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
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~36.8k 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> -- docker run -i --rm -e GITHUB_PERSONAL_ACCESS_<redacted> $ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ${workspaceFolder} $ claude mcp add fetch -- uvx mcp-server-fetch $ npx degit bradleybond512/crystal-ball/.claude ./rig-crystal-ball # 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> -- docker run -i --rm -e GITHUB_PERSONAL_ACCESS_<redacted> $ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ${workspaceFolder} $ claude mcp add fetch -- uvx mcp-server-fetch
$ npx degit bradleybond512/crystal-ball/.agents/skills/crystal-ball-feature-workflow .claude/skills/crystal-ball-feature-workflow $ curl -fsSL --create-dirs -o .claude/agents/cross-agent-reviewer.md https://raw.githubusercontent.com/bradleybond512/crystal-ball/main/.claude/agents/cross-agent-reviewer.md 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 |
|---|---|---|
| crystalball | local / custom | 2.5k |
| GitHub MCP · "github" env: GITHUB_PERSONAL_ACCESS_TOKEN | docker | 18.0k |
| Filesystem | npm | 4.2k |
| Fetch | pypi | 450 |
Skills (1)
Subagents (1)
| cross-agent-reviewer model: sonnet | Independent Claude review of a codex/* or copilot/* branch for the cross-agent gate. Use for every Claude cross-agent review; it always runs on Sonnet. |
Slash commands (8)
/alerts/correlate/market-pulse/sentinel/sitrep/threat-brief/watch/watchlist
Similar rigs
viehgroup/agentscan
Find leaked keys, risky permissions and hidden instructions in AI agent configs: Claude Code, Cursor, Copilot, Windsurf, Gemini CLI and MCP.
YOLO Cowboy 25.2k tok · · Q3
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
shriramkv/mcp-client-config-audit
Audits MCP client configs (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, goose) for risky server wiring like unpinned packages, leaked secrets, shell wrappers and unsafe containers, and grades each A-F with CI gates.
MCP Hoarder 40.6k tok · · Q3