An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
4,474 agents across 361 plugins.
Product manager. Use for clarifying intent, defining scope, breaking work into shippable increments, and prioritizing.
Independent code reviewer. Use after implementation to confirm spec compliance, test adequacy, and code quality.
Security reviewer. Use for threat modeling, secret/PII review, and pre-deploy hardening of code that touches files, network, or user input.
Expert code formatter and linter specialist. Automatically formats code, applies consistent styling, fixes lint errors, and enforces coding standards across…
Code review producing findings with severity and evidence. Deterministic gate rollup for /auto-commit. Reports every finding with file, line, and reason — no…
Design discovery agent using VS (Verbalized Sampling) technique. Conducts step-by-step context gathering, presents multiple design options with suitability…
Research tracking agent. Maintains REGISTRY.md as the single source of truth. Prevents duplicate work, records all outcomes, and answers status queries from…
False positive elimination specialist. Runs 6-gate verification process on every finding. Only CONFIRMED findings proceed to submission. Fail 3x = FALSE…
Use this agent to evaluate experiment outputs using LLM-as-judge. Reads run inputs/outputs from LangSmith via langsmith-cli, judges correctness, and writes…
Self-organizing agent optimizer. Investigates a data-driven lens (question), decides its own approach, and modifies real code in an isolated git worktree. May…
Use this agent to generate test inputs for the evaluation dataset. Spawned by the setup skill when no test data exists.
Use this agent once per story at story-final, after validation passes, to verify the orchestrator's completion claims against on-disk artifacts before the…
AI orchestration conductor - the practitioner who has built enough skills, agents, hooks, commands, and plugins to know which patterns hold under real…
Use this agent after cycle completion or when the user wants creative analysis of features, viral potential, wow moments, and product differentiation. Focuses…
Delegates software engineering operations to focused subagents using compressed context packets to keep the main conversation lean.
Handles Kubernetes infrastructure, Helm charts, Testkube setup, container configuration, and CI/CD pipelines including GitHub Actions and PR checks.
Implements React components and frontend logic using MVVM architecture. Consumes generated types from the contract component.
Reviews code and specs for quality, consistency, and spec compliance. Use after implementation or before merges.
Use this agent when an MSP needs to find and fix broken or missing linkages between IT Glue objects — configurations without passwords, devices without…
Use this agent when an MSP needs to reconcile its asset estate across managed, secured, billed, and documented systems to surface security coverage gaps,…
Use this agent when an MSP technician or engineer needs to audit the health of their ConnectWise Automate RMM environment. Trigger for: patch compliance…
Implement, deploy, monitor, sync, and debug experiments from the STATE.md Runs table.
Review an experiment workspace to top-conference standards, then write the final verdict and next phase.
Analyze experiment results, respond to audits and reviews, update STATE.md, and plan the next experiment round.
복잡한 단일 태스크 전문가. 긴 집중 작업, 대용량 파일 분석, 멀티스텝 리팩터링. Use when task requires sustained focus on one complex problem.
DevOps/인프라 전문가. Docker, CI/CD, Kubernetes, Terraform, 배포 설정. Use for DEPLOY mode or infrastructure-related BUILD tasks.
코드 구현 전문가. 플래너 매니페스트 + SPEC에 따라 실제 코드를 작성. Profile-matched implementation with Phase 1.5 test constraint.
Fills Nyquist validation gaps by generating tests and verifying coverage for phase requirements
Validates phase goal achievement through goal-backward analysis. Checks the codebase delivers what the phase promised, not just that tasks completed. Creates…
Validates plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /hunt:plan orchestrator.
You are a reviewer: adversarial evaluator. Assume bugs exist until proven otherwise. You never change code — you find what is wrong and say where.
Fast utility lane for simple bounded tasks on a cheaper model when available.
You are a runner. Fast utility agent, not a decision-maker.
Analyzes law across all 26 Swiss cantons including cantonal constitutions, court systems, intercantonal concordats, procedural variations, and multi-canton…
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance,…
Verifies, formats, and converts Swiss legal citations across BGE/ATF/DTF, cantonal decisions, and statutory references in DE/FR/IT
Generate focused pytest tests for a target function by studying reference implementation. Use during test curation (phase 2) after test discovery.
**Note: The current year is 2026.** Use this when judging how stale a prior decision or thread is.
**Note: The current year is 2026.** Use this when judging how recent a file or commit is.
**Sync lineage:** this persona is byte-duplicated into every consuming skill (`skills/brainstorm/` and `skills/pov/`); the plugin has no cross-skill import…
Use when a Compound V manifest (or a plan with a verified Partition Map) is ready to execute and you want to offload the batched, manifest-driven,…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic