Vibemetric — AI skill for Claude Code
Mac app that scores how well you work with AI, from your local Claude Code and Codex history.
How to install Vibemetric
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open vibemetric-app/vibemetric and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Vibemetric does
Mac app that scores how well you work with AI, from your local Claude Code and Codex history.
Alternatives in AI
- Claude Squad — by smtg-ai - Claude Squad is a terminal app that manages multiple Claude Code, Codex (and other local agents i 6.5k ★
- Agentrq — AgentRQ: Human-in-loop realtime conversational task manager for AI Agents 1.1k ★
- Iai Personal Memory Engine — A cyber brain for your AI 866 ★
README
Vibemetric
A small native macOS app that scores **how well you work with AI**. It reads your local Claude Code and Codex history and returns an **AI Native Score** card: 10 dimensions scored 0–10, with evidence-based reasons, one improvement to make first, and a roadmap.
[](https://github.com/vibemetric-app/vibemetric/actions/workflows/ci.yml) [](LICENSE)
This repository is the complete free app, open source under the [MIT license](LICENSE). Scoring runs on your Mac with your own Claude Code or Codex CLI.
**Pro features** (deep dives, Pro Reviews, recommendations) use Vibemetric's hosted service and are available only in the official app from [vibemetric.app](https://vibemetric.app). Builds from source include the complete free app.
**Trademark:** the code is open source; the Vibemetric name and logo are not. Forks must use a different name and icon.
Installation
Requirements
**macOS 14 Sonoma or later**, on Apple Silicon or Intel.
**Claude Code or Codex CLI, installed and signed in.** Choose the scoring engine on the first-assessment screen or in **Settings → Scoring engine**. Both engines assess Claude Code and Codex history, using your selected engine’s account and plan or API credits.
- Claude Code: check
claude --version, then runclaudeto sign in. - Codex CLI: check
codex --version, then runcodex login. Use a version that supportsexec forkand--ignore-user-config --ignore-rules --strict-config --output-schema; Vibemetric checks these capabilities and selects the newest working installation, including the CLI bundled with the ChatGPT desktop app. On 2026-09-30, GPT-6 Sol worked with the bundled 0.158.0-alpha.2.1 CLI; the older npm 0.145.0 installation rejected the same request.
- Claude Code: check
**Some Claude C
Related Skills
Dev Report Weekly
Local-first desktop app that turns reviewed Git history into auditable weekly reports with Codex, Claude Code,
Open Dot
Open-source personal AI agents that work on their own, on their own computers. Mac app, OpenAI + Composio.
Imessage MCP CLI
iMessage MCP server and CLI for Claude Code, Codex and AI agents on a Mac. 10 tools for an inbox that survives
Dettivo Linux
Private, offline speech-to-text for Linux: push-to-talk dictation into any app, meeting transcription with spe
Self Learning Design Library
Retrieval library for LLM-assisted design work: distilled designer style profiles, universal principles, and p
Mac Agent Monitor App
MAC版灵动岛--Agent运行监测:本地查看 Codex、Claude Code、VS Code 等 AI Agent 的运行状态、工作时长、对话与 Token 用量。
Related Agents
Bonsai
Runs a task on the local Bonsai 2 27B model (PrismML ternary 27B, MLX, on this Mac) and returns its answer. Us
Work Reviewer
Reads one local repo clone's RECENT git history (since a given commit) and clusters what landed into 1-3 thema
Civitai Intent Review
Scores a feature segment in the main Civitai Next.js app (src/) against the intent doc for the work — did the