orchestrator
Routes QA tickets to the right agents in the right order — including environment setup and live browser validation
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
4,481 agents across 361 plugins.
Routes QA tickets to the right agents in the right order — including environment setup and live browser validation
Analyzes a multi-repo release diff to map cross-repo impact, AC compliance, and deployment risks
Maps code changes to existing tests — finds which tests to run, which may break, and where coverage gaps exist
Agent name must be lowercase-with-hyphens, under 64 characters, with no XML tags
Use this agent when you need to create, update, or edit artefacts — documents, guides, specifications, skills, or any content that should meet quality…
Use this agent when the user needs comprehensive research on a topic, question, or domain — gathering information, synthesising findings, and producing…
Reviews implementation against enriched roadmap chunk, architecture, and code quality standards. Applies perspective references loaded by orchestrator.…
Documentation and reference researcher. Fetches official docs, verifies technical information, and summarizes findings. READ-ONLY.
Code quality and spec compliance reviewer. Verifies implementation matches requirements and project standards. Read-only for source files; Bash restricted to…
Adversarial test engineer. Writes tests that are genuinely hard to pass. Thinks like an attacker hunting for weak implementations. Use before implementation to…
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.
Rug-pull, tokenomics, and centralization deep-dive. Owner-drain/mint/pause/blacklist backdoors, honeypots, depeg death-spirals, ve-bribe capture. Emits a 0-100…
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
The clarity pass is where good docs are made. Draft to get the ideas down, then edit ruthlessly for the reader. The goal: the shortest path to the reader's…
The contract is the deliverable. Express it as an **OpenAPI 3.1** document so it is human-readable *and* machine-checkable. This reference covers how to…
Debugging is the scientific method applied to a misbehaving system. You don't "stare at code until you see it"; you run controlled experiments that each rule…
Used by the deep-audit orchestrator. Do not invoke directly. Audits a codebase for security vulnerabilities — hardcoded secrets, injection risks, unsafe…
Update and optimize project documentation to reflect recent changes and improve AI agent usability. Use when user asks to "update documentation", "sync docs…
You are a specialist in Railway.app platform deployments, with deep expertise in multi-environment configurations, infrastructure provisioning, and…
Specialized agent for creating comprehensive form systems and managing application routing. Handles form validation, multi-step flows, file uploads, submission…
Specialized agent for creating and maintaining modern web applications with React, TypeScript, and Bootstrap integration. Focuses on responsive design,…
When Claude should delegate to this agent. Describe the end-to-end task it owns (e.g. "Run a full LLM security assessment of a feature, from threat model to…
Runs governance, risk & compliance work — framework gap-assessments (SOC 2 / ISO 27001 / PCI / HIPAA / GDPR / NIST), security risk assessment and the risk…
Senior AI security reviewer for an end-to-end assessment of an LLM / RAG / agentic feature — from threat model through OWASP LLM Top 10 and prompt-injection…
Reviews code for quality, security, and performance. Detects code smells, identifies vulnerabilities, and recommends maintainable patterns. Use when aiming to…
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents…
Analytics engineer for warehouse-backed dbt projects on BigQuery. Implements dimensional models, dbt transformations, warehouse-specific patterns, data quality…
Dispatched leaf for Google field data — returns real Search Console analytics (impressions, clicks, CTR, position), URL Inspection and sitemap status, CrUX/PSI…
Dispatched leaf for image SEO — fetches a page (or scans a local build) and scores every image on alt text, file size, modern formats, responsive srcset, lazy…
Dispatched leaf for local SEO — builds the normalized NAP-consistency matrix and computes Share of Local Voice + coverage / top-3 / avg-rank over a geo-grid,…
GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.
Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex…
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or…
Wave-план разработки. Использует reordering-agent для DAG. Каждая секция = feature в feature_list.json с явными affected_files, verification_command,…
ВНЕШНИЙ оценщик харнеса проекта. Fresh context, НЕ видит .harness/assessment.json. Читает только артефакты репо и выставляет 7-tuple оценку (1-5 балл per…
Поиск, клонирование и анализ GitHub-репозиториев по теме проекта. Минимум 3 репо, ≥1 клонирован для разбора. Извлекает архитектурные паттерны и anti-patterns.…
The `medium` rung of `cad-plan-checker`; `bin/route.mjs` picks it, not the user.
The `xhigh` rung of `cad-plan-checker`; `bin/route.mjs` picks it, not the user.
The `high` rung of `cad-planner` (phase plan authoring); `bin/route.mjs` picks it, not the user.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic