Skip to content
Back to search

ai-setup

Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/caliber-ai-org--ai-setup/badge.svg)](/listings/caliber-ai-org--ai-setup)

HTML

<a href="/listings/caliber-ai-org--ai-setup"><img src="/api/listings/caliber-ai-org--ai-setup/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "caliber",
  3. "owner": {
  4. "name": "Caliber",
  5. "url": "https://github.com/caliber-ai-org/ai-setup"
  6. },
  7. "plugins": [
  8. {
  9. "name": "caliber-jev-compaction",
  10. "source": "./plugin/caliber-jev-compaction",
  11. "description": "Verbatim Jev-guided compaction for Claude Code sessions — scores tool calls with TypeSafe's Jev model and drops stale ones instead of summarizing.",
  12. "version": "0.3.0",
  13. "license": "MIT"
  14. }
  15. ]
  16. }
README.md · README · 94 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="assets/readme/logo.png" alt="Caliber" width="120">
  3. </p>
  4. <p align="center"><b>The open-source context layer for coding agents.</b><br>
  5. Claude Code · Cursor · Codex · OpenCode · GitHub Copilot</p>
  6. <p align="center">
  7. <a href="https://www.npmjs.com/package/@rely-ai/caliber"><img src="https://img.shields.io/npm/v/@rely-ai/caliber?style=flat-square&color=14121A&labelColor=F7EFDC&label=npm" alt="npm version"></a>
  8. <a href="./LICENSE"><img src="https://img.shields.io/npm/l/@rely-ai/caliber?style=flat-square&color=14121A&labelColor=F7EFDC" alt="MIT license"></a>
  9. <a href="https://nodejs.org"><img src="https://img.shields.io/node/v/@rely-ai/caliber?style=flat-square&color=14121A&labelColor=F7EFDC" alt="Node version"></a>
  10. </p>
  11. <p align="center">
  12. <img src="assets/readme/pillars.png" alt="01 Fresh: context that follows the code. 02 Shared: write a skill once, every agent has it. 03 Lean: compact without summarizing." width="900">
  13. </p>
  14. ## Start
  15. ```bash
  16. npx @rely-ai/caliber bootstrap
  17. ```
  18. Then, in Claude Code or the Cursor CLI, run `/setup-caliber`. Your agent writes `CLAUDE.md`, Cursor rules, `AGENTS.md` and Copilot instructions, shows you the diff, and installs the hooks that keep them current. No agent handy? `caliber init` does the same as a wizard.
  19. Node 20+. Runs on your Claude Code or Cursor seat, or your own Anthropic, OpenAI, MiniMax or Vertex key. Bootstrap, scoring and sync run fully local.
  20. ## Fresh
  21. A pre-commit hook reads your diff and refreshes the context files your agents read. `caliber score` checks them against the repo, with no LLM: do the paths exist, are the commands real, has anything drifted.
  22. ```bash
  23. caliber score --compare main
  24. ```
  25. ## Shared
  26. Write a skill, rule, plugin or MCP server in one agent and `caliber sync` puts it in every other one. It's deterministic, degrades where an agent lacks a feature (a skill becomes a Copilot instruction file), and never overwrites a file you edited by hand.
  27. ```bash
  28. caliber sync --status
  29. ```
  30. ## Lean: Jev compaction <sup>new</sup>
  31. <p align="center">
  32. <img src="assets/readme/jev.png" alt="Built-in /compact turns the session into a lossy paragraph. Jev scores each tool call, drops the stale ones and keeps every message verbatim." width="900">
  33. </p>
  34. `/compact` summarizes, and summaries forget the file path, the error and the constraint you gave an hour ago. [TypeSafe's](https://typesafe.ai) Jev scores every tool call, drops the stale ones, and keeps everything else byte-for-byte.
  35. **Claude Code:** a plugin that replaces `/compact`.
  36. ```bash
  37. export CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1
  38. export AI_GATEWAY_API_KEY=... # or TYPESAFE_API_KEY
  39. claude plugin marketplace add caliber-ai-org/ai-setup
  40. claude plugin install caliber-jev-compaction@caliber
  41. ```
  42. **Cursor, Codex and any other agent:** the same scoring from the CLI.
  43. ```bash
  44. caliber compact --provider cursor --transcript <jsonl>
  45. caliber compact --provider generic --transcript ./session.json --write
  46. ```
  47. Bring your own Vercel AI Gateway or TypeSafe key. If Jev is unavailable, Claude Code falls back to its built-in compaction. Setup and verification: [`FUNCTIONAL_CHECKLIST.md`](FUNCTIONAL_CHECKLIST.md).
  48. ## Commands
  49. | Command | |
  50. |---|---|
  51. | `caliber bootstrap` / `init` | Set up (agent skill or CLI wizard) |
  52. | `caliber score` | Audit config quality, no LLM |
  53. | `caliber refresh` | Update configs from recent changes |
  54. | `caliber sync` | Mirror skills, rules, plugins and MCP across agents |
  55. | `caliber compact` | Jev compaction report (`--write` for generic transcripts) |
  56. | `caliber plugin install` | Install the Jev plugin into this project |
  57. | `caliber learn` | Learn patterns from your sessions into `CALIBER_LEARNINGS.md` |
  58. | `caliber hooks` | Manage refresh and sync hooks |
  59. | `caliber config` | Choose provider, key and model |
  60. | `caliber undo` / `uninstall` | Revert changes / remove everything Caliber added |
  61. Every write is shown as a diff first and backed up to `.caliber/backups/`. Anonymous usage analytics (command names, never code) can be turned off with `CALIBER_TELEMETRY_DISABLED=1`.
  62. ## Contributing
  63. ```bash
  64. git clone https://github.com/caliber-ai-org/ai-setup.git && cd ai-setup
  65. npm install && npm run test
  66. ```
  67. See [CONTRIBUTING.md](./CONTRIBUTING.md). MIT licensed.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.