abmach/maestro
Agent Skills bundle that gives AI coding agents a plan → parallel-implement → test → document workflow. Works with Oh My Pi, Claude Code and OpenCode.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit abmach/maestro/skills ./rig-maestro/skills 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 abmach/maestro/skills/arrange .claude/skills/arrange $ npx degit abmach/maestro/skills/audition .claude/skills/audition $ npx degit abmach/maestro/skills/compose .claude/skills/compose $ npx degit abmach/maestro/skills/cue .claude/skills/cue $ npx degit abmach/maestro/skills/elaborate .claude/skills/elaborate $ npx degit abmach/maestro/skills/instruments .claude/skills/instruments $ npx degit abmach/maestro/skills/interlude .claude/skills/interlude $ npx degit abmach/maestro/skills/orchestrate .claude/skills/orchestrate $ npx degit abmach/maestro/skills/prelude .claude/skills/prelude $ npx degit abmach/maestro/skills/rehearse .claude/skills/rehearse $ npx degit abmach/maestro/skills/score .claude/skills/score
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 (11)
Similar rigs
drader/researcher_agent
An LLM-driven research assistance framework for Claude Code (CC BY-NC 4.0)
Pragmatist 1.9k tok ·
snaplyze/claude-orchestration
Claude Code plugin for orchestration: five specialist subagents with explicit model and effort, subscription profiles, user-scope install, and runtime verification
Pragmatist 3.2k tok ·
ChristianBlevens/RaiGolmi
A computer you build by talking to an AI.
Pragmatist 2.7k tok ·
XXX1694/Vanguard
Command center for Claude Code: live pane for your subagent squad, limits and context, an orchestrator with specialist agents, bundled MCP servers and skills, levels and achievements.
Minimalist 307 tok ·