AgentWorkforce/relay
Infrastructure for coding agents
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add shared-sessions -- agent-relay mcp --sessions-only $ npx degit AgentWorkforce/relay/.claude ./rig-relay # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add shared-sessions -- agent-relay mcp --sessions-only $ npx degit AgentWorkforce/relay/.agents/skills/choosing-swarm-patterns .claude/skills/choosing-swarm-patterns $ npx degit AgentWorkforce/relay/.agents/skills/creating-agent-skills-skill .claude/skills/creating-agent-skills-skill $ npx degit AgentWorkforce/relay/.agents/skills/emil-design-eng .claude/skills/emil-design-eng $ npx degit AgentWorkforce/relay/.agents/skills/orchestrating-agent-relay .claude/skills/orchestrating-agent-relay $ npx degit AgentWorkforce/relay/.agents/skills/relay-80-100-workflow .claude/skills/relay-80-100-workflow $ npx degit AgentWorkforce/relay/.agents/skills/review-animations .claude/skills/review-animations $ npx degit AgentWorkforce/relay/.agents/skills/review-fix-signoff-loop .claude/skills/review-fix-signoff-loop $ npx degit AgentWorkforce/relay/.agents/skills/setting-up-relayfile .claude/skills/setting-up-relayfile $ npx degit AgentWorkforce/relay/.agents/skills/using-agent-relay .claude/skills/using-agent-relay $ npx degit AgentWorkforce/relay/.agents/skills/writing-relayflows .claude/skills/writing-relayflows $ npx degit AgentWorkforce/relay/.claude/skills/browser-testing-with-screenshots .claude/skills/browser-testing-with-screenshots $ npx degit AgentWorkforce/relay/.claude/skills/creating-claude-agents-skill .claude/skills/creating-claude-agents-skill $ npx degit AgentWorkforce/relay/.claude/skills/creating-claude-hooks-skill .claude/skills/creating-claude-hooks-skill $ npx degit AgentWorkforce/relay/.claude/skills/creating-claude-rules-skill .claude/skills/creating-claude-rules-skill $ npx degit AgentWorkforce/relay/.claude/skills/creating-skills-skill .claude/skills/creating-skills-skill $ npx degit AgentWorkforce/relay/.claude/skills/debugging-websocket-issues .claude/skills/debugging-websocket-issues $ npx degit AgentWorkforce/relay/.claude/skills/deploying-to-staging-environment .claude/skills/deploying-to-staging-environment $ npx degit AgentWorkforce/relay/.claude/skills/frontend-design .claude/skills/frontend-design $ npx degit AgentWorkforce/relay/.claude/skills/github-oauth-nango-integration .claude/skills/github-oauth-nango-integration $ npx degit AgentWorkforce/relay/.claude/skills/implementing-command-palettes .claude/skills/implementing-command-palettes $ npx degit AgentWorkforce/relay/.claude/skills/prpm-json-best-practices-skill .claude/skills/prpm-json-best-practices-skill $ npx degit AgentWorkforce/relay/plugins/shared-sessions/skills/search-shared-sessions .claude/skills/search-shared-sessions
$ curl -fsSL --create-dirs -o .claude/agents/accessibility.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/accessibility.md $ curl -fsSL --create-dirs -o .claude/agents/api-designer.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/api-designer.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/backend.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/backend.md $ curl -fsSL --create-dirs -o .claude/agents/cli.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/cli.md $ curl -fsSL --create-dirs -o .claude/agents/data.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/data.md $ curl -fsSL --create-dirs -o .claude/agents/database.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/database.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/deployer.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/deployer.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/devops.md $ curl -fsSL --create-dirs -o .claude/agents/documentor.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/documentor.md $ curl -fsSL --create-dirs -o .claude/agents/explainer.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/explainer.md $ curl -fsSL --create-dirs -o .claude/agents/fixer.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/fixer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/frontend.md $ curl -fsSL --create-dirs -o .claude/agents/infrastructure.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/infrastructure.md $ curl -fsSL --create-dirs -o .claude/agents/integrator.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/integrator.md $ curl -fsSL --create-dirs -o .claude/agents/lead.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/lead.md $ curl -fsSL --create-dirs -o .claude/agents/migrator.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/migrator.md $ curl -fsSL --create-dirs -o .claude/agents/mobile.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/mobile.md $ curl -fsSL --create-dirs -o .claude/agents/monitor.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/monitor.md $ curl -fsSL --create-dirs -o .claude/agents/performance.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/performance.md $ curl -fsSL --create-dirs -o .claude/agents/prototyper.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/prototyper.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/qa.md $ curl -fsSL --create-dirs -o .claude/agents/refactorer.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/refactorer.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/planner-strategy.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/roles/planner-strategy.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer-criteria.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/roles/reviewer-criteria.md $ curl -fsSL --create-dirs -o .claude/agents/worker-focus.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/roles/worker-focus.md $ curl -fsSL --create-dirs -o .claude/agents/security.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/security.md $ curl -fsSL --create-dirs -o .claude/agents/shadow-active.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/shadow-active.md $ curl -fsSL --create-dirs -o .claude/agents/shadow-auditor.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/shadow-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/shadow-reviewer.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/shadow-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/sysadmin.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/sysadmin.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/tester.md $ curl -fsSL --create-dirs -o .claude/agents/validator.md https://raw.githubusercontent.com/AgentWorkforce/relay/main/.claude/agents/validator.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| agent-relay · "shared-sessions" | binary | 2.5k |
