Browse 46 published agents on Shared Context. Install them into Claude Code, Cursor, Gemini CLI, or Codex with one command.
A sub-agent is a separate LLM call with its own system prompt, tool allow-list, and role. The host agent hands off a specific task — code review, research, test generation — and the sub-agent returns a single structured answer. Its context stays isolated from the main conversation.
Reach for a sub-agent when the task benefits from a clean, short context window, a constrained tool set, or a different model from the primary agent. Reach for a skill when the task is a repeatable procedure the host itself should run. The overlap is real; most workflows combine both.
Shared Context installs an agent into the native location of each supported tool — `~/.claude/agents/`, `~/.cursor/agents/`, and so on. The YAML front matter is preserved because it is the agent specification.
Your AI chief of staff — distills expert knowledge into resources, finds off-the-shelf solutions, and manages your working context
Effortlessly create new AI resources with the correct format for any type.
Efficiently delegates independent audit tasks across multiple workers for comprehensive site analysis.
Analyzes integration exports from Boomi and Cyclr to create a standard integration schema and migration plan.
Validate generated CNI TypeScript code against migration schema for accuracy and compliance.
Orby is an interactive agent for navigating and managing the Prismatic platform.
Builds custom components for Prismatic with scaffolding and code generation.
Researches external APIs by analyzing documentation and extracting key specifications.
Builds Prismatic Code Native Integrations (CNI) with streamlined deployment and testing.
Guides developers in embedding Prismatic's marketplace and workflow builder into web applications.
Automate redistricting analyses for the ALARM fifty-states project.
Creates verified execution plans with acceptance criteria that block progression. Decomposes work into dependency-ordered waves of parallel tasks with grep-verifiable or command-runnable criteria.
Automate test writing and execution to ensure code quality.
Feature implementation agent for building and modifying code in isolated environments.
UI/UX design agent for visual design decisions and accessibility audits.
Automate the writing and updating of documentation to ensure accuracy and relevance.
Lint and static analysis agent for enforcing code quality standards.
Manage project documentation seamlessly with the Manager agent.