agentleFS
OpenCovenOpenCoven/coven/skills/1password/SKILL.md

1password

Skill75 starsChanged 4 months agoMITView on GitHub

Manage secrets via 1Password CLI (op). Read, create, and inject secrets. Provides whitelisted access for other skills (ask-curl, GitHub, etc.) via op:// secret references and 1Password Environments.

  • Reads credentials
  • Installs packages

43 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use openclaw-performance, plugin-sdk-impact and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • clawdbotSkill

    openclaw-performance

    Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.

    Also in 7 projects that use this

  • clawdbotSkill

    plugin-sdk-impact

    Count Plugin SDK consumers across live ClawHub releases and bundled OpenClaw plugins before deprecation, removal, or behavior changes; supports public release-date filters.

    Also in 7 projects that use this

  • hkyutongSkill

    node-connect

    Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

    Also in 18 projects that use this

  • molt-botSkill

    discord-e2e

    Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.

    Also in 10 projects that use this

  • molt-botSkill

    openclaw-repair-sweep

    Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

    Also in 10 projects that use this

  • AtomicBot-aiSkill

    taskflow-inbox-triage

    Also in 6 projects that use this

  • +2 more from molt-bot

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 43 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Create env files with op:// references — secrets are resolved at runtime, never stored on disk.

    line 58
  2. Very specific:

    Always use --vault: when creating items to avoid putting secrets in the wrong vault

    line 138

“Common” is measured: kept by at least 6 in 10 of the 43 edited versions of this file we could read. “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

1Password Secret Management

Securely store and retrieve secrets. Never expose them in chat, logs, or files.

Prerequisites

  • op CLI installed: brew install --cask 1password-cli
  • Signed in: op signin (or service account via OP_SERVICE_ACCOUNT_TOKEN)
  • For biometric unlock: enable in 1Password desktop app → Settings → Developer → CLI integration

Core Commands

Read a secret

op read "op://VaultName/ItemName/FieldName"

List vaults

op vault list --format json | jq '.[].name'

List items in a vault

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

Create an item

op item create \
  --category login \
  --vault "Development" \
  --title "Service API Key" \
  --field "credential=secret_value_here"

Search items

op item list --format json | jq '.[] | select(.title | test("github"; "i"))'

Environment Files (Secret References)

Create env files with op:// references — secrets are resolved at runtime, never stored on disk.

Setup for ask-curl

mkdir -p ~/.config/ask-curl

# Create env file with secret references (NOT actual secrets)
cat > ~/.config/ask-curl/env.curl << 'ENV'
GITHUB_TOKEN=op://Development/GitHub PAT/credential
OPENAI_API_KEY=op://Development/OpenAI/api key
SLACK_WEBHOOK=op://Development/Slack Webhook/url
ENV

Use with op run

# Inject secrets from env file into a command
op run --env-file=~/.config/ask-curl/env.curl -- curl -s \
  -H "Authorization: Bearer $GITHUB_TOKEN" \
  "https://api.github.com/user"

# Inject secrets into any command
op run --env-file=~/.config/ask-curl/env.curl -- node script.js

Skill Whitelisting

Control which skills can access which secrets by using separate env files per skill:

~/.config/ask-curl/env.curl       # HTTP/API secrets for ask-curl
~/.config/github/env.gh           # GitHub-specific secrets
~/.config/openclaw/env.gateway    # Gateway/infra secrets

Each env file contains only the op:// references that skill needs — principle of least privilege.

Register a new secret for a skill

# 1. Store the secret in 1Password
op item create --vault "Development" --category login \
  --title "New Service" --field "api_key=<secret-value>"

# 2. Add the reference to the skill's env file
echo 'NEW_SERVICE_KEY=op://Development/New Service/api_key' >> ~/.config/ask-curl/env.curl

1Password Environments (Teams/Pro)

For team workflows, use 1Password Environments instead of local env files:

# List environments
op environment list

# Run with an environment
op run --environment "Production" -- ./deploy.sh

Service Accounts (Automation)

For unattended/cron usage where biometric auth isn't available:

# Create a service account (one-time, from 1Password web)
# Then set the token:
export OP_SERVICE_ACCOUNT_TOKEN="ops_..."

# Now op commands work without interactive auth
op read "op://AutomationVault/Deploy Key/credential"

Safety Rules

  1. NEVER display secret values — use op read only in subshells or pipes
  2. NEVER store secrets in files — only op:// references in env files
  3. NEVER commit env files with real secrets — only op:// refs are safe to commit
  4. Always use --vault when creating items to avoid putting secrets in the wrong vault
  5. Verify before creating — op item list --vault X to check for duplicates first
  6. Use separate vaults for different trust levels (Development, Production, Personal)

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.