~ / rigs / mgtechgroup / lyra-lynx-mythonexus

mgtechgroup/lyra-lynx-mythonexus

Hybrid knowledge base + dotfiles + Claude Code plugin — growing hive of agents with 14-day capability-building cycles

↗ GitHub ★ 0 MIT updated 8d ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.0k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit mgtechgroup/lyra-lynx-mythonexus/agents ./rig-lyra-lynx-mythonexus/agents
$ npx degit mgtechgroup/lyra-lynx-mythonexus/commands ./rig-lyra-lynx-mythonexus/commands

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.

$ curl -fsSL --create-dirs -o .claude/agents/repo-installer.md https://raw.githubusercontent.com/mgtechgroup/lyra-lynx-mythonexus/main/agents/repo-installer.md
$ curl -fsSL --create-dirs -o .claude/agents/security-gatekeeper.md https://raw.githubusercontent.com/mgtechgroup/lyra-lynx-mythonexus/main/agents/security-gatekeeper.md
$ curl -fsSL --create-dirs -o .claude/agents/self-audit-orchestrator.md https://raw.githubusercontent.com/mgtechgroup/lyra-lynx-mythonexus/main/agents/self-audit-orchestrator.md
$ curl -fsSL --create-dirs -o .claude/agents/unix-env-auditor.md https://raw.githubusercontent.com/mgtechgroup/lyra-lynx-mythonexus/main/agents/unix-env-auditor.md
$ curl -fsSL --create-dirs -o .claude/agents/windows-env-auditor.md https://raw.githubusercontent.com/mgtechgroup/lyra-lynx-mythonexus/main/agents/windows-env-auditor.md

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 *)"
    ]
  }
}

Subagents (5)

repo-installer
model: inherit
Use this agent when the user asks to clone and install a GitHub repository. This agent handles project-type detection, install workflows, and PATH verification across Windows, macOS, and Linux. Exampl
security-gatekeeper
model: inherit
Use this agent before any `git push` from this repo, when the user asks for a security audit / scan / vulnerability check, or proactively before any commit that touches `scripts/`, `agents/`, `dotfile
self-audit-orchestrator
model: inherit
Use this agent at the start of a new 14-day cycle (Day 1), during the cycle to execute the 2-hour sprint, and at the close (Day 14) for system-wide scoring and improvement installation. Also invoke wh
unix-env-auditor
model: inherit
Use this agent when the user asks for a Unix (macOS/Linux) environment audit, when commands like `python` / `pip` / `<tool>` start failing unexpectedly, when PATH-related issues arise, or proactively
windows-env-auditor
model: inherit
Use this agent when the user asks for a Windows environment audit, when commands like `python` / `pip` / `<tool>` start failing unexpectedly, when PATH-related issues arise, or proactively at the star

Slash commands (8)

/audit/cycle-end/cycle-start/env-audit/install-repo/knowledge/propose-agent/sync-memory

Similar rigs

copied ✓