undeadlist/claude-code-agents
Claude Code Agents Prompt templates for Claude Code's subagent system. Run parallel code audits, automate fix cycles, get stuff reviewed. Built for the Claude Code Task tool. Not a framework. Just prompts that work. What This Does Claude Co
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 undeadlist/claude-code-agents/agents ./rig-claude-code-agents/agents $ npx degit undeadlist/claude-code-agents/skills ./rig-claude-code-agents/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.
$ npx degit undeadlist/claude-code-agents/skills/bug-fix .claude/skills/bug-fix $ npx degit undeadlist/claude-code-agents/skills/full-audit .claude/skills/full-audit $ npx degit undeadlist/claude-code-agents/skills/new-feature .claude/skills/new-feature $ npx degit undeadlist/claude-code-agents/skills/pre-commit .claude/skills/pre-commit $ npx degit undeadlist/claude-code-agents/skills/pre-deploy .claude/skills/pre-deploy $ npx degit undeadlist/claude-code-agents/skills/release-prep .claude/skills/release-prep
$ curl -fsSL --create-dirs -o .claude/agents/api-tester.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/api-tester.md $ curl -fsSL --create-dirs -o .claude/agents/architect-reviewer.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/architect-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/browser-qa-agent.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/browser-qa-agent.md $ curl -fsSL --create-dirs -o .claude/agents/bug-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/bug-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/code-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/code-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/code-fixer.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/code-fixer.md $ curl -fsSL --create-dirs -o .claude/agents/console-monitor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/console-monitor.md $ curl -fsSL --create-dirs -o .claude/agents/db-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/db-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/dep-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/dep-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/deploy-checker.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/deploy-checker.md $ curl -fsSL --create-dirs -o .claude/agents/doc-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/doc-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/env-validator.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/env-validator.md $ curl -fsSL --create-dirs -o .claude/agents/fix-planner.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/fix-planner.md $ curl -fsSL --create-dirs -o .claude/agents/fullstack-qa-orchestrator.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/fullstack-qa-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/infra-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/infra-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/perf-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/perf-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/pr-writer.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/pr-writer.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/security-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/seed-generator.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/seed-generator.md $ curl -fsSL --create-dirs -o .claude/agents/seo-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/seo-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/test-runner.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/test-runner.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/test-writer.md $ curl -fsSL --create-dirs -o .claude/agents/ui-auditor.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/ui-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/visual-diff.md https://raw.githubusercontent.com/undeadlist/claude-code-agents/main/agents/visual-diff.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:
{
"permissions": {
"deny": [
"Read(~/.ssh/**)",
"Read(**/.env)",
"Bash(rm -rf *)",
"Read(./.env)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(**/*.pem)",
"Bash(rm -rf /*)",
"Read(~/.aws/**)",
"Bash(rm -rf:*)",
"Read(.env)",
"Bash(git push --force*)",
"Read(**/*.key)",
"Read(./.env.*)",
"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(wget *)",
"Bash(npm publish:*)",
"Bash(gh pr merge *)",
"Bash(chown *)",
"Bash(docker *)"
]
}
} Skills (6)
Subagents (24)
| api-tester model: inherit | API endpoint testing. Discovery, validation, auth flows, error handling. |
| architect-reviewer model: inherit | Supervisor agent. Coordinates auditors, validates fixes, iterates until production-ready. |
| browser-qa-agent model: inherit | Navigates running web applications via Chrome integration to find UI bugs, console errors, and UX issues. Uses /chrome tools to interact with localhost or deployed apps. |
| bug-auditor model: inherit | Runtime bug scanner. Finds error handling gaps, race conditions, memory leaks, null refs. |
| code-auditor model: inherit | Code quality auditor. Reviews patterns, maintainability, complexity, consistency. |
| code-fixer model: inherit | Implements fixes from FIXES.md. Production-quality code following project patterns. |
| console-monitor model: inherit | Real-time console monitoring during browser sessions. Watches for errors, warnings, and logs as you test. |
| db-auditor model: inherit | Database auditor. Schema design, N+1 queries, indexes, connection pooling. |
| dep-auditor model: inherit | Dependency auditor. Outdated packages, vulnerabilities, licenses, unused deps. |
| deploy-checker model: inherit | Pre-deployment validation. Build, env vars, dependencies, migrations, health checks. |
| doc-auditor model: inherit | Documentation coverage analyzer. Finds missing docs, outdated comments, API gaps. |
| env-validator model: inherit | Environment configuration validator. Compares .env.example vs .env, checks for secrets. |
| fix-planner model: inherit | Creates prioritized fix plans from audit findings. Generates FIXES.md with deduplication. |
| fullstack-qa-orchestrator model: inherit | Coordinates browser-qa-agent with code-fixer for complete test-fix-verify cycles. The Replit-style workflow. |
| infra-auditor model: inherit | Infrastructure and deployment checker. Env vars, headers, database config. |
| perf-auditor model: inherit | Performance auditor. Bundle size, Core Web Vitals, slow queries, memory leaks. |
| pr-writer model: inherit | Pull request description generator. Summarizes changes, creates checklist. |
| security-auditor model: inherit | Comprehensive security analysis. OWASP Top 10, injection, auth, secrets, headers. |
| seed-generator model: inherit | Test data generator. Creates realistic seed data based on schema. |
| seo-auditor model: inherit | SEO and discoverability auditor. Meta tags, OpenGraph, sitemap, structured data. |
| test-runner model: inherit | Runs tests and validates fixes. TypeScript, lint, unit tests. |
| test-writer model: inherit | Auto-generates tests for existing code. Unit tests, integration tests, coverage gaps. |
| ui-auditor model: inherit | UI/UX consistency and accessibility checker. Design patterns, a11y issues. |
| visual-diff model: inherit | Screenshot comparison for visual regression testing. Captures before/after states and reports differences. |
Similar rigs
Yassinekrn/claude-setup
Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).
Orchestrator 1.2k tok ·
stuartshields/claude-setup
Educational Claude Setup
Fort Knox 3.7k tok ·
pedrofalcao10/Quick-Claude-Code-Setup
—
Pragmatist 70 tok ·
kmanan/claude-setup
🤖 My Claude Code setup — global permissions, hooks, rules, and skills for managing 20+ projects with zero friction
Pragmatist 249 tok ·