# ai-setup: a set by caliber-ai-org

The caliber-ai-org/ai-setup repository on GitHub: 17 cards with a description and an install command. Inside: 8 rules, 8 skills and 1 plugin. They install into Claude Code, Codex and Cursor.

17 cards

- HTML: https://affpapa.org/en/nevibecode/by/caliber-ai-org/ai-setup
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [caliber-onboarding](https://affpapa.org/en/nevibecode/rules/caliber-onboarding.md) — rule · caliber-ai-org · Claude Code, Codex, Cursor +3 · ★ 1319 repo stars — caliber-onboarding — a rule for Claude Code and Codex that checks whether Caliber configs are synced before the agent responds to your first message.
- [llm-layer](https://affpapa.org/en/nevibecode/rules/llm-layer.md) — rule · caliber-ai-org · Claude Code, Codex, Cursor +3 · ★ 1319 repo stars — llm-layer pins the conventions for model-provider code: the LLMProvider interface, config lookup, seat-based handling and usage tracking.
- [testing](https://affpapa.org/en/nevibecode/rules/testing.md) — rule · caliber-ai-org · Claude Code, Codex, Cursor +3 · ★ 1319 repo stars — Defines Vitest testing patterns for Caliber, enforcing colocated test suites, environment isolation, and global LLM mocks.
- [caliber-conventions](https://affpapa.org/en/nevibecode/rules/caliber-conventions.md) — rule · caliber-ai-org · Claude Code, Codex, Cursor +3 · ★ 1319 repo stars — The caliber-conventions rule sets conventions for Caliber TypeScript CLI development.
- [testing-patterns](https://affpapa.org/en/nevibecode/rules/testing-patterns.md) — rule · caliber-ai-org · Claude Code, Codex, Cursor +3 · ★ 1319 repo stars — testing-patterns is a Claude Code rule for Vitest conventions: test locations, LLM mocks, and running a single spec.
- [scoring-patterns](https://affpapa.org/en/nevibecode/rules/scoring-patterns.md) — rule · caliber-ai-org · Claude Code, Codex, Cursor +3 · ★ 1319 repo stars — scoring-patterns defines coding rules for the src/scoring/** directory.
- [llm-patterns](https://affpapa.org/en/nevibecode/rules/llm-patterns.md) — rule · caliber-ai-org · Claude Code, Codex, Cursor +3 · ★ 1319 repo stars — The llm-patterns rule sets patterns for LLM providers in a project.
- [caliber-pre-commit](https://affpapa.org/en/nevibecode/rules/caliber-pre-commit.md) — rule · caliber-ai-org · Claude Code, Codex, Cursor +3 · ★ 1319 repo stars — caliber-pre-commit — a commit-time rule: it checks for the Caliber git hook and, when the hook is absent, syncs and stages your agent config files.
- [find-skills](https://affpapa.org/en/nevibecode/skills/caliber-ai-org-find-skills.md) — skill · caliber-ai-org · Claude Code, Codex, Cursor +4 · ★ 1319 repo stars — find-skills discovers community skills from the Caliber registry and installs them directly into your coding session.
- [save-learning](https://affpapa.org/en/nevibecode/skills/save-learning.md) — skill · caliber-ai-org · Claude Code, Codex, Cursor +4 · ★ 1319 repo stars — save-learning turns a user's lasting preferences into project learnings.
- [setup-caliber](https://affpapa.org/en/nevibecode/skills/setup-caliber.md) — skill · caliber-ai-org · Claude Code, Codex, Cursor +4 · ★ 1319 repo stars — setup-caliber walks a project through Caliber setup: installs the CLI, hooks agent config sync into every commit, and creates the config files your agents are missing.
- [adding-a-command](https://affpapa.org/en/nevibecode/skills/adding-a-command.md) — skill · caliber-ai-org · Claude Code, Codex, Cursor +4 · ★ 1319 repo stars — adding-a-command generates Commander.js CLI commands in src/commands/, connects them to src/cli.ts, and sets up telemetry tracking.
- [llm-provider](https://affpapa.org/en/nevibecode/skills/llm-provider.md) — skill · caliber-ai-org · Claude Code, Codex, Cursor +4 · ★ 1319 repo stars — The llm-provider skill guides you through adding an LLM backend to a project, from its provider class to configuration and factory registration.
- [scoring-checks](https://affpapa.org/en/nevibecode/skills/scoring-checks.md) — skill · caliber-ai-org · Claude Code, Codex, Cursor +4 · ★ 1319 repo stars — Adds deterministic scoring checks that measure AI agent config quality.
- [caliber-testing](https://affpapa.org/en/nevibecode/skills/caliber-testing.md) — skill · caliber-ai-org · Claude Code, Codex, Cursor +4 · ★ 1319 repo stars — caliber-testing is a Claude Code skill that generates Vitest tests with process.env resets, vi.hoisted mocks, and test files placed in __tests__ directories.
- [writers-pattern](https://affpapa.org/en/nevibecode/skills/writers-pattern.md) — skill · caliber-ai-org · Claude Code, Codex, Cursor +4 · ★ 1319 repo stars — The writers-pattern skill guides you through adding a module that writes agent config files for a new platform.
- [caliber-jev-compaction](https://affpapa.org/en/nevibecode/plugins/caliber-jev-compaction.md) — plugin · caliber-ai-org · Claude Code, Codex · ★ 1319 repo stars — caliber-jev-compaction compacts Claude Code sessions using TypeSafe's Jev model to score and drop stale tool calls instead of summarizing.

## Install the whole set (Claude Code / Skills CLI)

```bash
/plugin marketplace add caliber-ai-org/ai-setup
```

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
