Jai-Keshav-Sharma/chaperone
Open-source AI agent security gate: deterministic ALLOW/BLOCK/ESCALATE authorization before every tool call, plain-English policy compilation, tamper-evident audit ledger. MCP security gateway + Claude Code/Cursor guardrails. Rust, Apache-2
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit Jai-Keshav-Sharma/chaperone/.claude ./rig-chaperone # 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 Jai-Keshav-Sharma/chaperone/.agents/skills/design-taste-frontend .claude/skills/design-taste-frontend $ npx degit Jai-Keshav-Sharma/chaperone/.agents/skills/impeccable .claude/skills/impeccable $ npx degit Jai-Keshav-Sharma/chaperone/.agents/skills/karpathy-guidelines .claude/skills/karpathy-guidelines $ npx degit Jai-Keshav-Sharma/chaperone/.agents/skills/motion-framer .claude/skills/motion-framer
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (4)
Similar rigs
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Minimalist 723 tok · · Q3
madeinorbit/podium
Podium is an ADE with built-in cross-harness subagents and agent communication. It runs on desktop, mobile and VPS.
Pragmatist 2.6k tok · · Q38
swarmclawai/andrej-karpathy-skills
Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENTS.md or Agent Skills-compatible agent.
Pragmatist 3.1k tok · · Q3
Anmol-Srv/sigil
Persistent memory for AI coding agents. Local-first. MCP-native. Auto-captured from Claude Code, shared with Cursor, Codex, and any MCP client. Your agents don't remember what you decided yesterday. Sigil does. Every prompt, every session,
Minimalist 223 tok · · Q0