Agent skill · software engineering · mvanhorn
pp-openrouter
The only OpenRouter CLI built for fleet operations: budgets, anomaly alarms, and failover maps over a local usage ledger — not another chat wrapper. Trigger phrases: `which model is cheapest for this task`, `what did my crons spend on openrouter`, `check openrouter credits runway`, `is openrouter degraded right now`, `why did my openrouter cost spike`, `use openrouter`, `run openrouter`.
Why this skill is useful
Adds executable commands for OpenRouter introspection and cost analysis that enhance AI agent capabilities beyond standard knowledge.
What it needs
Requires openrouter-pp-cli installed locally. About 11k tokens when loaded. Last updated 2026-08-06. 1,890 stars on the source repository.
What this skill does
OpenRouter — Printing Press CLI Prerequisites: Install the CLI This skill drives the openrouter-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: openrouter-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 before this CLI has a public-library category, install Node or use the category-specific Go fallback after publish. 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. Every other OpenRouter tool wraps chat; this one governs it. A synced local mirror of models, generations, and credits powers per-cron cost attribution (usage cost-by), pre-flight budget gates (budget check), degradation watches (providers degraded), and runway projections (credits runway) that no single API call can answer. The full endpoint surface — catalog, keys admin, activity, analytics — ships alongside as typed commands. When to Use This CLI Reach for this CLI when the task is operating LLM workloads over OpenRouter: attributing spend to crons or agents, gating scheduled runs on budgets, shortlisting models by capability and price, watching provider health before dispatch, or projecting credit and cap runway. It is the right tool whenever the question spans local history plus the API — anything a single raw HTTP call cannot answer. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills mvanhorn/openrouter