verify-setup

A command that checks whether a project's Claude Code infrastructure is set up correctly. It examines dependencies, executable scripts, configuration files, and registered hooks.

In plain words
What is it for?
Use it to run the health check, repair printed configuration or dependency problems, and rerun it until failures are cleared.
Why use it?
It finds setup failures that can prevent project automation from working and reports optional features that still need a user's decision.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/diet103/claude-code-infrastructure-showcase/verify-setup
Clone the repo
git clone --depth 1 https://github.com/diet103/claude-code-infrastructure-showcase

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00302
Opus 5 $0.00005 $0.00151
Sonnet 5 $0.00002 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 3d ago against content hash 5ff12201433d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/verify-setup.md · 26 lines

What it actually says

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

Steps

  1. Run the health check from the project root:

    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.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 26 lines · 10 tokens per session scan A 5ff12201433d

Subscribe to this mod's changes

verify-setup is a command published in the GitHub repository diet103/claude-code-infrastructure-showcase (10,016 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 302 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.