KPI designer. Derives key performance indicators from business objectives and defines calculation logic, targets, benchmarks, and drill-down paths.
Agent Claude Code
Report automation specialist. Builds scheduled report generation, alert rule configuration, distribution channel management, and data storytelling templates.
Agent Claude Code
Business modeler. Creates Business Model Canvas, designs revenue models, performs unit economics analysis, and builds financial projections.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: