OpenEval.Pinokio — Development skill for Claude Code
1-click Pinokio launcher for OpenEval — a local-first evaluation dashboard for agent CLIs.
How to install OpenEval.Pinokio
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open RasputinKaiser/OpenEval.Pinokio and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What OpenEval.Pinokio does
1-click Pinokio launcher for OpenEval — a local-first evaluation dashboard for agent CLIs.
Alternatives in Development
- IPolloWork — Enterprise-grade, local-first Agent Workbench for people and agent teams 4.9k ★
- Claude Usage — A local dashboard for tracking your Claude Code token usage, costs, and session history 864 ★
- Extension — Create, list, validate, and manage project-local Dashboard/TUI extensions and experiment registry objects 51 ★
README
OpenEval — 1-Click Pinokio Launcher
A one-click [Pinokio](https://pinokio.computer) launcher for **[OpenEval](https://github.com/RasputinKaiser/OpenEval)**, a local-first, harness-agnostic evaluation dashboard for agent CLIs.
OpenEval runs repeatable cases against agent harnesses (Claude Code, Codex, ncode, and any user descriptor under `harnesses/`), grades results with deterministic and rubric-based checks, persists run history to a local SQLite database, and turns everything into an operator-friendly Next.js dashboard. Your run history, transcripts, and stats stay on your own machine under `app/data/`.
What This Launcher Does
This launcher installs and runs OpenEval with a single click, so you don't have to clone the repo, install Node dependencies, or build and serve the app by hand.
- Install — clones the OpenEval repository into
app/, runsnpm install, and builds the production bundle (npm run build) so pages load fast at start time. - Start — serves the pre-built dashboard (
npm starton the next free port), waits for the local URL, and exposes an Open App button. All pages render per-request against your live local data — the production build doesn't make anything stale. - Update — pulls the latest launcher and app code, reinstalls dependencies, and rebuilds the production bundle.
- Reset — deletes the
app/folder to revert to a clean, pre-install state (removes cloned code, dependencies, and local run history).
Requirements
- Node.js 20+ (bundled/managed by Pinokio's environment).
- OpenEval is local-first and runs entirely on your machine. Optional LLM-judge and cost-estimation features use OpenRouter or a local CLI and are only active if you configure them inside the app's Settings.
How To Use
- Open this launcher in Pinokio.
- Click Install and wait for the clone + dependency install to finish.
- Click Start. When the server is ready, the sidebar shows an Open App button — click it to open t
Related Skills
Tokentelemetry Hermes Plugin
TokenTelemetry launcher tab inside Hermes Dashboard — local observability for Hermes Agent and 9 coding agents
Agentic OS Dashboard
Local cockpit for Claude Code usage — rate limits, activity chart, one-click skill buttons.
Agent Deck
Local web dashboard to orchestrate multiple Claude Code & OpenCode CLI sessions — real PTY terminals, persona
Jev Score
Local-first document evaluation workspaces powered by Jev
Agnt
Control coding-agent CLIs from your iPhone — Codex, Claude Code, opencode, and any other agent you plug in. ag
PrAImate
A terminal launcher for agent CLIs — Claude Code, Codex CLI, OpenCode, Gemini CLI, DeepSeek-TUI — that pairs e
Related Agents
CLI UX Tester
Expert UX evaluator for CLIs and developer APIs. Synthesizes pre-collected test data into an 11-criteria evalu
Phyll Reviewer
Fresh-eyes UX reviewer for apps built with AI. Walks the app as a first-time end user with Phyll's browser too
Dashboard Support
Support agent for the Agent Dashboard - guided install and setup diagnostics on the local machine, plus remote