Varlock Skill

Install

mkdir -p ~/.claude/skills/varlock && curl -sSL https://raw.githubusercontent.com/wrsmith108/varlock-claude-skill/main/skills/varlock/SKILL.md -o ~/.claude/skills/varlock/SKILL.md

This is third-party code. Review the repository files before installing.

What it does

The skill gives the agent rules for handling environment variables via the Varlock CLI. The agent does not read .env or print secrets with echo or printenv; it reads the value-free .env.schema instead. It validates keys with varlock load, which masks sensitive values, and runs commands needing secrets through varlock run. Requests to change a secret are declined, and the user is asked to do it by hand.

Who it is for. For developers using Claude Code on projects with API keys and passwords in .env.

Example request

Check whether the Stripe keys are set in this project without showing their values

Limitations

The skill is instructions only and does not technically block reading .env; protection depends on the agent following the rules. It requires the Varlock CLI and a .env.schema file in the project. Per the README, Varlock installs by downloading and running a script from varlock.dev.

How to disable. Delete the ~/.claude/skills/varlock folder.

Security check

• The skill consists of instructions that restrict how the agent handles secrets

README in short

The README explains how secrets leak into terminal output, model context, logs and commits, and how the skill prevents it. Install with a single curl command or by copying from a clone; the Varlock CLI installs separately. It includes a table of safe replacements for risky commands, an annotated .env.schema example and responses to secret-related requests. MIT licensed.

SKILL.md

---
name: varlock
description: Secure environment variable management with Varlock. Use when handling secrets, API keys, credentials, or any sensitive configuration. Ensures secrets are never exposed in terminals, logs, traces, or Claude's context. Trigger phrases include "environment variables", "secrets", ".env", "API key", "credentials", "sensitive", "Varlock".
version: 1.0.0
---

# Varlock Security Skill

Secure-by-default environment variable management for Claude Code sessions.

> **Repository**: https://github.com/dmno-dev/varlock
> **Documentation**: https://varlock.dev

## Core Principle: Secrets Never Exposed

When working with Claude, secrets must NEVER appear in:
- Terminal output
- Claude's input/output context
- Log files or traces
- Git commits or diffs
- Error messages

This skill ensures all sensitive data is properly protected.

---

## CRITICAL: Security Rules for Claude

### Rule 1: Never Echo Secrets

```bash
# ❌ NEVER DO THIS - exposes secret to Claude's context
echo $CLERK_SECRET_KEY
cat .env | grep SECRET
printenv | grep API

# ✅ DO THIS - validates without exposing
varlock load --quiet && echo "✓ Secrets validated"
```

### Rule 2: Never Read .env Directly

```bash
# ❌ NEVER DO THIS - exposes secret to Claude's context
cat .env
less .env
Read tool on .env file

# ✅ DO THIS - read schema (safe) not values
cat .env.schema
varlock load  # Shows masked values
```

### Rule 3: Use Varlock for Validation

```bash
# ❌ NEVER DO THIS - exposes secret in error
test -n "$API_KEY" && echo "Key: $API_KEY"

Related