Repomix Safe Mixer logo

Repomix Safe Mixer

CommunityPopular
daymade
repomix-safe-mixer

Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing. Use when packaging code for distribution, creating reference packages, or when the user mentions security concerns about sharing code with repomix.

Overview

Publisherdaymade
Repositoryclaude-code-skills
Skill namerepomix-safe-mixer
Stars
1.4K
Forks
222
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by daymade on GitHub. Read the source before you install it.

Installation

Install the Repomix Safe Mixer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/daymade/claude-code-skills/tree/main/repomix-safe-mixer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/daymade/claude-code-skills.git /tmp/claude-code-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-skills/repomix-safe-mixer .claude/skills/repomix-safe-mixer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Repomix Safe Mixer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Repomix Safe Mixer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Repomix Safe Mixer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Repomix Safe Mixer

Overview

Safely package codebases with repomix by automatically detecting and removing hardcoded credentials.

This skill prevents accidental credential exposure when packaging code with repomix. It scans for hardcoded secrets (API keys, database credentials, tokens), reports findings, and ensures safe packaging.

When to use: When packaging code with repomix for distribution, creating shareable reference packages, or whenever security concerns exist about hardcoded credentials in code.

Core Workflow

Standard Safe Packaging

Use safe_pack.py from this skill's scripts/ directory for the complete workflow: scan → report → pack.

bash
python3 scripts/safe_pack.py <directory>

What it does:

  1. Scans directory for hardcoded credentials
  2. Reports findings with file/line details
  3. Blocks packaging if secrets found
  4. Packs with repomix only if scan is clean

Example:

bash
python3 scripts/safe_pack.py ./my-project

Output if clean:

🔍 Scanning ./my-project for hardcoded secrets...
✅ No secrets detected!
📦 Packing ./my-project with repomix...
✅ Packaging complete!
   Package is safe to distribute.

Output if secrets found:

🔍 Scanning ./my-project for hardcoded secrets...
⚠️  Security Scan Found 3 Potential Secrets:

🔴 supabase_url: 1 instance(s)
   - src/client.ts:5
     Match: https://your-project-ref.supabase.co

❌ Cannot pack: Secrets detected!

Options

Custom output file:

bash
python3 scripts/safe_pack.py \
  ./my-project \
  --output package.xml

With repomix config:

bash
python3 scripts/safe_pack.py \
  ./my-project \
  --config repomix.config.json

Exclude patterns from scanning:

bash
python3 scripts/safe_pack.py \
  ./my-project \
  --exclude '.*test.*' '.*\.example'

Force pack (dangerous, skip scan):

bash
python3 scripts/safe_pack.py \
  ./my-project \
  --force  # ⚠️ NOT RECOMMENDED

Standalone Secret Scanning

Use scan_secrets.py from this skill's scripts/ directory for scanning only (without packing).

bash
python3 scripts/scan_secrets.py <directory>

Use cases:

  • Verify cleanup after removing credentials
  • Pre-commit security checks
  • Audit existing codebases

Example:

bash
python3 scripts/scan_secrets.py ./my-project

JSON output for programmatic use:

bash
python3 scripts/scan_secrets.py \
  ./my-project \
  --json

Exclude patterns:

bash
python3 scripts/scan_secrets.py \
  ./my-project \
  --exclude '.*test.*' '.*example.*' '.*SECURITY_AUDIT\.md'

Detected Secret Types

The scanner detects common credential patterns including:

Cloud Providers:

  • AWS Access Keys (AKIA...)
  • Cloudflare R2 Account IDs and Access Keys
  • Supabase Project URLs and Anon Keys

API Keys:

  • Stripe Keys (sk_live_..., pk_live_...)
  • OpenAI API Keys (sk-...)
  • Google Gemini API Keys (AIza...)
  • Generic API Keys

Authentication:

  • JWT Tokens (eyJ...)
  • OAuth Client Secrets
  • Private Keys (-----BEGIN PRIVATE KEY-----)
  • Turnstile Keys (0x...)

See references/common_secrets.md for complete list and patterns.

Handling Detected Secrets

When secrets are found:

Step 1: Review Findings

Examine each finding to verify it's a real credential (not a placeholder or example).

