1,263 tagged agent, measured the same way as everything else here.
Browse within: agentic 86coding 68code 61vibe 60vibecoding 60chatbot 51agentic-workflow 47framework 46harness 45agent-framework 43gemini-cli 43agent-orchestration 42persona 42Multi-Agent 37
JCodesMore/youtube-for-ai-agents
Agent
Part of youtube
Watches a YouTube video and reports back with analysis — structured summary by default, or custom analysis via instructions.
viksant/vibe-coding-tools-content
Agent
AI agent for automated accessibility testing and WCAG compliance.
viksant/vibe-coding-tools-content
Agent
AI agent for optimizing web animations and ensuring smooth 60fps performance.
viksant/vibe-coding-tools-content
Agent
RESTful and GraphQL API design specialist.
Agent Codex
Use when building complete frontend applications across React, Vue, and Angular frameworks requiring multi-framework expertise and full-stack integration.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Evaluate expectations against an execution transcript and outputs.
Agent Claude Code
Use this agent when you need help with frontend build tools, configuration files, or infrastructure-related issues. Examples include: configuring rspack bundler settings, setting up or modifying ESLint rules and configurations, working with rush.json for monorepo management, troubleshooting build pipeline issues…
ncoevoet/claude-markdown-health-check
Agent Claude Code
Analyzes logs for anomalies. Use when investigating errors or unexpected behavior in application logs.
ncoevoet/claude-markdown-health-check
Agent Claude Code
Deploys the application to staging. Use when the user asks to push a build to the staging environment.
ncoevoet/claude-markdown-health-check
Agent Claude Code
Reviews diffs for correctness and security issues. Use after code edits to verify quality before a commit.
Agent
Deep reasoning agent. Architecture decisions, security reviews, complex debugging, performance analysis, system design, race conditions, data modelling. Use when getting it wrong has high cost.
Agent
Implementation agent. Writing code, generating boilerplate, scaffolding components, implementing features from specs, writing tests, standard bug fixes.
Agent
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
Agent
Part of forge
Classifies stuck/failed workers before retry to shape the debugger's approach.
Agent
Part of forge
Decomposes complex objectives into executable modules with dependency DAG.
Agent
Part of forge
Reviews completed module output for correctness, security, and architecture.
Agent
Part of hyperdroid
Use this agent to investigate Android app crashes, ANRs, or native crashes. Collects and analyzes logs, tombstones, ANR traces, and provides diagnosis. Triggers on "app crashed", "analyze crash", "debug ANR", "tombstone", "native crash".
armanzeroeight/fastagent-plugins
Agent
Strategic guidance for API design, versioning, authentication, and REST/GraphQL architecture. Use when designing APIs, choosing API patterns, or making architectural decisions for web services.
armanzeroeight/fastagent-plugins
Agent
Designs container strategies, optimizes Docker images, and implements security best practices. Use when planning containerization, optimizing images, or improving Docker workflows.
armanzeroeight/fastagent-plugins
Agent
Designs documentation strategy, organizes content structure, and ensures style consistency. Use when creating documentation, README files, API docs, or changelogs.
Agent
Part of autopunk-media-skills
Takes a dataset or data source and a research question and produces a complete data journalism package — story angles, data collection plan, cleaning instructions, statistical analysis, reader-friendly explanations, chart descriptions, and a published methodology statement — ready for an editor to review.
Agent
Part of autopunk-media-skills
Takes a newsroom description and produces a complete operational infrastructure package — AI usage policy, beat setup guides for every coverage area, an editorial calendar, longer-term content arcs, and a reusable ethics review template — everything a newsroom needs to run well from day one.
Agent Cursor
Run all CI checks locally and systematically fix any failures. Replicates GitHub workflow validations.
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: