viehgroup/agentscan
Find leaked keys, risky permissions and hidden instructions in AI agent configs: Claude Code, Cursor, Copilot, Windsurf, Gemini CLI and MCP.
stack: Python
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
CONTEXT TAX · EVERY TURN
up to ~25.2k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github $ claude mcp add --transport http internal-api http://mcp.example.internal/sse -H 'Authorization: YOUR_VALUE' $ claude mcp add fetch -- uvx mcp-server-fetch $ claude mcp add pinned -- npx -y @modelcontextprotocol/server-filesystem@2025.8.21 . $ npx degit viehgroup/agentscan/examples/demo/.claude ./rig-agentscan # 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.
$ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github $ claude mcp add --transport http internal-api http://mcp.example.internal/sse -H 'Authorization: YOUR_VALUE' $ claude mcp add fetch -- uvx mcp-server-fetch $ claude mcp add pinned -- npx -y @modelcontextprotocol/server-filesystem@2025.8.21 .
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 *)"
]
}
} MCP servers (4)
| server | source | est. tokens |
|---|---|---|
| GitHub MCP · "github" env: GITHUB_PERSONAL_ACCESS_TOKEN | npm | 18.0k |
| mcp.example.internal · "internal-api" | remote · remote | 2.5k |
| Fetch | pypi | 450 |
| Filesystem · "pinned" | npm | 4.2k |
Cursor rules (1)
style
Permissions
deny (0)
—
ask (0)
—
allow (3)
Bash(npm test:*)
Bash(curl:*)
Bash
Similar rigs
bradleybond512/crystal-ball
Tauri 2 desktop intelligence platform — Cesium.js 3D globe, 185 live panels, MCP server for Claude Code, and an explainable algorithm intelligence layer (truth scoring, evidence graph, compound risk, forecast calibration) plus shortage / we
Pragmatist 36.8k tok · · Q25
floating-astronaut/vibe-coding-kit
Replace your dev team: an operating system for a coordinated Claude Code, Codex and Kimi AI coding team. Docs-first lanes, zero-drift handoffs. MIT.
Pragmatist 22.8k tok · · Q5
haritzloza/nebula
Personal Hyprland dotfiles for CachyOS — gaming, dev, and an embedded Claude AI widget
Pragmatist 25.6k tok · · Q21
xudipta/cookbook
A CI-validated cookbook of infrastructure & tooling notes — Kubernetes, Docker, Linux, Terraform, CI/CD, Agent Skills, and MCP — where every note ships with a runnable, automatically checked example.
Pragmatist 24.7k tok · · Q0