Step 2: Replace with Environment Variables

Before:

javascript
const SUPABASE_URL = "https://your-project-ref.supabase.co";
const API_KEY = "<hardcoded-anon-key-DO-NOT-COMMIT>";

After:

javascript
const SUPABASE_URL = import.meta.env.VITE_SUPABASE_URL || "https://your-project-ref.supabase.co";
const API_KEY = import.meta.env.VITE_API_KEY || "your-api-key-here";

// Validation
if (!import.meta.env.VITE_SUPABASE_URL) {
  console.error("⚠️ Missing VITE_SUPABASE_URL environment variable");
}

Step 3: Create .env.example

bash
# Example environment variables
VITE_SUPABASE_URL=https://your-project-ref.supabase.co
VITE_API_KEY=your-api-key-here

# Instructions:
# 1. Copy this file to .env
# 2. Replace placeholders with real values
# 3. Never commit .env to version control

Step 4: Verify Cleanup

Run scanner again to confirm secrets removed:

bash
python3 scripts/scan_secrets.py ./my-project

Step 5: Safe Pack

Once clean, package safely:

bash
python3 scripts/safe_pack.py ./my-project

Post-Exposure Actions

If credentials were already exposed (e.g., committed to git, shared publicly):

  1. Rotate credentials immediately - Generate new keys/tokens
  2. Revoke old credentials - Disable compromised credentials
  3. Audit usage - Check logs for unauthorized access
  4. Monitor - Set up alerts for unusual activity
  5. Update deployment - Deploy code with new credentials
  6. Document incident - Record what was exposed and actions taken

Common False Positives

The scanner skips common false positives:

Placeholders:

  • your-api-key, example-key, placeholder-value
  • <YOUR_API_KEY>, ${API_KEY}, TODO: add key

Test/Example files:

  • Files matching .*test.*, .*example.*, .*sample.*

Comments:

  • Lines starting with //, #, /*, *

Environment variable references (correct usage):

  • process.env.API_KEY
  • import.meta.env.VITE_API_KEY
  • Deno.env.get('API_KEY')

Use --exclude to skip additional patterns if needed.

Integration with Repomix

This skill works with standard repomix:

Default usage (no config):

bash
python3 scripts/safe_pack.py ./project

With repomix config:

bash
python3 scripts/safe_pack.py \
  ./project \
  --config repomix.config.json

Custom output location:

bash
python3 scripts/safe_pack.py \
  ./project \
  --output ~/Downloads/package-clean.xml

The skill runs repomix internally after security validation, passing through config and output options.

Example Workflows

Workflow 1: Package a Clean Project

bash
# Scan and pack in one command
python3 scripts/safe_pack.py \
  ~/workspace/my-project \
  --output ~/Downloads/my-project-package.xml

Workflow 2: Clean and Package a Project with Secrets

bash
# Step 1: Scan to discover secrets
python3 scripts/scan_secrets.py ~/workspace/my-project

# Step 2: Review findings and replace credentials with env vars
# (Edit files manually or with automation)

# Step 3: Verify cleanup
python3 scripts/scan_secrets.py ~/workspace/my-project

# Step 4: Package safely
python3 scripts/safe_pack.py \
  ~/workspace/my-project \
  --output ~/Downloads/my-project-clean.xml

Workflow 3: Audit Before Commit

bash
# Pre-commit hook: scan for secrets
python3 scripts/scan_secrets.py . --json

# Exit code 1 if secrets found (blocks commit)
# Exit code 0 if clean (allows commit)

Resources

References:

  • references/common_secrets.md - Complete credential pattern catalog

Scripts:

  • scripts/scan_secrets.py - Standalone security scanner
  • scripts/safe_pack.py - Complete scan → pack workflow

Related Skills:

  • repomix-unmixer - Extracts files from repomix packages
  • skill-creator - Creates new Claude Code skills

Security Note

This skill detects common patterns but may not catch all credential types. Always:

  • Review findings manually
  • Rotate exposed credentials
  • Use .env.example templates
  • Validate environment variables
  • Monitor for unauthorized access

Not a replacement for: Secret scanning in CI/CD, git history scanning, or comprehensive security audits.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Repomix Safe Mixer AI skill do?

Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing. Use when packaging code for distribution, creating reference packages, or when the user mentions security concerns about sharing code with repomix.

Why use Repomix Safe Mixer on TypingMind?

Because you install it once and use it with any model. Repomix Safe Mixer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Repomix Safe Mixer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/daymade/claude-code-skills/tree/main/repomix-safe-mixer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Repomix Safe Mixer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Repomix Safe Mixer?

As many as you like. As long as a model supports skills, you can use Repomix Safe Mixer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Repomix Safe Mixer AI skill free?

Yes. It is published on GitHub by daymade under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