Awesome Claude

Curated Claude workflow infrastructure.

HeyClaude is a file-backed, human-reviewed directory for Claude agents, MCP servers, skills, hooks, commands, tools, prompts, rules, guides, templates, and statuslines.

1339+ file-backed entries stay useful as both an awesome-list catalog and a machine-readable registry for builders.

Registry snapshot

1339entries 10sections humanmerge gate

sourcefirst UGC no ZIPcommunity uploads APIMCP + feeds

Listed on Gittensor Unofficial community project. Contribution eligibility and rewards follow Gittensor's current rules.

Explore The Directory

🤖 Agents 106 Specialized Claude agents and expert roles.

🔌 MCP Servers 467 Model Context Protocol servers and integrations.

🧰 Tools 183 Apps, developer tools, services, and products for Claude-native builders.

🧠 Skills 175 Source-backed skill packs and reusable capabilities.

📏 Rules 83 Prompt guardrails, project rules, and operating constraints.

⌨️ Commands 43 Slash commands and reusable command prompts.

🪝 Hooks 87 Claude Code hook configs and automation helpers.

📚 Guides 128 Long-form guides and practical walkthroughs.

📦 Collections 25 Curated bundles of related assets.

📟 Statuslines 42 Statusline scripts and workflow telemetry.

Choose Your Path

🔎 Discover Search the curated directory and jump from README entries into richer detail pages. Browse resources

🧾 Contribute Submit free, source-backed Claude resources through PR-first private-gate review. Submit content

⚙️ Integrate Use the registry as JSON, RSS, Atom, LLM text, Raycast data, or a read-only MCP server. API docs · MCP package

💼 List Claim an entry, post a Claude role, or route commercial listings through the website. Claim/update · Jobs

Contributor rules, docs, and local validation

Contributor Guardrails

Free Claude resources use PR-first intake by default. Fully valid, source-backed, content-only submissions may be merged automatically after content validation, Superagent, and private maintainer-agent review pass. Tool, app, service promotion, listing claims, and jobs use the website lead forms instead of GitHub content submissions.

README.md, apps/web/public/data/**, apps/web/src/generated/**, apps/web/src/routeTree.gen.ts, and apps/web/public/downloads/** are generated or maintainer-owned outputs. Direct contributors should not edit them in content PRs.

Community submissions may link to source repositories, documentation, install commands, or full copyable content. Community-submitted ZIP/MCPB packages are not published as HeyClaude-hosted downloads. Maintainer-built convenience packages use checksums and package trust metadata after review.

Project Docs

| Area | Links | | ------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Community | [Contributing](CONTRIBUTING.md), [Code of conduct](CODEOFCONDUCT.md), [Security policy](SECURITY.md), [License](LICENSE) | | Content model | [Registry schema](content/SCHEMA.md), [content examples](examples/content/README.md), submit flow | | Packages | [Registry package](packages/registry), [read-only MCP server](packages/mcp), [Raycast extension](integrations/raycast) | | Operations | [Submission gate ops](docs/submission-queue-ops.md), [package trust model](docs/package-security-policy.md), [API security contract](docs/api-security-contract.md), [deployment](apps/web/DEPLOYMENT.md) | | Public policy | Legal/disclaimer, claim/update, advertise |

Local Validation

1. Direct content PRs should add or update exactly one content//.mdx file.
2. For direct content PRs, run pnpm validate:content:strict and do not commit generated output.
3. For platform, package, API, MCP, Raycast, or maintainer artifact work, run pnpm --filter web run prebuild, pnpm validate:packages, pnpm scan:packages, pnpm validate:clean, pnpm audit:content, pnpm validate:raycast-feed, pnpm test:mcp, pnpm test:registry-artifacts, pnpm test:seo-jsonld, pnpm test:commercial-intake, MCP_ENDPOINT_URL=http://localhost:3000/api/mcp pnpm --filter @heyclaude/mcp validate:endpoint, and pnpm build as relevant.
4. Generated registry, route, package-download, and README artifacts are build or maintainer automation outputs, not normal content PR diffs.

---

Content Catalog

🤖 AI Agents (106)

