An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
271 agents across 361 plugins.
Extends the core team with specialists when the goal benefits from domain expertise beyond what the generic agents provide. Runs once after the planner. Never…
Catches problems the verifier wouldn't — things that work but aren't done the right way. Uses researcher-defined quality standards to judge output.…
Completes exactly one task and moves the loop forward. Derives execution method from the goal and researcher findings. Output goes to the project directory,…
This is a reference for the researcher agent. Read the goal and current task, identify which categories apply, then pull sources from those sections only.…
Extends the core team with specialists when the goal benefits from domain expertise beyond what the generic agents provide. Runs once after the planner. Never…
Catches problems the verifier wouldn't — things that work but aren't done the right way. Uses researcher-defined quality standards to judge output.…
Completes exactly one task and moves the loop forward. Derives execution method from the goal and researcher findings. Output goes to the project directory,…
Makes the loop smarter over time by capturing what was learned. Runs after each auditor pass.
Turns the goal and research findings into a clear, executable task plan. Runs once after researcher and resource-scout during loop startup. Never executes the…
Maps what's known, what's needed, and what could go wrong before the executor acts. Also surfaces existing tools, MCPs, skills, and libraries that eliminate…
Maps everything available and connected in this environment before the loop starts. Provides exact usage syntax for every resource found. Runs once at loop…
Checks output against researcher-defined criteria, then runs the stop condition. Marks tasks done or failed. Never writes application code.
Makes the loop smarter over time by capturing what was learned. Runs after each auditor pass.
Turns the goal and research findings into a clear, executable task plan. Runs once after researcher and resource-scout during loop startup. Never executes the…
Maps what's known, what's needed, and what could go wrong before the executor acts. Also surfaces existing tools, MCPs, skills, and libraries that eliminate…
Maps everything available and connected in this environment before the loop starts. Provides exact usage syntax for every resource found. Runs once at loop…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic