agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/password-manager/SKILL.md

password-manager

Skill5 starsChanged 8 months agoMITView on GitHub

Access 1Password secrets and inject environment variables via the op CLI. Use when user needs to retrieve credentials, inject secrets into commands, or look up stored items. Never stores or logs secrets.

  • Reads credentials
  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Read secrets and inject environment variables from 1Password using the op CLI.

    line 21
  2. Very specific:

    Always check if CLI is installed and signed in: op whoami

    line 82
  3. Very specific:

    If not installed, show brew install 1password-cli and stop

    line 83
  4. Very specific:

    If not signed in, show op signin and stop

    line 84
  5. Distinctive:

    NEVER print secret values in assistant responses — only confirm "retrieved" or use them directly in commands

    line 85
  6. Very specific:

    NEVER write secrets to files that might be committed (e.g., .env in a git repo) without warning the user

    line 86
  7. Distinctive:

    NEVER log, store, or repeat credential values in memory or workspace files

    line 87
  8. Very specific:

    Use op read URI format for precise field access.

    line 88
  9. Distinctive:

    If the user asks "what's my password for X", retrieve it and only show the value in the terminal — do not include it in any saved file

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Password Manager (1Password)

Read secrets and inject environment variables from 1Password using the op CLI.

Prerequisites

brew install 1password-cli

Sign in:

op signin

Or for biometric unlock (recommended):

  1. Open 1Password app → Settings → Developer → enable "Integrate with 1Password CLI"
  2. Then op commands will use Touch ID automatically

Verify:

op whoami

Commands

CommandDescription
op whoamiShow current signed-in account
op vault listList all vaults
op item listList all items
op item list --vault "<Vault>"List items in a vault
op item get "<Item Name>"Get full item details
op item get "<Item Name>" --fields passwordGet just the password field
op read "op://<vault>/<item>/<field>"Read a specific field by URI
op run --env-file=.env.1p -- <command>Inject secrets as env vars and run command
op inject -i .env.tpl -o .envRender a secrets template to a file

Usage Examples

Get an API key:

op read "op://Personal/OpenAI/api_key"

Get a database password:

op item get "Production DB" --fields password

Inject secrets and run a script:

# .env.1p file contains: API_KEY=op://Work/MyService/api_key
op run --env-file=.env.1p -- python3 script.py

List all items in Work vault:

op item list --vault "Work" --format json | jq '.[].title'

Rules

  • Always check if CLI is installed and signed in: op whoami
  • If not installed, show brew install 1password-cli and stop
  • If not signed in, show op signin and stop
  • NEVER print secret values in assistant responses — only confirm "retrieved" or use them directly in commands
  • NEVER write secrets to files that might be committed (e.g., .env in a git repo) without warning the user
  • NEVER log, store, or repeat credential values in memory or workspace files
  • Use op read URI format for precise field access; use op item get when unsure of field names
  • For injecting into commands, prefer op run over reading the secret and passing it as an argument
  • If the user asks "what's my password for X", retrieve it and only show the value in the terminal — do not include it in any saved file

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.