• Agent Observability SRE Agent - Community reusable agent prompt for Claude Code analytics and agent platform on-call using official analytics documentation: usage signals, session failure triage, MCP latency patterns, and SRE runbooks for agent hosting teams.
• Agent SDK Production Architect Agent - An agent prompt for taking Claude Agent SDK apps to production: choosing the SDK vs CLI vs Managed Agents surface, least-privilege tool and permission scoping, session persistence, cost tracking, OpenTelemetry, and isolated hosting.
• Agent Skill QA Reviewer Agent - Source-backed Claude Code subagent prompt for reviewing Agent Skills before adoption or publication, checking SKILL.md scope, descriptions, invocation control, supporting files, tool permissions, helpfulness, safety, and privacy risks against official Claude Code skills guidance.
• Agent Skills Enterprise Librarian Agent - An agent prompt for curating an organization's Agent Skills: reviewing each SKILL.md name and description, scope (personal, project, or plugin) and precedence, per-skill allowed-tools, and whether Claude or the user invokes it.
• Agent Skills Framework Engineer - Claude Code Agents - An agent persona for authoring Claude Agent Skills: structured SKILL.md files with name and description frontmatter, progressively disclosed instructions, and bundled scripts the model loads on demand.
• Agent View Fleet Operator Agent - A reusable agent prompt for running a fleet of Claude Code background sessions from agent view (opened with the agents command). It triages which sessions need input, which are still working, and which have finished, then decides what to dispatch next, which to answer, and which to stop.
• AI Agent Cost Governance Analyst Agent - Community reusable agent prompt for Claude Code and agent spend governance using official costs documentation: budgets, model tier policy, caching awareness, anomaly triage, and team reporting workflows.
• AI Code Review Security Agent - Agents - AI-powered code review specialist focusing on security vulnerabilities, OWASP Top 10, static analysis, secrets detection, and automated security best practices enforcement
• DevOps Engineer Agent - CI/CD, Terraform, Kubernetes - A Claude Code DevOps engineer persona grounded in GitHub Actions, Terraform, Docker, and Kubernetes. It writes and reviews CI/CD workflows, IaC, and deployment manifests using real tooling and documented commands.
• AI Workflow Privacy Compliance Review Agent - Source-backed agent for reviewing AI workflow submissions before publication with data-flow mapping, privacy metadata, governance evidence, MCP/tool authority checks, retention disclosure, and compliance escalation gates.
• Allways Agent Quickstart for Claude - Source-backed Claude agent prompt for using the Allways agent quickstart, live dashboards, API docs, and open source repo in a read-only-first workflow.
• Angular Repository Contributor Agent for Claude - Source-backed Claude agent prompt for contributing to the official angular/angular repository using its AGENTS.md guidance for pnpm, Bazel test targets, coding standards, commit guidelines, zoneless tests, async stability, and PR handling.
• Ansible Repository Contributor Agent for Claude - Source-backed Claude agent prompt for contributing to the official ansible/ansible repository using its AGENTS.md guidance for licensing, ansible-test workflows, Docker container selection, changelog fragments, CI triage, module documentation, and devel-branch PRs.
• API Builder Agent for Claude - Specialized agent for designing, building, and optimizing RESTful APIs and GraphQL services with modern best practices
• Astro Repository Contributor Agent for Claude - Source-backed Claude agent prompt for contributing to the official Astro monorepo using its AGENTS.md guidance, pnpm workspace commands, package-local testing, bgproc dev server management, agent-browser UI checks, and Astro docs sources.
• Atlas Migration Safety Review Agent - Source-backed agent for reviewing Atlas database schema migrations with migration lint, analyzers, drift detection, CI/CD evidence, dev-database simulation, rollout risk, rollback planning, and production safety gates.
• Autogen Conversation Agent Builder - Agents - A Claude agent persona for building multi-agent apps with Microsoft AutoGen v0.4: the asynchronous agent runtime, message-passing between agents, the AgentChat API, cross-language (Python and .NET) support, and tool use.
• Backend Architect Agent - Agents - Expert backend architect specializing in scalable system design, microservices, API development, and infrastructure planning
• Bedrock Claude Code Platform Agent - Community reusable agent prompt for operating Claude Code on Amazon Bedrock using official setup docs: IAM credential chains, regional model IDs, inference profiles, enterprise network config, quota errors, and Bedrock-specific troubleshooting steps.
• Buf Protobuf API Review Agent - Source-backed agent for reviewing typed Protobuf and gRPC API contract changes with Buf breaking-change evidence, lint results, buf.yaml policy, BSR schema checks, generated-code impact, consumer compatibility, and rollout decisions.
• Changesets Release Cutover Agent - Source-backed agent for managing Changesets release cutovers, version PRs, changelog evidence, package bump decisions, pre-release mode, publish gates, and npm registry safety.
• Claude Code Auto Mode Policy Auditor Agent - A reusable agent prompt that reviews a Claude Code auto mode setup: whether autoMode.environment trusts the right repos, buckets, and domains, how the allow, softdeny, and hard_deny tiers resolve, and whether $defaults is kept across settings scopes.
• Claude Code Desktop Operations Agent - Community reusable agent prompt for operating Claude Code Desktop using official desktop docs: parallel sessions, agent view, notifications, background jobs, and desktop-specific troubleshooting workflows.
• Claude Code Enterprise Rollout Agent - An agent prompt for planning an enterprise Claude Code rollout via server-managed settings: permission deny lists, disableBypassPermissionsMode, allowManagedPermissionRulesOnly, managed MCP allow/deny, and forceRemoteSettingsRefresh fail-closed startup.
• Claude Code Routine Designer Agent - Source-backed agent that designs safe recurring Claude Code routines, turning a repeated task into a well-scoped, idempotent skill-driven workflow with clear triggers, permissions, and reporting, grounded in the official Claude Code skills docs.
• Claude Code Security Guidance Remediator Agent - Source-backed agent that reviews active Claude Code sessions and configuration for security gaps, cross-references the official security guidance, and produces a ranked remediation plan covering permissions, MCP trust, prompt injection, credential handling, and hook safety.
• Claude Code Worktree Coordinator Agent - Source-backed agent that coordinates parallel Claude Code sessions across git worktrees, planning isolation, base-branch choice, gitignored-file copying, subagent worktrees, and cleanup so parallel edits do not collide, grounded in the official Claude Code worktrees docs.
• Claude Haiku 45 Speed Optimizer Agent - Agents - An agent pattern for routing rapid-iteration work to Claude Haiku 4.5 — more than twice Sonnet's speed at one-third the cost ($1/$5 per million tokens) — while keeping about 90% of Sonnet 4.5's agentic-coding quality.
• Claude MCP Skills Integration Agent - Claude Code Agents - MCP Skills integration specialist for remote server configuration, tool permissions, multi-MCP orchestration, and Claude Desktop ecosystem workflows.
• CLAUDE.md Knowledge Manager Agent - Claude Code Agents - CLAUDE.md specialist for creating, maintaining, and optimiz

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: JSONbored
• Source: JSONbored/awesome-claude
• License: MIT
• Homepage: https://heyclau.de

Install and usage instructions live in the source repository linked above.