agentrigs
+ submit rig
~ / rigs / kangarko / ai-files

kangarko/ai-files

A (very) opinionated senior engineers AI tweaks collection.

↗ GitHub ★ 6 no license updated 21d ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~3.9k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit kangarko/ai-files/skills ./rig-ai-files/skills

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 kangarko/ai-files/skills/copywriting .claude/skills/copywriting
$ npx degit kangarko/ai-files/skills/stop-slop .claude/skills/stop-slop
$ npx degit kangarko/ai-files/skills/strategic-thinking .claude/skills/strategic-thinking
$ npx degit kangarko/ai-files/skills/vscode-claude-thinking .claude/skills/vscode-claude-thinking

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 (4)

copywritingstop-slopstrategic-thinkingvscode-claude-thinking

Similar rigs

DesiRichDev/Claude-Cowork-Linkedin-X
Social content agent for LinkedIn and X. Drop in your brand config, research signals, write platform-native posts, review quality, push to Supabase. Built on Claude Code.
★ 2 project Claude CodeCodex 5 skills 7mo ago
Pragmatist 505 tok ·
cansitki/agentic-builder-workbench
Private starter operating system for agentic coding, Obsidian workflows, and secure vibe coding
★ 0 project Codex 9 skills 1mo ago
Pragmatist 8.1k tok ·
sami-abdul/claude-content-pipeline
Content Intelligence System for Claude Code. Skills, agents, and rules that mine real codebases to produce grounded social media content. Adapted from production agent infrastructure (claude-pre-dev-setup + agentic-org).
★ 1 project Claude Code 6 skills 5 agents 8mo ago
Orchestrator 3.0k tok ·
aigentcraft/claude-dotfiles
—
★ 0 setup Claude Code 13 skills 3 hooks today
Skill Collector 2.8k tok ·
copied ✓