agentrigs
+ submit rig
~ / rigs / libkim / agent-parity

libkim/agent-parity

One setup, four agents, identical behavior — cross-agent memory, skills, and instructions for Claude Code, Codex, Cursor, and Antigravity CLI

↗ GitHub ★ 5 MIT updated 1mo ago project Claude CodeCodexCursor
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~3.3k 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 libkim/agent-parity/.claude ./rig-agent-parity  # 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 libkim/agent-parity/.agents/skills/agent-parity .claude/skills/agent-parity
$ npx degit libkim/agent-parity/.agents/skills/motion-design .claude/skills/motion-design
$ npx degit libkim/agent-parity/.agents/skills/write-governance .claude/skills/write-governance
$ npx degit libkim/agent-parity/.agents/skills/write-requirement .claude/skills/write-requirement

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 *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
memory local / custom 2.5k

Skills (4)

agent-paritymotion-designwrite-governancewrite-requirement

Hooks (2)

eventmatcherruns
SessionStart*.agent-parity/bin/agent-parity sync-claude
SessionStart*.agent-parity/bin/agent-parity self-heal claude

Permissions

deny (0)
—
ask (0)
—
allow (6)
mcp__memory__memory_add
mcp__memory__memory_recent
mcp__memory__memory_search
mcp__memory__memory_get
mcp__memory__memory_update
mcp__memory__memory_governance

Similar rigs

GTKottman/mortiflix-oss
A motion design studio on your own machine: Claude makes the video step by step, you approve every stage. Bring your own Claude Code or API key.
★ 494 project Claude Code 9 skills 1d ago
Pragmatist 682 tok ·
designhouseme/AdvancedSkills
Teach your AI agent to build websites the way we do: research the company, plan, code, review, and kill the AI slop (bye-bye, gradient text).
★ 0 collection Claude Code 10 skills 7d ago
Skill Collector 786 tok ·
HAR5HA-7663/My_Claude_Setup
Full export of my Claude Code setup — settings, skills, agents, hooks, statusline, plugins, MCP configs + agent install instructions
★ 0 setup Claude Code 28 skills 3d ago
Skill Collector 7.5k tok ·
codemirket/harness
Reusable agent skills, project workflows and executable verification tools for Codex Desktop and Claude Desktop Code.
★ 0 setup Claude CodeCodex 2 mcp 43 skills today
Skill Collector 7.4k tok ·
copied ✓