Agent skill · mvanhorn
pp-rightbrain
The first Rightbrain CLI that reaches past tasks — agents, approvals, evals, triggers and audit, plus a local mirror that makes credit spend and latency regressions queryable. Trigger phrases: `is it safe to promote this revision`, `which agent runs are waiting for approval`, `what got slower or more expensive this week`, `why was this agent run slow`, `what changed in the project this week`, `check the rightbrain rollout split`, `use rightbrain`, `run rightbrain`.
What it needs
About 11k tokens when loaded.
What this skill does
Rightbrain — Printing Press CLI Prerequisites: Install the CLI This skill drives the rightbrain-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first: 1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows: 2. Verify: rightbrain-pp-cli --version 3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill. If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.5 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead: If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds. Rightbrain's own CLI covers login and task CRUD; the rest of the platform has no command line at all. This one exposes the whole user-reachable API surface, resolves your org and project from config so you never paste two UUIDs into a command, and mirrors runs into SQLite so the questions the API can only answer one page at a time — which revision is actually serving traffic, what got slower this week, which agent runs are parked awaiting approval — become single commands. When to Use This CLI Reach for this CLI when you are operating Rightbrain in production rather than building against it for the first time. It is the right tool for promoting a task revision behind an eval gate, checking whether an A/B split is really splitting, sweeping for agent runs parked awaiting human approval, tracing why one agent run was slow, and answering week-over-week cost and latency questions across every task in a project. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills mvanhorn/rightbrain