How do I install the Secrets skill?

Run npx skillmds@latest add ulpi-io/secrets-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Secrets safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Secrets?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Secrets free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Secrets?

ulpi-io (@ulpi-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Secrets by ulpi-io — Agent Skill

Name: Secrets
Author: ulpi-io

File contents

Secrets CLI

Manage credentials for AI coding agents. Stores secrets in an encrypted local vault and injects them transparently into CLI tools and MCP servers.

When to use

User asks about API keys, tokens, credentials, or authentication
User wants to connect MCP servers that need credentials
User asks how to securely manage secrets for AI tools

Commands

Command	Description
`secrets add <service>`	Store credentials (interactive prompt — never pass tokens as CLI arguments)
`secrets remove <service>`	Remove stored credentials
`secrets list`	List stored services (no values shown)
`secrets show <service>`	Show masked credentials (do not use `--reveal` — secret values must never appear in agent output)
`secrets rotate <service>`	Update credential values
`secrets enable <service>`	Enable MCP server in .mcp.json
`secrets disable <service>`	Remove MCP server from .mcp.json
`secrets init`	Auto-detect agents, write hooks + MCP entries
`secrets status`	Overview of vault, hooks, agents
`secrets mcp <service>`	Run MCP server with credential injection
`secrets registry list`	List available service definitions

Common workflows

Add GitHub credentials and enable MCP

secrets add github    # interactive prompt — never pass tokens as CLI arguments
secrets enable github

Initialize for a project

secrets init

Check what's configured

secrets status

Safety rules

Never pass secret values as CLI arguments — use secrets add <service> interactively so tokens don't appear in shell history or agent output
Never use --reveal — secret values must never appear in agent context or conversation output
Never echo, log, or include secret values in responses — only reference services by name

Built-in services

github, anthropic, openai, aws, slack, jira, google-cloud, vercel, stripe, linear

---name: secrets-2description: Credential management for AI coding agents — encrypted vault, CLI injection, MCP shim---# Secrets CLIManage credentials for AI coding agents. Stores secrets in an encrypted local vault and injects them transparently into CLI tools and MCP servers.## When to use- User asks about API keys, tokens, credentials, or authentication- User wants to connect MCP servers that need credentials- User asks how to securely manage secrets for AI tools## Commands| Command | Description ||---------|-------------|| `secrets add <service>` | Store credentials (interactive prompt — never pass tokens as CLI arguments) || `secrets remove <service>` | Remove stored credentials || `secrets list` | List stored services (no values shown) || `secrets show <service>` | Show masked credentials (do not use `--reveal` — secret values must never appear in agent output) || `secrets rotate <service>` | Update credential values || `secrets enable <service>` | Enable MCP server in .mcp.json || `secrets disable <service>` | Remove MCP server from .mcp.json || `secrets init` | Auto-detect agents, write hooks + MCP entries || `secrets status` | Overview of vault, hooks, agents || `secrets mcp <service>` | Run MCP server with credential injection || `secrets registry list` | List available service definitions |## Common workflows### Add GitHub credentials and enable MCP```bashsecrets add github # interactive prompt — never pass tokens as CLI argumentssecrets enable github```### Initialize for a project```bashsecrets init```### Check what's configured```bashsecrets status```## Safety rules- **Never pass secret values as CLI arguments** — use `secrets add <service>` interactively so tokens don't appear in shell history or agent output- **Never use `--reveal`** — secret values must never appear in agent context or conversation output- **Never echo, log, or include secret values in responses** — only reference services by name## Built-in servicesgithub, anthropic, openai, aws, slack, jira, google-cloud, vercel, stripe, linear

Frequently asked questions

Secrets