Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Use this agent when you want a comprehensive code review of changes in the current branch compared to main. This includes reviewing for bugs, optimization opportunities, code style issues, potential mistakes, and adherence to project conventions. The agent should be invoked after completing a feature branch or before…
Agent Claude Code
Use this agent when backend API endpoints are added, modified, or removed, or when the Flow structure changes and the OpenAPI specification files need to be updated. This includes changes to route handlers in windmill-api, modifications to request/response schemas, changes to authentication requirements, or updates to…
Agent
You are a read-only verification subagent spawned to check a design deliverable the main agent just built or edited. Your only job: load that deliverable, verify it, and report a single verdict — done or needswork — back to the main agent. You must not modify, create, or delete any file, edit the source, build, or…
Agent
You are a read-only capability probe spawned before a design task tries to read or inspect screenshots. Your only job is to determine whether this Claude Code session's current model/provider can accept image input.
Agent
A set of shared instructions for agents working with a task board, including rules for status updates, progress reports, and workflow history.
Agent Claude Code
Adversarially verifies one landed packet against its requirement; read-only.
Agent Claude Code
Implements exactly one work packet — minimal diff, targeted checks, own-paths-only commits.
Agent Claude Code
Resolves contested design questions against the specs; decision + rationale, never code.
Agent
Customization assistant for al-folio v1.x starter and plugin ecosystem.
Agent
Documentation specialist for al-folio v1.x.
Agent Claude Code
Use this agent when you want to analyze and improve agent performance after any agent invocation. This agent should be used proactively after observing agent interactions to provide coaching feedback on tool usage, MCP integration, and overall effectiveness. Examples: Context: User has just used a code-review agent to…
Agent Claude Code
Comprehensive Buildkite CI/CD expert for status checks, build introspection, and failure diagnosis. Handles everything from simple status queries to deep error analysis. Examples: Context: User wants to know the current build status. user: 'What's the status of my PR in Buildkite?' assistant: 'I'll use the…
Agent Claude Code
Expert agent for updating GitHub PRs through optimized AI workflow. Handles thesis collection, diff analysis, and PR body generation with human-AI collaboration approach. Examples: Context: User wants to update their PR with latest changes. user: '/aiupdatepr' assistant: 'I'll use the pr-update-expert agent to update…
Agent
Part of claude-seo
Backlink profile analyst using free and paid sources. Fetches data from Moz API, Bing Webmaster Tools, Common Crawl web graphs, and verification crawler. Merges multi-source data with confidence-weighted scoring.
Agent
Part of claude-seo
E-commerce SEO analyst. Validates product schema, analyzes Google Shopping and Amazon marketplace visibility, identifies pricing gaps, and recommends product page optimizations. Spawned when e-commerce site detected during audits.
Agent
Part of claude-seo
Performance analyzer. Measures and evaluates Core Web Vitals and page load performance.
Agent Claude Code
You are the architecture planning agent for Spree Commerce.
wanshuiyin/Auto-claude-code-research-in-sleep
Agent
ARIS reviewer agent using Anthropic Claude Sonnet 4.5 for cross-family review.
wanshuiyin/Auto-claude-code-research-in-sleep
Agent
ARIS reviewer agent using OpenAI GPT-5.4 for cross-family review.
Agent Claude Code
Use when a Maestro test-android run has failed and a structured per-flow diagnosis is needed without bloating the caller's context. Accepts either a local artifact directory or a GitHub Actions run/job URL. Reads commands JSON, screenshots, and maestro.log; classifies each newly-failing passing/ flow; identifies…
Agent Claude Code
Researches one Pipecat service unit (provider × type) for new provider models and API affordances, writes the dated report, and leaves a committed branch for a draft PR when the change is clear-cut. Spawned by the /provider-research skill with a JSON payload; not for ad-hoc use.
Agent
Part of openmetadata-skills
Verify that PR review comments were substantively addressed in code, not just checkbox-resolved. Used as a sub-agent by connector-review or standalone.
Agent
Part of openmetadata-skills
Review TypeScript/React code changes against OpenMetadata frontend patterns and CI checkstyle rules — ESLint, Prettier, import organization, license headers, i18n sync, Playwright lint, and component architecture.
Agent
Part of openmetadata-skills
Review Java code changes against OpenMetadata backend patterns and Kafka-grade quality standards — method size limits, IntelliJ-level inspections, immutability, granular error handling, and human-readable code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: