Specialized sub-agents for focused tasks like review and research.
Ranked by GitHub stars. Search to find fast, or page through the full list.
Python SDK for Claude Code
Use proactively when attacker-controlled input, trust boundaries, authorization decisions, sensitive sinks, secrets, or security-impacting changes require exploitability analysis. Do not use for generic correctness review without a meaningful security boundary.
Use proactively when a decision depends on current official documentation, release notes, schemas, supported models, APIs, or version-specific behavior. Do not use when the primary work is tracing local code or implementing a change.
Migration and upgrade review
Use after a completed change when acceptance criteria must be exercised through the real user-facing, CLI, service, browser, filesystem, or integration boundary. Do not use to implement fixes or when the change is incomplete.
Use proactively when a failure must be reproduced, isolated, and causally explained before a fix is written. Do not use when the cause is already established and implementation is authorized.
General bug investigation and root cause analysis
Use when requirements, an approved design, or a root cause are clear and one scoped, complete implementation is authorized. Do not use for unresolved exploration, product decisions, diagnosis-only work, or review-only requests.
Use proactively when a task needs local repository structure, entry points, ownership, data flow, or change-surface mapping before a decision. Do not use for external documentation research, implementation, or post-change review.
Analyze brownfield codebase and create initial continuity ledger
Use when established requirements and evidence leave multiple viable designs or cross-component boundaries that need explicit trade-offs before implementation. Do not use for a small specified fix or while the root cause is still unknown.
Session analysis, precedent lookup, and learning extraction
Multi-agent coordination for complex patterns
System architecture specialist for design decisions, ADR creation, scalability assessment, and technology selection
Analyze Claude Code sessions using Braintrust logs
Performance profiling, race conditions, memory issues
Use this agent to autonomously build, test, and deploy complete applications from plain-English descriptions. Runs a 9-phase pipeline across 4 stacks with enterprise-grade safety hooks.
Lightweight fixes and quick tweaks
Codebase exploration and pattern finding
Performance analyzer. Measures and evaluates Core Web Vitals and page load performance.
Refactoring planning AND migration planning
Extract perception changes from session thinking blocks and store as learnings
GitHub API data collector and archival specialist for repository SEO telemetry.
External research - web, docs, APIs with optional LLM
Unit and integration test execution and validation
Global finding verification agent. Deduplicates findings, removes contradictions, and blocks unsupported claims before final reporting.
Analyze Claude Code sessions using Braintrust logs
Security vulnerability analysis and testing
Content quality reviewer. Evaluates E-E-A-T signals, readability, content depth, AI citation readiness, and thin content detection.
Documentation, handoffs, session summaries, and ledger management
Document the codebase comprehensively
Technical SEO specialist. Analyzes crawlability, indexability, security, URL structure, mobile optimization, Core Web Vitals, and JavaScript rendering.
Create implementation plans using research, best practices, and codebase analysis
Build Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestration
Sitemap architect. Validates XML sitemaps, generates new ones with industry templates, and enforces quality gates for location pages.
External repository research and analysis
Validate plan tech choices against current best practices and past precedent
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
Query the artifact index for precedent and guidance
Review implementation by comparing plan (intent) vs Braintrust session (reality) vs git diff (changes)
GitHub search benchmark specialist. Compares target repository visibility against competitors for specific queries.
End-to-end and acceptance test execution
Release prep, version bumps, changelog generation
Feature and implementation code review
Investigate issues using codebase exploration, logs, and code search
Implementation and refactoring agent using TDD workflow
Integration and API review
Refactoring and code transformation review