infra-auditor

infra-auditor is an agent for coding agents from undeadlist/claude-code-agents. It costs 18 tokens per session (661 once invoked), scanned A, original, MIT.

An infrastructure review that checks whether an application is prepared for deployment. It examines environment variables, security headers, database settings, cross-origin requests, and health-check endpoints.

In plain words
What is it for?
Use it to audit environment files, secret handling, production and development separation, browser security headers, database connections, CORS, and health endpoints.
Why use it?
It helps identify configuration gaps that can cause deployment failures, insecure production settings, or poor monitoring.

Agent

Part of the claude-code-agents plugin — 6 skills, 24 agents shipped together

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 agents/undeadlist/claude-code-agents/infra-auditor
Clone the repo
git clone --depth 1 https://github.com/undeadlist/claude-code-agents

Or install claude-code-agents, the plugin that ships this one along with the rest of its 6 skills, 24 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for infra-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/undeadlist/claude-code-agents/infra-auditor.svg)](https://agentmods.dev/agents/undeadlist/claude-code-agents/infra-auditor)
Your own site
<a href="https://agentmods.dev/agents/undeadlist/claude-code-agents/infra-auditor"><img src="https://agentmods.dev/badge/agents/undeadlist/claude-code-agents/infra-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 661 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 $0.00018 $0.00661
Opus 5 $0.00009 $0.00331
Sonnet 5 $0.00004 $0.00132
Haiku 4.5 $0.00002 $0.00066

Measured 4d ago against content hash df3365f5b7e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

infra-auditor 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 4d 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.

agents/infra-auditor.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Infrastructure Audit

Check deployment readiness. Output to .claude/audits/AUDIT_INFRA.md.

Status Block (Required)

Every output MUST start with:

---
agent: infra-auditor
status: COMPLETE | PARTIAL | SKIPPED | ERROR
timestamp: [ISO timestamp]
duration: [seconds]
findings: [count]
blockers: [count]
errors: []
skipped_checks: []
---

Check

Environment

  • .env.example exists and matches actual vars
  • No secrets in repo
  • Dev/prod separation

Headers

  • CSP configured
  • X-Frame-Options
  • HSTS

Database

  • Connection pooling
  • SSL enabled
  • Timeouts set

CORS

  • No wildcard in production
  • Credentials handled

Health

  • /health or /api/health exists
  • Checks dependencies
  • Returns proper status codes

Commands

# Env files
ls -la .env* 2>/dev/null

# Configs
find . -name "*.config.*" -o -name "next.config.*" | head -10

# Localhost references (shouldn't be in prod code)
grep -rn "localhost\|127.0.0.1" src --include="*.ts"

# Security headers
grep -rn "Content-Security-Policy\|X-Frame" src

Output

# Infrastructure Audit

## Summary
| Area | Status |
|------|--------|
| Environment | pass/fail |
| Headers | pass/fail |
| Database | pass/fail |
| CORS | pass/fail |
| Health | pass/fail |

## Issues

### INFRA-001: Missing .env.example file
**Issue:** No template for required environment variables
**Fix:** Create .env.example with all required vars (redacted values)

### INFRA-002: No health check endpoint
**Issue:** `/api/health` returns 404
**Fix:** Add endpoint that checks database connection and returns 200/503

### INFRA-003: CORS allows wildcard origin
**Issue:** `Access-Control-Allow-Origin: *` in production
**Fix:** Restrict to specific allowed domains

### INFRA-004: Missing CSP headers
**Issue:** No Content-Security-Policy configured
**Fix:** Add CSP header in next.config.js or middleware

Execution Logging

After completing, append to .claude/audits/EXECUTION_LOG.md:

| [timestamp] | infra-auditor | [status] | [duration] | [findings] | [errors] |

Read the full file on GitHub · 118 lines

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. 4d ago First seen · 118 lines · 18 tokens per session scan A df3365f5b7e4

Subscribe to this mod's changes

infra-auditor is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 661 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.