bayanovea/ai-setup
My Claude Code setup: global rules, hooks, skills and templates, symlinked into ~/.claude.
stack: Shell
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
$ git clone --depth 1 https://github.com/bayanovea/ai-setup 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 bayanovea/ai-setup/claude/skills/backlog-parallel .claude/skills/backlog-parallel $ npx degit bayanovea/ai-setup/claude/skills/english-prompt .claude/skills/english-prompt $ npx degit bayanovea/ai-setup/claude/skills/english-review .claude/skills/english-review $ npx degit bayanovea/ai-setup/claude/skills/make-text-not-ai .claude/skills/make-text-not-ai $ npx degit bayanovea/ai-setup/claude/skills/memory-audit .claude/skills/memory-audit $ npx degit bayanovea/ai-setup/claude/skills/perf-review-log .claude/skills/perf-review-log $ npx degit bayanovea/ai-setup/claude/skills/save-clear .claude/skills/save-clear $ npx degit bayanovea/ai-setup/claude/skills/split-branch-for-review .claude/skills/split-branch-for-review $ npx degit bayanovea/ai-setup/claude/skills/unit-test-writer .claude/skills/unit-test-writer
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 (9)
Similar rigs
baberarjumand/agentic_markdown_memory_agent-skill
An agent skill that sets up a markdown memory layout for agents. The layout keeps a short always-on file and loads everything else only when a task needs it.
Minimalist 186 tok · · Q0
himkt/config
🪄 Dotfiles, claude code configs, and system settings for macOS & Linux, which makes everyday software development fun!
Pragmatist 3.8k tok · · Q5
Dataojitori/nocturne_memory
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for
Pragmatist 148 tok · · Q0
shawnlu96/claudestra
Run your coding agents — Claude Code and Pi — on your workstation and drive them from your phone: a self-hosted PWA web client (Discord optional), every session in tmux.
Orchestrator 7.5k tok · · Q10