agentrigs
+ submit rig
~ / rigs / hotovo / aider-desk

hotovo/aider-desk

Platform for AI-powered software engineers

↗ GitHub ★ 1,446 apache-2.0 updated 8d ago project Codex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~2.2k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/hotovo/aider-desk

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 hotovo/aider-desk/.aider-desk/skills/theme-factory .claude/skills/theme-factory
$ npx degit hotovo/aider-desk/.aider-desk/skills/writing-tests .claude/skills/writing-tests
$ npx degit hotovo/aider-desk/resources/skills/agent-creator .claude/skills/agent-creator
$ npx degit hotovo/aider-desk/resources/skills/extension-creator .claude/skills/extension-creator

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)

theme-factorywriting-testsagent-creatorextension-creator

Similar rigs

alexpricedev/Billet
⚒️ Guardrails for your AI coding agents — a full-stack TypeScript starter on Bun
★ 3 project Claude Code 4 skills 1 hooks today
Pragmatist 6.0k tok ·
wondping0/wondev
Write your AI agent knowledge once. Compile it to every agent config format - CLAUDE.md, AGENTS.md, .cursor/rules and more.
★ 0 project Claude Code 6 skills 8d ago
Pragmatist 229 tok ·
anilcancakir/claude-code
Claude Code plugin that plans before it edits: interview-driven plans on disk, steps routed to haiku/sonnet/opus by cost, four-layer verification per wave, and a read-only gate for autonomous runs.
★ 3 project Claude Code 1 mcp 9 skills 16d ago
Pragmatist 2.9k tok ·
AYESHAKHAN101/personal-ai-employee
Personal AI Employee – Bronze Tier autonomous AI system that monitors files, extracts tasks, and executes workflows using Claude Code skills.
★ 1 project Claude Code 13 skills 7mo ago
Skill Collector 5.8k tok ·
copied ✓