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 Code can spawn subagents via Task(). These are the prompts those agents receive.
@undeadlistFix bugs with regression prevention using test-first approach
@undeadlistRun all 11 audit agents in parallel, then consolidate findings with fix-planner
@undeadlistDevelop new features with test-first approach (TDD)
@undeadlistRun code quality checks and tests before committing
@undeadlistValidate build, environment, and dependencies before deployment
@undeadlistFull audit + fixes + deploy validation for production release
@undeadlistAPI endpoint testing. Discovery, validation, auth flows, error handling.
@undeadlistSupervisor agent. Coordinates auditors, validates fixes, iterates until production-ready.
@undeadlistNavigates running web applications via Chrome integration to find UI bugs, console errors, and UX issues. Uses /chrome tools to…
@undeadlistRuntime bug scanner. Finds error handling gaps, race conditions, memory leaks, null refs.
@undeadlistCode quality auditor. Reviews patterns, maintainability, complexity, consistency.
@undeadlist© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Implements fixes from FIXES.md. Production-quality code following project patterns.
@undeadlistReal-time console monitoring during browser sessions. Watches for errors, warnings, and logs as you test.
@undeadlistDatabase auditor. Schema design, N+1 queries, indexes, connection pooling.
@undeadlistDependency auditor. Outdated packages, vulnerabilities, licenses, unused deps.
@undeadlistPre-deployment validation. Build, env vars, dependencies, migrations, health checks.
@undeadlistDocumentation coverage analyzer. Finds missing docs, outdated comments, API gaps.
@undeadlistEnvironment configuration validator. Compares .env.example vs .env, checks for secrets.
@undeadlist