specmatic/specmatic-mcp-sample-with-spec-kit
This project demonstrates contract-first development using a spec-kit approach where OpenAPI specifications evolve organically through feature development. Each feature analyzes existing contracts for reuse before extending the API, using S
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 specmatic/specmatic-mcp-sample-with-spec-kit/.claude ./rig-specmatic-mcp-sample-with-spec-kit # 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.
$ curl -fsSL --create-dirs -o .claude/agents/api-mock-manager.md https://raw.githubusercontent.com/specmatic/specmatic-mcp-sample-with-spec-kit/main/.claude/agents/api-mock-manager.md $ curl -fsSL --create-dirs -o .claude/agents/api-resiliency-tester.md https://raw.githubusercontent.com/specmatic/specmatic-mcp-sample-with-spec-kit/main/.claude/agents/api-resiliency-tester.md $ curl -fsSL --create-dirs -o .claude/agents/contract-test-runner.md https://raw.githubusercontent.com/specmatic/specmatic-mcp-sample-with-spec-kit/main/.claude/agents/contract-test-runner.md $ curl -fsSL --create-dirs -o .claude/agents/openapi-spec-author.md https://raw.githubusercontent.com/specmatic/specmatic-mcp-sample-with-spec-kit/main/.claude/agents/openapi-spec-author.md $ curl -fsSL --create-dirs -o .claude/agents/ui-component-tester.md https://raw.githubusercontent.com/specmatic/specmatic-mcp-sample-with-spec-kit/main/.claude/agents/ui-component-tester.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 *)"
]
}
} Subagents (5)
| api-mock-manager model: inherit | Use this agent when you need to manage mock servers using Specmatic MCP for OpenAPI specifications. Examples include: setting up mock servers from OpenAPI specs, configuring Specmatic mock server para |
| api-resiliency-tester model: inherit | Use this agent to test API resilience using Specmatic MCP resiliency tests and analyze JUnit test reports. Examples: <example>Context: User wants to test how their API handles invalid/boundary conditi |
| contract-test-runner model: inherit | Use this agent to validate API implementations against OpenAPI specifications using Specmatic MCP contract testing. Examples: <example>Context: User has just implemented a new REST API endpoint and wa |
| openapi-spec-author model: inherit | Use this agent when you need to create, modify, or generate OpenAPI 3.0.x specifications for APIs. Examples include: when designing a new REST API and need the specification document, when updating ex |
| ui-component-tester model: inherit | Use this agent when you need to test UI components using Playwright MCP for component-level validation and user interaction testing. Focus on individual component behavior, form interactions, and user |
Slash commands (4)
/plan/reset-sample-project/specify/tasks
Similar rigs
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Orchestrator 2.6k tok ·
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
Orchestrator 14.5k tok ·
alirezarezvani/claude-skills
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, complian
Orchestrator 48.5k tok ·
czlonkowski/n8n-mcp
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
Orchestrator 3.8k tok ·