chipi/agentic-ai-homelab
How I work with agentic AI: personal patterns, homelab infra (vLLM, Ollama, Grafana Alloy, LibreChat), project scaffolding. Not best practices - what I run.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/chipi/agentic-ai-homelab 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 chipi/agentic-ai-homelab/workstation/claude/skills/close-arc .claude/skills/close-arc $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/compose-check .claude/skills/compose-check $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/dgx-status .claude/skills/dgx-status $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/docs-preflight .claude/skills/docs-preflight $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/fleet-stats .claude/skills/fleet-stats $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/gpu-mode .claude/skills/gpu-mode $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/homelab-endpoint .claude/skills/homelab-endpoint $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/new-doc .claude/skills/new-doc $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/o11y-review .claude/skills/o11y-review $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/obs-boot .claude/skills/obs-boot $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/replay-proven-fix .claude/skills/replay-proven-fix $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/repro-first .claude/skills/repro-first $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/scoped-agents .claude/skills/scoped-agents $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/secrets-scan .claude/skills/secrets-scan $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/ship .claude/skills/ship $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/triage-fleet-review .claude/skills/triage-fleet-review $ npx degit chipi/agentic-ai-homelab/workstation/claude/skills/vllm-deploy .claude/skills/vllm-deploy
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (17)
Similar rigs
EricAndrechek/Pacer
Native macOS app for tracking Claude Code usage — tokens, cost, rate-limit pacing, per-project breakdowns. SwiftUI + SwiftData.
Pragmatist 16.3k tok ·
MahammadNuriyev62/dotfiles
Portable dev environment bootstrap with Claude Code settings, rules, hooks, and skills
Minimalist 1.4k tok ·
bobmcallan/satellites
Make AI coding agents follow your process: satellites gates every story transition through reviewer skills, so work can't reach 'done' by skipping steps. Config-over-code, repo-agnostic.
Automator 2.6k tok ·
cjos9/claude-setup
A Claude Code setup for Windows, macOS and Linux: global settings and instructions, plus the flow plugin with push and secret guards, a build check before Claude stops, notifications and shipping to pull or merge requests.
Minimalist 1.5k tok ·