Skip to main content
command CX Codex

verify-setup — Claude Code command: infrastructure health check and repair

verify-setup — a command that diagnoses your project's infrastructure, identifies what's broken, and guides you through fixes. Use it when Claude Code hooks, dependencies or configs fail.

MIT ★ 10,055 updated 2026-07-13

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/verify-setup.md
Open on GitHub

What verify-setup does

verify-setup runs a health check on your project: missing dependencies, script permissions, JSON syntax in .claude/settings.json and .claude/skills/skill-rules.json, hook registration. The script reports each failure with a specific fix.

Each [FAIL] line includes a remedy: run npm install in .claude/hooks/ for missing packages, add execute bits with chmod +x for scripts, fix JSON syntax (often a trailing comma). If hooks lack registration in settings.json, the command asks whether to copy them from the showcase repository or remove dead registrations.

Warnings ([WARN]) flag optional features — session intelligence, jq-based file tracking, AI classification keys — which the script lists but does not install, letting you decide.

What it helps with

  • Identify broken dependencies and missing npm packages
  • Fix file permissions on .claude/hooks/ scripts
  • Validate and repair JSON syntax in config files
  • Register hooks or remove orphaned entries from settings.json
  • Diagnose which parts of the infrastructure need attention

Example prompts for the agent

  • Run the health check and show me what's broken
  • Check the Claude Code infrastructure and fix anything failing
  • Execute verify-setup and help me understand the errors

How to install verify-setup

Manually: put the files in place

.claude/commands/verify-setup.md

Call it with /verify-setup. For all projects use ~/.claude/commands/

Questions about verify-setup

How do I install verify-setup in Claude Code?

Copy .claude/commands/verify-setup.md to your project root. For Codex, place ~/.codex/prompts/verify-setup.md in your home directory. For GitHub Copilot, add .github/prompts/verify-setup.prompt.md to the repo. For Gemini CLI, put .gemini/commands/verify-setup.toml in config.

What does verify-setup check?

It validates dependencies, script permissions, JSON files, and hook registration. When it finds issues, it prints the exact steps to fix them.

What are [WARN] lines?

Warnings for optional features like session intelligence or AI classification keys. The command lists what each one does; you choose whether to enable them.

Source text

verify-setup.md · MIT
---
description: Run the infrastructure health check and fix anything that fails
argument-hint: (no arguments needed)
---

Run the Claude Code infrastructure health check and get it fully green.

## Steps

1. Run the health check from the project root:
   ```bash
   bash .claude/scripts/verify-setup.sh
   ```

2. For every `[FAIL]` line, apply the printed fix. Common fixes:
   - Dependencies missing: `cd .claude/hooks && npm install`
   - Scripts not executable: `chmod +x .claude/hooks/*.sh`
   - Invalid JSON in `.claude/settings.json` or `.claude/skills/skill-rules.json`: read the file, find the syntax error (usually a trailing comma), and repair it without changing any settings values
   - Missing hook scripts registered in settings.json: ask the user whether to copy them from the showcase repo (https://github.com/diet103/claude-code-infrastructure-showcase) or remove the dead registrations

3. Re-run the script after each fix until it reports 0 failed.

4. `[WARN]` lines are optional features (session intelligence, jq-based file tracking, AI classification keys). Do NOT install API keys or system packages on the user's behalf - summarize what each warning means and let the user decide.

5. Report the final result to the user: what was broken, what you fixed, and what (if anything) remains as a warning.

© diet103 · MIT · diet103/claude-code-infrastructure-showcase

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

From the same set16

The whole set →
route-research-for-testing route-research-for-testing is a Claude Code command that collects changed routes from the current session and tests them via cURL to check edited API endpoints. CX Codex +1 ★ 10,055repo stars source-command-verify-setup source-command-verify-setup executes infrastructure health checks and repairs broken configurations or hook dependencies. CX Codex +1 ★ 10,055repo stars dev-docs-update The dev-docs-update command records active work before a context reset, covering task files, project memory, unfinished work, and handoff notes. CX Codex +1 ★ 10,055repo stars dev-docs dev-docs generates a detailed implementation plan for any task: analyzes your codebase, breaks work into phases, creates task checklists with dependencies and effort estimates, and persists across context switches. CX Codex +1 ★ 10,055repo stars auto-error-resolver auto-error-resolver is a subagent that fixes TypeScript compilation errors from hook reports and verifies the build with tsc. CX Codex ★ 10,055repo stars frontend-error-fixer The frontend-error-fixer subagent investigates frontend failures during builds and in the browser. Use it for TypeScript, React, network, and rendering problems. CX Codex ★ 10,055repo stars refactor-planner refactor-planner — a subagent that studies your code structure and writes a phased refactoring plan with risk assessment. Use it before reworking a legacy module or an oversized component. CX Codex ★ 10,055repo stars plan-reviewer plan-reviewer reviews technical plans, migrations, and system integrations before writing code. Catches architectural traps, missing dependencies, and edge cases early. CX Codex ★ 10,055repo stars

More in the catalog

Project sponsors

Companies that keep this analytics open