agentrigs
+ submit rig
~ / rigs / yiftahb / agsync

yiftahb/agsync

Agsync is a repo-native control plane for managing skills, MCP servers, secrets, and agent configs across AI clients like Claude Code and Cursor.

↗ GitHub ★ 10 MIT updated 12d ago project Codex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~1.2k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/yiftahb/agsync

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 yiftahb/agsync/.agsync/skills/agent-skills .claude/skills/agent-skills
$ npx degit yiftahb/agsync/.agsync/skills/agsync .claude/skills/agsync
$ npx degit yiftahb/agsync/.agsync/skills/context-manager .claude/skills/context-manager

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 (3)

agent-skillsagsynccontext-manager

Similar rigs

runpod/lazy-agent
Like LazyVim, but for terminal-based AI agent workflows. Get a beautiful, productive terminal setup in minutes.
★ 25 project Claude CodeCodex 13 skills 8mo ago
Skill Collector 5.2k tok ·
Mark393295827/third-brain-v7-skills
agent wiki +engineering skills
★ 138 collection Claude CodeCodexGemini CLI 21 skills 2mo ago
Skill Collector 2.4k tok ·
EAIconsulting/cowork-skills-library
21 Claude Cowork skills: beginner to power user in 18 minutes. Free forever. By Everyday AI.
★ 0 collection Claude Code 21 skills 6mo ago
Skill Collector 1.1k tok ·
Olatisunkanmi/claudefiles
—
★ 8 project Claude Code 41 skills 9 agents 18 hooks 6mo ago
Orchestrator 4.7k tok ·
copied ✓