Skip to content
Back to search

2password

1Password for coding agents: find, use, and save secrets without exposing them

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/kitlangton--2password/badge.svg)](/listings/kitlangton--2password)

HTML

<a href="/listings/kitlangton--2password"><img src="/api/listings/kitlangton--2password/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Requires [Bun](https://bun.sh) and the [1Password CLI](https://developer.1password.com/docs/cli/get-started/).

bun add -g 2password                  # the CLI
bunx skills add kitlangton/2password  # teaches your agent to use it

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 41 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # 2password
  2. 1Password for coding agents. Your agent finds, uses, and saves secrets without ever seeing them, and asks you to approve far less often.
  3. ## Install
  4. Requires [Bun](https://bun.sh) and the [1Password CLI](https://developer.1password.com/docs/cli/get-started/).
  5. ```sh
  6. bun add -g 2password # the CLI
  7. bunx skills add kitlangton/2password # teaches your agent to use it
  8. ```
  9. ## Use
  10. ```sh
  11. 2password find openai stripe # returns op:// references, never values
  12. 2password run --env "OPENAI_API_KEY=op://Personal/OpenAI API Key/credential" -- bun dev
  13. 2password env run .env.tpl -- bun dev
  14. 2password create api-credential --title "OpenAI API Key" --vault Personal --clipboard
  15. ```
  16. Run `2password --help` to see all commands.
  17. ## Fewer prompts
  18. - **One prompt per command.** `find` with many queries and env files with many references each need a single 1Password approval.
  19. - **No prompts at all.** Give your agent its own vault and a service account whose token lives in macOS Keychain, or on Windows in a file encrypted for your user (DPAPI):
  20. ```sh
  21. 2password service-account setup --vault Automation --create-vault --write --save-vault Personal
  22. ```
  23. ## Safety
  24. - Only `read` and `env resolve` intentionally return or materialize a secret from 2password.
  25. - `run` and `env run` inject plaintext into the selected child process. 2password does not print the value, but the child can; only use them with commands you trust with that credential.
  26. - New secrets come in through the clipboard or a pipe, never as arguments. Every write is read back and checked.
  27. - Writes are never retried automatically.
  28. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.