stacklok/toolhive
ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit stacklok/toolhive/.claude ./rig-toolhive # 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.
$ npx degit stacklok/toolhive/.claude/skills/add-rule .claude/skills/add-rule $ npx degit stacklok/toolhive/.claude/skills/check-contribution .claude/skills/check-contribution $ npx degit stacklok/toolhive/.claude/skills/code-review-assist .claude/skills/code-review-assist $ npx degit stacklok/toolhive/.claude/skills/deflake .claude/skills/deflake $ npx degit stacklok/toolhive/.claude/skills/deploy-otel .claude/skills/deploy-otel $ npx degit stacklok/toolhive/.claude/skills/deploying-vmcp-locally .claude/skills/deploying-vmcp-locally $ npx degit stacklok/toolhive/.claude/skills/doc-review .claude/skills/doc-review $ npx degit stacklok/toolhive/.claude/skills/implement-story .claude/skills/implement-story $ npx degit stacklok/toolhive/.claude/skills/release-notes .claude/skills/release-notes $ npx degit stacklok/toolhive/.claude/skills/split-pr .claude/skills/split-pr $ npx degit stacklok/toolhive/.claude/skills/toolhive-release .claude/skills/toolhive-release $ npx degit stacklok/toolhive/.claude/skills/vmcp-review .claude/skills/vmcp-review $ npx degit stacklok/toolhive/skills/toolhive-cli-user .claude/skills/toolhive-cli-user
$ curl -fsSL --create-dirs -o .claude/agents/bug-triage.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/bug-triage.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/documentation-writer.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/documentation-writer.md $ curl -fsSL --create-dirs -o .claude/agents/golang-code-writer.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/golang-code-writer.md $ curl -fsSL --create-dirs -o .claude/agents/kubernetes-expert.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/kubernetes-expert.md $ curl -fsSL --create-dirs -o .claude/agents/mcp-protocol-expert.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/mcp-protocol-expert.md $ curl -fsSL --create-dirs -o .claude/agents/oauth-expert.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/oauth-expert.md $ curl -fsSL --create-dirs -o .claude/agents/security-advisor.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/security-advisor.md $ curl -fsSL --create-dirs -o .claude/agents/site-reliability-engineer.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/site-reliability-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-lead-orchestrator.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/tech-lead-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/toolhive-expert.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/toolhive-expert.md $ curl -fsSL --create-dirs -o .claude/agents/unit-test-writer.md https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/unit-test-writer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (13)
add-rulecheck-contributioncode-review-assistdeflakedeploy-oteldeploying-vmcp-locallydoc-reviewimplement-storyrelease-notessplit-prtoolhive-releasevmcp-reviewtoolhive-cli-user
Subagents (12)
| bug-triage model: inherit | Triages GitHub issues by investigating whether they've been resolved in the codebase, recommending closures, and helping craft polite closure messages. Use when doing bug triage sessions or cleaning u |
| code-reviewer model: inherit | Reviews code for ToolHive best practices, security patterns, Go conventions, and architectural consistency |
| documentation-writer model: inherit | Maintains consistent documentation, updates CLI docs, and ensures documentation matches code behavior |
| golang-code-writer model: inherit | Write, generate, or create new Go code — functions, structs, interfaces, methods, or complete packages |
| kubernetes-expert model: inherit | Specialized in Kubernetes operator patterns, CRDs, controllers, and cloud-native architecture for ToolHive |
| mcp-protocol-expert model: inherit | PROACTIVELY use for MCP protocol questions, transport implementations, JSON-RPC debugging, and spec compliance verification. Expert in the current stable MCP specification. |
| oauth-expert model: inherit | Specialized in OAuth 2.0, OIDC, token exchange, and authentication flows for ToolHive |
| security-advisor model: inherit | Security guidance for code reviews, architecture decisions, auth implementations, and threat modeling |
| site-reliability-engineer model: inherit | Observability and monitoring guidance — OpenTelemetry instrumentation, metrics, tracing, and monitoring stack configuration |
| tech-lead-orchestrator model: inherit | Architectural oversight, task breakdown, and delegation for complex multi-component features |
| toolhive-expert model: inherit | Codebase knowledge, navigation, and implementation guidance — use for understanding existing code and patterns |
| unit-test-writer model: inherit | Write comprehensive unit tests for Go code — functions, methods, or components that need thorough test coverage |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Edit|Write | cd "$CLAUDE_PROJECT_DIR" && changed_file="$CLAUDE_TOOL_ARG_file_path"; if [ -n "$changed_file" ] && echo "$changed_file" | grep -q '\.go$'; then task lint-fix 2>/dev/null; task license-fix 2>/dev/null; fi; exit 0 |
Permissions
deny (0)
—
ask (0)
—
allow (29)
Bash(go test:*)
Bash(task test)
Bash(task lint)
Bash(task lint-fix)
Bash(task license-fix)
Bash(golangci-lint run:*)
Bash(go doc:*)
WebFetch(domain:modelcontextprotocol.io)
Bash(pre-commit:*)
Bash(pre-commit run:*)
Bash(pre-commit install:*)
Bash(pre-commit autoupdate:*)
Bash(helm-docs:*)
Bash(codespell:*)
Bash(task operator-install-crds)
Bash(task operator-uninstall-crds)
Bash(task operator-deploy-latest)
Bash(task operator-deploy-local)
Bash(task operator-undeploy)
Bash(task operator-generate)
Bash(task operator-manifests)
Bash(task operator-test)
Bash(task operator-e2e-test)
Bash(task crdref-install)
Bash(task crdref-gen)
Bash(helm template:*)
Bash(git log:*)
Bash(ct lint:*)
Bash(helm-docs --dry-run)
Similar rigs
stacklok/toolhive-registry-server
Discover, govern and control access to MCP servers and agent skills across your organization
Orchestrator 3.3k tok ·
nylas/cli
Nylas CLI is a unified command-line tool for Nylas API authentication, email management (GPG signing/encryption), calendar, contacts, webhooks, timezone utilities, and OTP extraction
Fort Knox 1.8k tok ·
sbstnppl/multi-agent-project-template
A comprehensive template for Python projects with Claude Code integration, featuring a professional multi-agent workflow system for development, testing, documentation, and deployment.
Orchestrator 4.3k tok ·
UtsavBalar1231/claude-code-configs
—
Pragmatist 5.0k tok ·