1password

A guide for using the 1Password command-line tool to retrieve secrets and configure authentication. 1Password is a service that stores passwords, keys, and other sensitive values.

In plain words
What is it for?
Use it for runtime secrets, SSH access, Git commit signing, shell integrations, CI environments, account selection, and troubleshooting the 1Password CLI.
Why use it?
It helps resolve login, SSH, signing, service-account, and configuration problems without exposing secret values unnecessarily.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/petejm/1password-skill/1password
Clone the repo
git clone --depth 1 https://github.com/petejm/1password-skill

Made for: Cursor.

Per session 8,182 This file is loaded in full into every session.
When invoked 8,182 The same file — it is already loaded in full.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.08182 $0.08182
Opus 5 $0.04091 $0.04091
Sonnet 5 $0.01636 $0.01636
Haiku 4.5 $0.00818 $0.00818

Measured 2d ago against content hash ca2cc3c74d4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

1password scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Claude Code's bubblewrap sandbox strips setgid bits; `op` requires the `onepassword-cli` group. Symptom: works in terminal but fails as a Claude tool call. Fix: `sudo usermod -aG onepassword-cli $(whoami)`, then log out

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Basic auth** (username+password, not token) — never use `curl -u` (mangles special chars):
integrations/cursor/.cursor/rules/1password.mdc · 569 lines

How it starts

The opening of the file, as written. The whole thing — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requires: op CLI 2.30.0+ with desktop app integration enabled — 2.30.0 made human-readable output concealed by default and added the --reveal flag this skill depends on. Run op --version to check.

1Password CLI — Decision Router

You're seeing... Go to
"Permission denied (publickey)" / git push auth fails → Auth Recovery
Need a secret value at runtime → Runtime Access
Don't know the vault, item, or field name → Runtime Access
Setting up op:// in config files / .env → Config File Patterns
SSH agent not responding / wrong socket path → SSH Agent
Git commit signing setup or failures → Git Signing
gh, aws, or claude should authenticate through 1Password → Shell Plugins
Headless / CI / no desktop app available → Service Accounts
op hangs, times out, or biometric won't appear → Troubleshooting
Wrong account / multi-account confusion → Troubleshooting
op not found / not installed → Troubleshooting
Specific error message → Error Catalog

Security Rules

  1. Prefer op run over op read — secret never enters conversation context. Never add --no-masking.
  2. Never run op commands speculatively — a command that needs authentication raises a biometric prompt on the user's desktop and physically interrupts them. An already-unlocked session answers silently (op signin --help: "'op signin' is idempotent. It only prompts for authentication if you aren't already authenticated"), so you cannot tell in advance which one you will get. Run op only when the user's request requires it.
  3. Scope with --vault on op item get / op item list — prevents exposing item names across all vaults. op read and op run have no --vault flag; for those the vault is the first segment of the op:// reference.
  4. Never store secrets in files — use op run --env-file or op inject for templating.
  5. Don't bypass security hooks — if a hook blocks .1password/ paths, fix the approach (set SSH_AUTH_SOCK in shell profile, not per-command).
  6. 1Password's Secure AI access guidance: strip hardcoded secrets out of AI/MCP tool configs and let op run supply them at launch. See the MCP server pattern under Config File Patterns.

Read the full file on GitHub · 569 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 569 lines · 8,182 tokens per session scan B ca2cc3c74d4d

Subscribe to this mod's changes

1password is a cursor rule published in the GitHub repository petejm/1password-skill (4 stars, last pushed 24d ago), licensed Apache-2.0. It adds 8,182 tokens to every session, about $0.0409 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.