lokeshmohanty/nix
My NixOS Configuration
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/lokeshmohanty/nix 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 lokeshmohanty/nix/config/agentic-harness/agents/skills/axi-standards .claude/skills/axi-standards $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/chrome-devtools-axi .claude/skills/chrome-devtools-axi $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/context-manager .claude/skills/context-manager $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/context7-mcp .claude/skills/context7-mcp $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/docs-sync .claude/skills/docs-sync $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/gh-axi .claude/skills/gh-axi $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/harness-ops .claude/skills/harness-ops $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/lavish-axi .claude/skills/lavish-axi $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/no-mistakes .claude/skills/no-mistakes $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/test-driven-development .claude/skills/test-driven-development $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/ui .claude/skills/ui $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/verification-before-completion .claude/skills/verification-before-completion $ npx degit lokeshmohanty/nix/config/agentic-harness/agents/skills/webdev .claude/skills/webdev
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 (14)
Similar rigs
Viqto0r/zames_pro
Terminal coding agent that drives chat.deepseek.com or chat.qwen.ai through Playwright — no API key required. Reads/edits files, runs commands, commits to git.
Pragmatist 11.3k tok · · Q8
taiyyoson/my-claude-code
Version-controlled Claude Code setup with three working modes
Pragmatist 1.1k tok · · Q0
nicolasaudran/claude-dotfiles
—
Pragmatist 320 tok · · Q15
malkreide/claude-config
Personal Claude config: global CLAUDE.md, vendored Superpowers skills and helper scripts
Minimalist 1.0k tok · · Q0