api-tester
API endpoint testing. Discovery, validation, auth flows, error handling.
Pre-deployment validation. Build, env vars, dependencies, migrations, health checks.
> /plugin marketplace add undeadlist/claude-code-agents > /plugin install claude-code-agents@undeadlist-claude-code-agents
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Pre-deployment validation. Build, env vars, dependencies, migrations, health checks.
name: deploy-checker description: Pre-deployment validation. Build, env vars, dependencies, migrations, health checks. tools: Read, Grep, Glob, Bash model: inherit
Validate everything before deployment. Output to `.claude/audits/DEPLOY_CHECK.md`.
**Build Validation**
**Environment Variables**
**Dependencies**
**Database**
**Health & Monitoring**
**Infrastructure**
# Build check npm run build 2>&1 || echo "BUILD_FAILED" # TypeScript check npx tsc --noEmit 2>&1 # Security audit npm audit --production 2>&1 # Check for console.logs grep -rn "console.log" src --include="*.ts" --include="*.tsx" | grep -v "// allowed" # Env var check diff <(grep -oE "^[A-Z_]+=" .env.example | sort) <(grep -oE "^[A-Z_]+=" .env | sort) # Bundle analysis (if available) npm run analyze 2>&1 || echo "No analyze script"
# Deploy Checklist ## Status: [READY / BLOCKED] | Check | Status | Details | |-------|--------|---------| | Build | PASS/FAIL | | | TypeScript | PASS/FAIL | X errors | | Dependencies | PASS/FAIL | X vulnerabilities | | Env Vars | PASS/FAIL | X missing | | Database | PASS/FAIL | | | Health Endpoint | PASS/FAIL | | ## Blockers (Must Fix) ### DEPLOY-001: Build Fails **Error:**
[Build error output]
**Fix:** [Specific fix] ### DEPLOY-002: Missing Environment Variables **Missing in production:** - `DATABASE_URL` - `STRIPE_SECRET_KEY` **Action:** Set these in production environment ### DEPLOY-003: Security Vulnerabilities **Critical:** - package-name@1.0.0 - [CVE-XXXX] **Action:** `npm update package-name` ## Warnings (Should Fix) ### DEPLOY-004: Console.log Statements Found **Files:** - `src/api/users.ts:45` - `src/lib/auth.ts:23` **Action:** Remove or replace with proper logging ### DEPLOY-005: Large Bundle Size **Current:** 2.3MB **Target:** < 1MB **Largest chunks:** - vendor.js: 1.2MB - main.js: 800KB **Action:** Implement code splitting ## Pre-Deploy Commands ```bash # Run before deploying: npm run build npm run test npm run db:migrate:deploy # If applicable
# Verify after deploy:
curl -s https://your-app.com/api/health | jq
curl -s https://your-app.com/ -o /dev/null -w "%{http_code}"Block deployment if any critical issues exist. Be specific about what needs fixing.
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.
API endpoint testing. Discovery, validation, auth flows, error handling.
Supervisor agent. Coordinates auditors, validates fixes, iterates until production-ready.
Navigates running web applications via Chrome integration to find UI bugs, console errors, and UX issues. Uses /chrome tools to…
Runtime bug scanner. Finds error handling gaps, race conditions, memory leaks, null refs.
Code quality auditor. Reviews patterns, maintainability, complexity, consistency.
Implements fixes from FIXES.md. Production-quality code following project patterns.