MiltonKlun/Qaizen
AI-assisted QA pipeline with traceable test cases, Playwright E2E and Postman/Newman API checks, schema validation, and four human review gates.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
up to ~47.5k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add playwright-test -- cmd /c npx playwright run-test-mcp-server $ claude mcp add atlassian -e CONFLUENCE_API_<redacted> -e CONFLUENCE_URL=YOUR_CONFLUENCE_URL -e CONFLUENCE_USERNAME=YOUR_CONFLUENCE_USERNAME -e ENABLED_TOOLS=YOUR_ENABLED_TOOLS -e JIRA_API_<redacted> -e JIRA_URL=YOUR_JIRA_URL -e JIRA_USERNAME=YOUR_JIRA_USERNAME -e READ_ONLY_MODE=YOUR_READ_ONLY_MODE -e TOOLSETS=YOUR_TOOLSETS -- docker run -i --rm -e JIRA_URL -e JIRA_USERNAME -e JIRA_API_TOKEN -e CONFLUENCE_URL -e CONFLUENCE_USERNAME -e CONFLUENCE_API_TOKEN -e ENABLED_TOOLS -e TOOLSETS -e READ_ONLY_MODE ghcr.io/sooperset/mcp-atlassian:0.23.1 $ claude mcp add atlassian-write -e CONFLUENCE_API_<redacted> -e CONFLUENCE_URL=YOUR_CONFLUENCE_URL -e CONFLUENCE_USERNAME=YOUR_CONFLUENCE_USERNAME -e ENABLED_TOOLS=YOUR_ENABLED_TOOLS -e JIRA_API_<redacted> -e JIRA_URL=YOUR_JIRA_URL -e JIRA_USERNAME=YOUR_JIRA_USERNAME -e TOOLSETS=YOUR_TOOLSETS -- docker run -i --rm -e JIRA_URL -e JIRA_USERNAME -e JIRA_API_TOKEN -e CONFLUENCE_URL -e CONFLUENCE_USERNAME -e CONFLUENCE_API_TOKEN -e ENABLED_TOOLS -e TOOLSETS ghcr.io/sooperset/mcp-atlassian:0.23.1 $ claude mcp add postman -e POSTMAN_<redacted> -- cmd /c npx @postman/postman-mcp-server --full $ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -e GITHUB_TOOLSETS=YOUR_GITHUB_TOOLSETS -- docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN -e GITHUB_TOOLSETS ghcr.io/github/github-mcp-server $ npx degit MiltonKlun/Qaizen/agents ./rig-qaizen/agents $ npx degit MiltonKlun/Qaizen/skills ./rig-qaizen/skills
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 playwright-test -- cmd /c npx playwright run-test-mcp-server $ claude mcp add atlassian -e CONFLUENCE_API_<redacted> -e CONFLUENCE_URL=YOUR_CONFLUENCE_URL -e CONFLUENCE_USERNAME=YOUR_CONFLUENCE_USERNAME -e ENABLED_TOOLS=YOUR_ENABLED_TOOLS -e JIRA_API_<redacted> -e JIRA_URL=YOUR_JIRA_URL -e JIRA_USERNAME=YOUR_JIRA_USERNAME -e READ_ONLY_MODE=YOUR_READ_ONLY_MODE -e TOOLSETS=YOUR_TOOLSETS -- docker run -i --rm -e JIRA_URL -e JIRA_USERNAME -e JIRA_API_TOKEN -e CONFLUENCE_URL -e CONFLUENCE_USERNAME -e CONFLUENCE_API_TOKEN -e ENABLED_TOOLS -e TOOLSETS -e READ_ONLY_MODE ghcr.io/sooperset/mcp-atlassian:0.23.1 $ claude mcp add atlassian-write -e CONFLUENCE_API_<redacted> -e CONFLUENCE_URL=YOUR_CONFLUENCE_URL -e CONFLUENCE_USERNAME=YOUR_CONFLUENCE_USERNAME -e ENABLED_TOOLS=YOUR_ENABLED_TOOLS -e JIRA_API_<redacted> -e JIRA_URL=YOUR_JIRA_URL -e JIRA_USERNAME=YOUR_JIRA_USERNAME -e TOOLSETS=YOUR_TOOLSETS -- docker run -i --rm -e JIRA_URL -e JIRA_USERNAME -e JIRA_API_TOKEN -e CONFLUENCE_URL -e CONFLUENCE_USERNAME -e CONFLUENCE_API_TOKEN -e ENABLED_TOOLS -e TOOLSETS ghcr.io/sooperset/mcp-atlassian:0.23.1 $ claude mcp add postman -e POSTMAN_<redacted> -- cmd /c npx @postman/postman-mcp-server --full $ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -e GITHUB_TOOLSETS=YOUR_GITHUB_TOOLSETS -- docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN -e GITHUB_TOOLSETS ghcr.io/github/github-mcp-server
