#228228th of 324 in Skills, plugins and prompts
ai-setup
CLI that generates and syncs context files across coding agents
- Stars
- 1.3k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Sep 2026
- Language
- TypeScript
519 on 3 Apr 20261,310 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Caliber is a Node CLI that writes and maintains CLAUDE.md, Cursor rules, AGENTS.md and Copilot instructions for a repo. A pre-commit hook refreshes them from your diff, and `caliber sync` mirrors skills, rules, plugins and MCP config between agents. It also ships a Claude Code plugin and a CLI command for Jev compaction, which replaces `/compact` with per-tool-call scoring.
Who it is for: Developers using several coding agents on one repo
Strengths
- `caliber score` audits context files against the repo without an LLM
- Sync is deterministic and never overwrites files you edited by hand
- Every write is shown as a diff and backed up to .caliber/backups/
- Covers Claude Code, Cursor, Codex, OpenCode and GitHub Copilot
Weaknesses
- Jev compaction needs a Vercel AI Gateway or TypeSafe API key
- Anonymous usage analytics are on by default; opt out via env var
- Setup and refresh need an agent seat or your own LLM API key
- On agents lacking a feature, sync degrades, e.g. skills become Copilot instruction files
What it needs
- no GPU
- Needs Node 20+, Claude Code or Cursor seat, or Anthropic/OpenAI/MiniMax/Vertex key, Vercel AI Gateway or TypeSafe key (Jev compaction only)
- Models: Anthropic, OpenAI, MiniMax, Vertex
Quick answers
Is ai-setup open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |