agentrigs
+ submit rig
~ / rigs / haekal-alg / dotfiles

haekal-alg/dotfiles

my dotfiles with claude-assisted installation

↗ GitHub ★ 0 no license updated 4d ago personal setup Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~420 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit haekal-alg/dotfiles/.claude ./rig-dotfiles  # 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.

$ npx degit haekal-alg/dotfiles/.claude/skills/generate-prd .claude/skills/generate-prd
$ npx degit haekal-alg/dotfiles/.claude/skills/generate-specs .claude/skills/generate-specs
$ npx degit haekal-alg/dotfiles/.claude/skills/generate-user-stories .claude/skills/generate-user-stories
$ npx degit haekal-alg/dotfiles/.claude/skills/install .claude/skills/install
$ npx degit haekal-alg/dotfiles/.claude/skills/talk-to-me-im-human .claude/skills/talk-to-me-im-human

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "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(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (5)

generate-prdgenerate-specsgenerate-user-storiesinstalltalk-to-me-im-human

Similar rigs

agenticmail/agenticmail
Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and place agent-driven outbound voice calls, all programmatically
★ 235 project Claude CodeCodex 3 skills 8d ago
Pragmatist 10.2k tok ·
keshrath/agent-discover
MCP server registry and marketplace — discover, install, activate, and manage MCP tools on demand
★ 7 project Claude Code 1 mcp 2 skills today
Pragmatist 4.7k tok ·
Cherwayway/agent-context-patch
Turn recurring Claude Code and OpenAI Codex mistakes into durable, reviewable workspace memory with safe local context patches.
★ 2 project Codex 3 skills today
Minimalist 562 tok ·
CodeShuX/tokenwise
Cut Claude Code spend without sacrificing quality — and prove it. Haiku/Sonnet/Opus router with real $-saved numbers, not vibes.
★ 1 project Claude Code 5 skills 5mo ago
Pragmatist 386 tok ·
copied ✓