agentleFS
jasonmichaelbell78-creatorjasonmichaelbell78-creator/sonash-v0/.claude/skills/decrypt-secrets/SKILL.md

decrypt-secrets

Skill2 starsChanged 9 months agoApache-2.0View on GitHub

Decrypt MCP tokens for remote sessions

  • Reads credentials

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the task doesn't match this skill's scope -- check related skills

    line 12
  2. Distinctive:

    When a more specialized skill exists for the specific task

    line 13
  3. Distinctive:

    When you see "Encrypted secrets found but not decrypted" in session startup

    line 18
  4. Distinctive:

    When MCP servers fail due to missing authentication

    line 19
  5. Distinctive:

    Run the decryption script and enter your passphrase:

    line 29
  6. Distinctive:

    If you haven't encrypted your secrets yet:

    line 39
  7. Very specific:

    Add your tokens to .env.local:

    line 41
  8. Very specific:

    Commit .env.local.encrypted to your repo

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Decrypt Secrets

Decrypt your encrypted MCP tokens at the start of a remote session.

When NOT to Use

  • When the task doesn't match this skill's scope -- check related skills
  • When a more specialized skill exists for the specific task

When to Use

  • At the start of a remote/web session when MCP servers need tokens
  • When you see "Encrypted secrets found but not decrypted" in session startup
  • When MCP servers fail due to missing authentication

How It Works

  1. Your tokens are stored encrypted in .env.local.encrypted (safe to commit)
  2. Running this decrypts them to .env.local (gitignored)
  3. MCP servers then use the tokens automatically

Instructions

Run the decryption script and enter your passphrase:

node scripts/secrets/decrypt-secrets.js

You'll be prompted for the passphrase you set when encrypting.

First-Time Setup

If you haven't encrypted your secrets yet:

  1. Add your tokens to .env.local:

    GITHUB_TOKEN=ghp_your_token
    SONAR_TOKEN=sqp_your_token
    CONTEXT7_API_KEY=your_key
  2. Encrypt them:

    node scripts/secrets/encrypt-secrets.js
  3. Commit .env.local.encrypted to your repo
  4. In future sessions, just run the decrypt script

Security Notes

  • .env.local is gitignored - your actual tokens are never committed
  • .env.local.encrypted uses AES-256-GCM encryption
  • Choose a strong passphrase (8+ characters)
  • Your passphrase is never stored anywhere

Version History

VersionDateDescription
1.02026-02-25Initial implementation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.