84 entries

Claude Agents

Browse specialized Claude agents, expert role prompts, and reusable AI operator profiles with source links, usage notes, and review-ready metadata.

Browse & filter all Agents

Quick start

Open the full asset and review the role boundaries.
Copy the complete prompt into your Claude agent definition.
Test on a small task before using it in regular work.

Top Agents

Agent Skill QA Reviewer Agent

Review Agent Skills for SKILL.md quality, invocation control, helpfulness, safety, privacy, and adoption readiness.

Review firstSource-backedReview firstAdded 5d ago

Safety ✓ Privacy ✓

Agent SDK Production Architect Agent

Review and design production Claude Agent SDK deployments: surface choice, permissions, context/cost, sessions, observability, and hosting.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Agent Skills Enterprise Librarian Agent

Curate an org Agent Skills library: SKILL.md quality, descriptions, scope and precedence, tool restrictions, and invocation control.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Agent View Fleet Operator Agent

Operate a fleet of Claude Code background sessions via agent view: triage needs- input, working, and completed, and dispatch or stop.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

AI Workflow Privacy Compliance Review Agent

Review AI workflow submissions for privacy metadata, data flows, retention, tool authority, governance evidence, and compliance escalation.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Atlas Migration Safety Review Agent

Review Atlas schema migrations with lint evidence, analyzers, drift checks, CI reports, dev-database simulation, rollout risk, and safety gates.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Buf Protobuf API Review Agent

Review Protobuf API changes with Buf breaking checks, lint evidence, generated-code impact, BSR policy, compatibility risk, and rollout gates.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Changesets Release Cutover Agent

Review Changesets version PRs, changelogs, package bumps, pre-release mode, publish gates, and npm release cutovers.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Claude Code Auto Mode Policy Auditor Agent

Audit Claude Code auto mode policy: environment trust, allow/soft_deny/hard_deny rules, $defaults handling, and settings scope.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Claude Code Enterprise Rollout Agent

Plan an enterprise Claude Code rollout: server-managed settings, deny lists, managed MCP policy, fail-closed startup, and audit hooks.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Claude Code Routine Designer Agent

Design safe recurring Claude Code routines: scoped, idempotent skill-driven workflows with clear triggers, permissions, and reporting.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Claude Code Worktree Coordinator Agent

Coordinate parallel Claude Code sessions across git worktrees: isolation, base branch, file copying, subagent worktrees, and cleanup.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Claude Plugin Marketplace Reviewer Agent

Review a Claude Code plugin or marketplace before install: source trust, bundled components, context cost, version pinning, and managed scope.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Codecov Patch Coverage Planning Agent

Plan targeted regression tests from Codecov patch coverage, flags, components, PR comments, missing uploads, and changed-file risk.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Dependency Update Triage Agent

Triage dependency update PRs with release evidence, lockfile review, advisories, Scorecard signals, tests, and merge recommendations.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

GitHub Community Issue Triage Agent

Triage GitHub issue queues with labels, issue types, milestones, duplicates, reproducibility checks, maintainer routing, and community-safe replies.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Inspect AI Benchmark Rubric Agent

Design Inspect AI benchmarks with tasks, datasets, solvers, scorer rubrics, model matrices, eval logs, and reviewer calibration.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Jupytext Reproducible Notebook Agent

Review Jupytext paired notebooks for sync safety, reproducible execution, clean diffs, local data boundaries, and notebook collaboration readiness.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Live Incident Debugging Triage Agent

Triage live production outages with impact framing, evidence timelines, logs, traces, dashboards, rollback options, and safe recommendations.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

MCP Authorization Boundary Review Agent

Review MCP OAuth boundaries, resource metadata, token audiences, and passthrough risk.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

MCP Server Threat Modeling Agent

Threat-model an MCP server before connecting it to Claude Code: trust, tool authority, prompt injection, credentials, and mitigations.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

MCP Tool Result Budget Review Agent

Review MCP tool result sizes against Claude Code output token budgets and recommend pagination, filtering, and limit tuning.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

NanoClaw Container Isolation Review Agent

Review a NanoClaw deployment's container isolation: mounts, per-agent scope, vaulted credentials, channel permissions, and scheduled tasks.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

Open Source PR Security Review Agent

Review public OSS PRs for trust-boundary, CI, secrets, dependency, provenance, and code-security risks before maintainer approval.

Review firstSource-backedReview firstAdded 8d ago

Safety ✓ Privacy ✓

See all 84 Agents →

Frequently asked

What are Claude Agents?: Specialized Claude agents and expert roles.
How do I use Agents from HeyClaude?: Copy the full prompt into a Claude agent definition and adapt it to your workflow.
Are HeyClaude Agents reviewed before they are listed?: Each entry is metadata-reviewed for source, trust, and safety/privacy signals before it appears. HeyClaude does not scan for malware, so always review the linked source before installing anything that touches your filesystem, network, or credentials.

New Agents, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.