minanyang/10x-agent
A multi-agent workflow for shipping code: agents plan, build and review, and nothing lands without evidence a script can check.
field: unknown workflow: Git & commitsPR / code reviewPlanning & specsSecurity reviewDebugging runs claude in CI
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 minanyang/10x-agent/agents ./rig-10x-agent/agents $ npx degit minanyang/10x-agent/skills ./rig-10x-agent/skills $ npx degit minanyang/10x-agent/hooks ./rig-10x-agent/hooks
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 minanyang/10x-agent/skills/audit .claude/skills/audit $ npx degit minanyang/10x-agent/skills/batch .claude/skills/batch $ npx degit minanyang/10x-agent/skills/close .claude/skills/close $ npx degit minanyang/10x-agent/skills/code-review-branch .claude/skills/code-review-branch $ npx degit minanyang/10x-agent/skills/code-review .claude/skills/code-review $ npx degit minanyang/10x-agent/skills/commit .claude/skills/commit $ npx degit minanyang/10x-agent/skills/feedback .claude/skills/feedback $ npx degit minanyang/10x-agent/skills/open .claude/skills/open $ npx degit minanyang/10x-agent/skills/roadmap .claude/skills/roadmap $ npx degit minanyang/10x-agent/skills/work .claude/skills/work
$ curl -fsSL --create-dirs -o .claude/agents/backend-engineer.md https://raw.githubusercontent.com/minanyang/10x-agent/main/agents/backend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/minanyang/10x-agent/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/devops-engineer.md https://raw.githubusercontent.com/minanyang/10x-agent/main/agents/devops-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/minanyang/10x-agent/main/agents/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/qa-engineer.md https://raw.githubusercontent.com/minanyang/10x-agent/main/agents/qa-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/minanyang/10x-agent/main/agents/security-reviewer.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 *)"
]
}
} Skills (10)
Subagents (6)
| backend-engineer model: opus | Use proactively when the user asks to build, modify, or debug server-side code — APIs, services, database schemas, queries, migrations, business logic, server-side performance, auth/session, backgroun |
| code-reviewer model: opus | Use proactively when the user asks for a code review — pending work, an entire branch, a PR, a specific file, or a second-opinion audit. Independent cold-context review producing severity-tagged findi |
| devops-engineer model: sonnet | Use proactively when the user asks to build, modify, or debug CI/CD pipelines (GitHub Actions, GitLab CI, CircleCI), Dockerfiles or container builds, infrastructure-as-code (Terraform, Pulumi, CloudFo |
| frontend-engineer model: opus | Use proactively when the user asks to build, modify, or debug UI in the project's existing frontend stack; when styling, accessibility, or client-side performance is involved; or when frontend tests n |
| qa-engineer model: sonnet | Use proactively when the user asks to design test plans, write or fix tests (unit / integration / e2e), reproduce a bug from a report, triage failing CI, investigate flaky tests, build regression suit |
| security-reviewer model: opus | Use proactively when the user asks to review pending changes for security issues, threat-model a feature, scan for committed secrets, audit dependencies for CVEs, review auth/authz logic, or analyze i |
Similar rigs
peterkimpro/claude-code-powerpack
Drop-in Claude Code config for efficient AI-assisted development. Includes CLAUDE.md template, permission allowlist, agents, skills, and memory system.
Pragmatist 4.4k tok · · Q33
ishaankarnik11/phishforge-agentic
AI studio that turns a scenario brief into email-safe phishing-simulation templates, with GPT Image 2 image generation, mask editing and an asset library. For authorized security-awareness audits. Built with an agentic workflow: scoped Clau
Orchestrator 2.1k tok · · Q0
felipebustillo/dotclaude
A complete reference for configuring Claude Code — agents, skills, rules, hooks, settings, and memory patterns
Orchestrator 300 tok · · Q0
SaketMunda/claude-org-template
Drop this into any project and start engineering at AI speed. No setup ceremony. No re-explaining context every session.
Orchestrator 1.4k tok · · Q33