agentrigs
+ submit rig
~ / rigs / panakh / agentic-os

panakh/agentic-os

A working agentic setup for Claude Code in one command: starter workspace, protocol skills, self-running routines, local Studio dashboard.

↗ GitHub ★ 2 MIT updated 3mo ago project Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.5k tokens
Featherweight · 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 panakh/agentic-os/.claude ./rig-agentic-os  # 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 panakh/agentic-os/.claude/skills/agent-protocol .claude/skills/agent-protocol
$ npx degit panakh/agentic-os/.claude/skills/inbox .claude/skills/inbox
$ npx degit panakh/agentic-os/.claude/skills/llm-wiki .claude/skills/llm-wiki
$ npx degit panakh/agentic-os/.claude/skills/memory-sync .claude/skills/memory-sync
$ npx degit panakh/agentic-os/.claude/skills/project-management .claude/skills/project-management
$ npx degit panakh/agentic-os/.claude/skills/self-learning .claude/skills/self-learning
$ npx degit panakh/agentic-os/.claude/skills/session-persist .claude/skills/session-persist
$ npx degit panakh/agentic-os/.claude/skills/wikify .claude/skills/wikify

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 (8)

agent-protocolinboxllm-wikimemory-syncproject-managementself-learningsession-persistwikify

Hooks (3)

eventmatcherruns
SessionStart*"$CLAUDE_PROJECT_DIR/.claude/hooks/enforce-skills.sh"
UserPromptSubmit*"$CLAUDE_PROJECT_DIR/.claude/hooks/enforce-skills-prompt.sh"
Stop*"$CLAUDE_PROJECT_DIR/.claude/hooks/persist-stop.sh"

Similar rigs

Kulaxyz/self-learning-skills
A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable skill/rule for next time.
★ 954 collection CodexCursor 1 skills 25d ago
Minimalist 1.5k tok ·
praneybehl/llm-wiki-plugin
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
★ 102 collection Codex 1 skills 26d ago
Minimalist 259 tok ·
tudoumashu/ai-memory-skillpack
Bounded project-memory skills for Codex CLI and Claude Code.
★ 445 project Claude Code 3 skills 1mo ago
Minimalist 260 tok ·
ychampion/claude-self-learning
A Claude Code self learning plugin that autonomously researches any technology and generates reusable SKILL.md files with installation guides, code examples, and best practices.
★ 3 project Claude Code 1 skills 2 agents 8mo ago
Pragmatist 252 tok ·
copied ✓