caliber-ai-org/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.
ARCHETYPE
Automator
Hooks on every lifecycle event: format, lint, notify, log.
Copy this rig
# review before running: this installs third-party code
$ npx degit caliber-ai-org/ai-setup/.claude ./rig-ai-setup # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit caliber-ai-org/ai-setup/.agents/skills/adding-a-command .claude/skills/adding-a-command $ npx degit caliber-ai-org/ai-setup/.agents/skills/caliber-testing .claude/skills/caliber-testing $ npx degit caliber-ai-org/ai-setup/.agents/skills/find-skills .claude/skills/find-skills $ npx degit caliber-ai-org/ai-setup/.agents/skills/llm-provider .claude/skills/llm-provider $ npx degit caliber-ai-org/ai-setup/.agents/skills/save-learning .claude/skills/save-learning $ npx degit caliber-ai-org/ai-setup/.agents/skills/scoring-checks .claude/skills/scoring-checks $ npx degit caliber-ai-org/ai-setup/.agents/skills/setup-caliber .claude/skills/setup-caliber $ npx degit caliber-ai-org/ai-setup/.agents/skills/writers-pattern .claude/skills/writers-pattern
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (8)
adding-a-commandcaliber-testingfind-skillsllm-providersave-learningscoring-checkssetup-caliberwriters-pattern
Hooks (8)
| event | matcher | runs |
|---|---|---|
| SessionEnd | * | caliber refresh --quiet |
| SessionEnd | * | caliber learn finalize --auto |
| PostToolUse | * | caliber learn observe |
| PostToolUseFailure | * | caliber learn observe --failure |
| UserPromptSubmit | * | caliber learn observe --prompt |
| Stop | * | "$CLAUDE_PROJECT_DIR/.claude/hooks/caliber-check-sync.sh" |
| SessionStart | * | "$CLAUDE_PROJECT_DIR/.claude/hooks/caliber-session-freshness.sh" |
| Notification | * | "$CLAUDE_PROJECT_DIR/.claude/hooks/caliber-freshness-notify.sh" |
Cursor rules (5)
caliber-conventions · alwayscaliber-learnings · alwayscaliber-pre-commit · alwaysllm-layertesting
Permissions
deny (0)
—
ask (0)
—
allow (3)
Bash(git *)
Bash(npm run *)
Bash(npx *)
Similar rigs
Leon-Drq/openagentskill
The skill layer for AI agents: npm for AI Agent Skills.
Minimalist 610 tok ·
axeldelafosse/loop
Dead-simple Bun CLI that runs Codex and Claude Code in a loop.
Minimalist 872 tok ·
charanganesh/dotfiles
My personal dotfiles — zsh, git, Ghostty, and Claude Code config
Minimalist 411 tok ·
superagent-ai/grok-cli
An open-source coding agent for the Grok API
Minimalist 1.9k tok ·