$ npx degit MiltonKlun/Qaizen/skills/analyzing-logs .claude/skills/analyzing-logs $ npx degit MiltonKlun/Qaizen/skills/designing-cases .claude/skills/designing-cases $ npx degit MiltonKlun/Qaizen/skills/planning-tests .claude/skills/planning-tests $ npx degit MiltonKlun/Qaizen/skills/receiving-tickets .claude/skills/receiving-tickets $ npx degit MiltonKlun/Qaizen/skills/syncing-jira .claude/skills/syncing-jira $ npx degit MiltonKlun/Qaizen/skills/syncing-testlink .claude/skills/syncing-testlink
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/MiltonKlun/Qaizen/main/agents/analyst.md $ curl -fsSL --create-dirs -o .claude/agents/api-agent.md https://raw.githubusercontent.com/MiltonKlun/Qaizen/main/agents/api-agent.md $ curl -fsSL --create-dirs -o .claude/agents/failure-classifier.md https://raw.githubusercontent.com/MiltonKlun/Qaizen/main/agents/failure-classifier.md $ curl -fsSL --create-dirs -o .claude/agents/reporter.md https://raw.githubusercontent.com/MiltonKlun/Qaizen/main/agents/reporter.md $ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.com/MiltonKlun/Qaizen/main/agents/spec-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-designer.md https://raw.githubusercontent.com/MiltonKlun/Qaizen/main/agents/test-designer.md $ curl -fsSL --create-dirs -o .claude/agents/test-management-adapter.md https://raw.githubusercontent.com/MiltonKlun/Qaizen/main/agents/test-management-adapter.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (5)
| server | source | est. tokens |
|---|---|---|
| playwright · "playwright-test" | npm | 2.5k |
| Atlassian env: CONFLUENCE_API_TOKEN, CONFLUENCE_URL, CONFLUENCE_USERNAME, ENABLED_TOOLS, JIRA_API_TOKEN +4 | docker | 10.0k |
| Atlassian · "atlassian-write" env: CONFLUENCE_API_TOKEN, CONFLUENCE_URL, CONFLUENCE_USERNAME, ENABLED_TOOLS, JIRA_API_TOKEN +3 | docker | 10.0k |
| @postman/postman-mcp-server · "postman" env: POSTMAN_API_KEY | npm | 2.5k |
| GitHub MCP · "github" env: GITHUB_PERSONAL_ACCESS_TOKEN, GITHUB_TOOLSETS | docker | 18.0k |
Skills (6)
Subagents (7)
| analyst | | |
| api-agent | | |
| failure-classifier | | |
| reporter | | |
| spec-reviewer | | |
| test-designer | | |
| test-management-adapter | | |
Similar rigs
spencerldixon/dotfiles
Dotfiles for my development environment and tooling
Automator 36.9k tok · · Q15
DiegoOya/expense_tracker
Expense tracker MCP server built spec-first with Claude Code: hooks, skills, subagents and an honest log of what went wrong.
Fort Knox 21.5k tok · · Q32
orynvn/claude-workspace-setup
A project template for Claude Code CLI — opinionated, token-efficient, and built for multi-agent workflows.
Orchestrator 22.3k tok · · Q18
dandyrow/dotfiles
Repository containing my configuration dotfiles
Pragmatist 35.5k tok · · Q5