agentopology/agentopology
Harness as code — the Terraform for AI agents. Define your agent team AND its memory once, deploy to Claude Code, OpenClaw, Cursor, Codex, Gemini, Copilot, Kiro. Declarative .at language + agent-maintained, Obsidian-portable company brains
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add supabase -- npx -y supabase --experimental mcp $ claude mcp add trigger -- npx trigger.dev@latest mcp $ npx degit agentopology/agentopology/.claude ./rig-agentopology # 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.
$ claude mcp add supabase -- npx -y supabase --experimental mcp $ claude mcp add trigger -- npx trigger.dev@latest mcp
$ npx degit agentopology/agentopology/.claude/skills/agentopology-skill .claude/skills/agentopology-skill $ npx degit agentopology/agentopology/.claude/skills/parser-dev .claude/skills/parser-dev
$ curl -fsSL --create-dirs -o .claude/agents/AGENT.md https://raw.githubusercontent.com/agentopology/agentopology/main/.claude/agents/binding-engineer/AGENT.md $ curl -fsSL --create-dirs -o .claude/agents/AGENT.md https://raw.githubusercontent.com/agentopology/agentopology/main/.claude/agents/cli-engineer/AGENT.md $ curl -fsSL --create-dirs -o .claude/agents/AGENT.md https://raw.githubusercontent.com/agentopology/agentopology/main/.claude/agents/doc-writer/AGENT.md $ curl -fsSL --create-dirs -o .claude/agents/AGENT.md https://raw.githubusercontent.com/agentopology/agentopology/main/.claude/agents/grammar-engineer/AGENT.md $ curl -fsSL --create-dirs -o .claude/agents/AGENT.md https://raw.githubusercontent.com/agentopology/agentopology/main/.claude/agents/test-engineer/AGENT.md $ curl -fsSL --create-dirs -o .claude/agents/AGENT.md https://raw.githubusercontent.com/agentopology/agentopology/main/.claude/agents/topology-reviewer/AGENT.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 *)"
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| Supabase | npm | 7.0k |
| trigger.dev · "trigger" | npm | 2.5k |
Skills (2)
Subagents (6)
| binding-engineer model: opus | Binding specialist — maintains all 5 platform bindings (Claude Code, Codex, Gemini CLI, Copilot CLI, OpenClaw) and ensures backward compatibility |
| cli-engineer model: sonnet | CLI and tooling specialist — develops the agentopology CLI commands and the interactive HTML visualizer |
| doc-writer model: sonnet | Documentation specialist — maintains examples, README, and docs for the open-source package |
| grammar-engineer model: opus | Language engineer — evolves the .at grammar, AST types, parser, validator, and reserved keywords as a cohesive unit |
| test-engineer model: sonnet | Test specialist — writes comprehensive parser tests, runs vitest, validates all example .at files |
| topology-reviewer model: opus | — |
Slash commands (6)
/binding/cli/docs/grammar/test/validate
Similar rigs
Rohankundra2009/claude-agents-forge
Build and run production-ready Claude Code agents with full agent specs, including turn limits, permissions, memory, and tool orchestration.
Orchestrator 1.3k tok ·
Mationetap/claude-agents-forge
Production-hardened agent system for Claude Code — uses the full agent spec (maxTurns, permissionMode, disallowedTools, Task() orchestration, memory scopes, MCP integration)
Orchestrator 1.3k tok ·
BitRaptors/Archie
Architecture rules your AI coding agent can't break — generates AGENTS.md, per-folder CLAUDE.md, and Claude Code hooks from your codebase.
Pragmatist 27.0k tok ·
supabase/agent-skills
Agent Skills to help developers using AI agents with Supabase
Pragmatist 8.9k tok ·