Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From op-remote
Guides usage of the op-remote MCP server for running commands with 1Password secrets. Triggers when op-remote:request_token tool is available, when running commands that need secrets from .env.tpl, or when encountering "op-remote", "secret access", "op://".
npx claudepluginhub wyattjoh/claude-code-marketplace --plugin op-remoteHow this skill is triggered — by the user, by Claude, or both
Slash command
/op-remote:op-remoteThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run commands with 1Password secrets injected via Telegram-approved access.
Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Breaks plans, specs, or PRDs into thin vertical-slice issues on the project issue tracker using tracer bullets. Useful for converting high-level work into grabbable implementation tickets.
Share bugs, ideas, or general feedback.
Run commands with 1Password secrets injected via Telegram-approved access. Secrets never enter your context. You see tokens and masked output only.
When you need to run a command that requires secrets from a .env.tpl file:
op-remote:request_token MCP tool (no arguments){"token": "...", "sock": "..."}op-remote run \
--token=<token> \
--sock=<sock> \
--env-file=.env.tpl \
--reason="<explain why you need to run this command>" \
-- <command and args>
--reason FlagAlways provide a clear, specific reason. The user sees this on their phone and uses it to decide whether to approve. Good reasons:
Bad reasons:
The op-remote:request_token tool returns this when the user tapped Stop in Telegram. You must immediately stop what you are doing and wait for the user to give you further instructions. Do not retry, do not attempt workarounds.
The user denied the request. Read the reason they provided. It may contain instructions (e.g., "don't run tests right now, focus on the linting issues instead"). Adjust your approach accordingly.
The user didn't respond within the timeout window. They may be unavailable. Wait and ask the user if they'd like you to retry.
op-remote:resumeOnly call this when the user explicitly asks you to resume after a stop. Do not call it on your own initiative. It requires Telegram approval.
op-remote:disable_auto_approveOnly call this when the user explicitly asks to disable auto-approval. This re-enables per-request Telegram approval for subsequent commands.
op-remote runop-remote:resume without explicit user instructionop-remote:disable_auto_approve without explicit user instruction--reason flag is visible to the user; be honest about what you are doing and why