ralis-ai/weir
Keep your sensitive credentials out of the agents you build and the coding agent you use. Test any agent with planted fake keys, or see which of your real keys a Claude Code session exposed.
stack: Python
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
GUARDRAILS
3/5
Protects secrets · No YOLO mode · Sandbox or ask-first rules · details
Quality 26/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit ralis-ai/weir/.claude ./rig-weir # 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.
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Read(~/.claude/**)",
"Read(~/.claude.json)",
"Read(~/.ssh/**)",
"Read(~/.aws/**)",
"Read(~/.config/gcloud/**)",
"Read(~/.netrc)",
"Read(~/.npmrc)",
"Read(~/.docker/config.json)",
"Read(~/.kube/**)",
"Read(~/.gnupg/**)",
"Edit(~/.claude/**)",
"Edit(~/.claude.json)",
"Edit(~/.ssh/**)",
"Edit(~/.aws/**)",
"Edit(~/.config/gcloud/**)",
"Edit(~/.netrc)",
"Edit(~/.npmrc)",
"Edit(~/.docker/config.json)",
"Edit(~/.kube/**)",
"Edit(~/.gnupg/**)"
]
},
"sandbox": {
"enabled": true
}
} Permissions
deny (20)
Read(~/.claude/**)
Read(~/.claude.json)
Read(~/.ssh/**)
Read(~/.aws/**)
Read(~/.config/gcloud/**)
Read(~/.netrc)
Read(~/.npmrc)
Read(~/.docker/config.json)
Read(~/.kube/**)
Read(~/.gnupg/**)
Edit(~/.claude/**)
Edit(~/.claude.json)
Edit(~/.ssh/**)
Edit(~/.aws/**)
Edit(~/.config/gcloud/**)
Edit(~/.netrc)
Edit(~/.npmrc)
Edit(~/.docker/config.json)
Edit(~/.kube/**)
Edit(~/.gnupg/**)
ask (0)
—
allow (0)
—
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
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Minimalist 554 tok · · Q3
github/spec-kit
💫 Toolkit to help you get started with SDD or any other process!
Minimalist 1.1k tok · · Q0
shareAI-lab/learn-claude-code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Minimalist 156 tok · · Q0