Skills (22)
choosing-swarm-patternscreating-agent-skillsemil-design-engorchestrating-agent-relayrelay-80-100-workflowreview-animationsreview-fix-signoff-loopsetting-up-relayfileusing-agent-relaywriting-relayflowsbrowser-testing-with-screenshotscreating-claude-agentscreating-claude-hookscreating-claude-rulescreating-skillsdebugging-websocket-issuesdeploying-to-staging-environmentfrontend-designgithub-oauth-nango-integrationimplementing-command-palettesprpm-json-best-practicessearch-shared-sessions
Subagents (36)
| accessibility | A11y auditing, WCAG compliance, and inclusive design review. Ensures digital content is usable by everyone. |
| api-designer | REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones. |
| architect | System design and architecture decisions. Technical planning, tradeoff analysis, and design documentation. |
| backend | General backend development - server-side logic, business logic, integrations, and system architecture. Use for implementing APIs, services, middleware, and backend features. |
| cli | Use for CLI tool development, command-line interfaces, terminal utilities, and shell scripting. |
| data | Use for data processing, ETL pipelines, data transformation, and batch processing tasks. |
| database | Database design, queries, migrations, and data modeling. Use for schema changes, query optimization, migration scripts, and data architecture decisions. |
| debugger | Bug investigation and root cause analysis. Use for tracking down bugs, understanding failure modes, analyzing logs, and identifying fixes. |
| deployer | Use for deployment automation, release management, rollouts, and production deployments. |
| devops | CI/CD pipelines, build automation, and pipeline optimization. Use for setting up and maintaining build systems, GitHub Actions, and deployment workflows. |
| documentor | Technical documentation, API docs, READMEs. Creates clear, comprehensive documentation for codebases. |
| explainer | Code explanation and architecture walkthroughs. Helps developers understand complex code and systems. |
| fixer | Use for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs. |
| frontend | Creates distinctive, production-grade frontend interfaces. Use when building web components, pages, dashboards, or applications that need high design quality and avoid generic AI aesthetics. |
| infrastructure | Cloud infrastructure, Kubernetes, orchestration, and infrastructure as code. Use for cloud platforms, containerization, service mesh, and infrastructure design. |
| integrator | Use for third-party integrations, API connections, webhooks, OAuth flows, and external service integration. |
| lead model: haiku | Use when coordinating multi-agent teams. Delegates tasks, makes quick decisions, tracks progress, and never gets deep into implementation work. |
| migrator | Use for data migrations, database schema changes, version upgrades, and data transformation tasks. |
| mobile | Use for mobile app development, React Native, Flutter, iOS, Android, and cross-platform mobile tasks. |
| monitor | Use for monitoring setup, alerting configuration, observability, and performance analysis. |
| performance | Performance optimization and profiling. Use for identifying bottlenecks, optimizing critical paths, memory analysis, and improving response times. |
| prototyper | Use for rapid prototyping, MVPs, proof-of-concepts, and quick experimental implementations. |
| qa | Quality assurance, testing protocols, and defect management. Creates test plans and validates feature completeness. |
| refactorer | Code refactoring and tech debt reduction. Use for improving code structure, extracting abstractions, reducing duplication, and improving maintainability without changing behavior. |
| researcher | Research tasks and codebase exploration. Investigates questions, finds patterns, and gathers information. |
| reviewer | Code review for quality, security, and best practices. Direct invocation for reviewing PRs, commits, or specific files. |
| planner-strategy | — |
| reviewer-criteria | — |
| worker-focus | — |
| security | Security auditing, vulnerability assessment, and secure coding review. Identifies OWASP risks and recommends mitigations. |
| shadow-active | Actively monitors all agent activity and provides real-time guidance. Assign as a shadow for high-stakes or learning scenarios. |
| shadow-auditor | Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review. |
| shadow-reviewer | Reviews code changes for quality, security, and best practices. Assign as a shadow to monitor another agent's code output. |
| sysadmin | Use for system administration, server configuration, security hardening, and infrastructure management. |
| tester | Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases. |
| validator | Input validation, data integrity, and schema enforcement. Ensures data quality at system boundaries. |
Similar rigs
agentsea/flashbacker
Claude Code state management with session continuity and AI personas, subagents and agent discussion
Orchestrator 5.1k tok ·
Markuysa/vibe-coding-template
Claude Code project template: five agent roles with tool-level permission boundaries, four workflow commands, and a permission baseline that keeps secrets and build noise out of context. Built on native worktrees and subagents — no third-pa
Fort Knox 1.2k tok ·
andrewchoi-hds/claude-code-config
Claude Code custom agents and slash commands for optimized development workflow
Orchestrator 2.2k tok ·
navox-labs/agents
15-agent AI engineering team for Claude Code. Full sprint cycle: Think, Plan, Build, Review, Test, Ship, Reflect. Zero dependencies.
Orchestrator 5.1k tok ·