PedroMosquera/squadai
One config. Every AI agent. Zero drift. Idempotent setup for OpenCode, Claude Code, Cursor, Windsurf, and Copilot.
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · No YOLO mode · Sandbox or ask-first rules · details
Copy this rig
# review before running: this installs third-party code $ claude mcp add context7 -- npx -y @upstash/context7-mcp@latest $ npx degit PedroMosquera/squadai/.claude ./rig-squadai # 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 context7 -- npx -y @upstash/context7-mcp@latest $ npx degit PedroMosquera/squadai/.claude/skills/code-review .claude/skills/code-review $ npx degit PedroMosquera/squadai/.claude/skills/find-skills .claude/skills/find-skills $ npx degit PedroMosquera/squadai/.claude/skills/pr-description .claude/skills/pr-description $ npx degit PedroMosquera/squadai/.claude/skills/testing .claude/skills/testing
$ curl -fsSL --create-dirs -o .claude/agents/designer.md https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/agents/designer.md $ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/agents/explorer.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/proposer.md https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/agents/proposer.md $ curl -fsSL --create-dirs -o .claude/agents/spec-writer.md https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/agents/spec-writer.md $ curl -fsSL --create-dirs -o .claude/agents/task-planner.md https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/agents/task-planner.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/agents/verifier.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Read(./.env*)",
"Read(**/secrets/**)",
"Read(**/.aws/credentials)",
"Read(**/.ssh/id_*)"
],
"ask": [
"Bash(git push --force*)",
"Bash(git push -f*)",
"Bash(git rebase*)",
"Bash(rm -rf /*)",
"Bash(rm -rf ~*)",
"Bash(sudo rm*)",
"Bash(dd if=*)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| Context7 | npm | 1.2k |
Skills (4)
Subagents (8)
| designer model: inherit | Designs architecture and interfaces from the specification |
| explorer model: inherit | Researches requirements and constraints by analyzing the codebase |
| implementer model: inherit | Implements according to specification with strict spec compliance |
| orchestrator model: inherit | | |
| proposer model: inherit | Proposes high-level solutions with tradeoff analysis |
| spec-writer model: inherit | Writes detailed formal specifications from the approved proposal |
| task-planner model: inherit | Breaks the design into dependency-ordered implementation tasks |
| verifier model: inherit | Verifies implementation matches specification contracts and criteria |
Permissions
deny (4)
Read(./.env*)
Read(**/secrets/**)
Read(**/.aws/credentials)
Read(**/.ssh/id_*)
ask (7)
Bash(git push --force*)
Bash(git push -f*)
Bash(git rebase*)
Bash(rm -rf /*)
Bash(rm -rf ~*)
Bash(sudo rm*)
Bash(dd if=*)
allow (0)
—
Similar rigs
ingenierodeatascos-cyber/ai-project-template
AI-First project template for building software with orchestrated AI agents using Spec-Driven Development. Includes router, planner, implementer and reviewer workflows for structured development with Codex, Claude Code or similar AI coding
Orchestrator 196 tok ·
pravindurgani/claude-code-multipane-iterm2
Stop your AI agent from reviewing its own code — 4-pane iTerm2 setup with role-locked Claude Code sessions. Step-by-step guide included.
Minimalist 1.0k tok ·
1a2b3cw/claude-team-config
AI 全栈开发团队配置 v2.0 - 基于 Claude Code 的 5 Agent + 13 Skill 协作开发模板
Orchestrator 33.6k tok ·
edenfunf/promptc
Measure worst-case skill-context exposure in your Claude Code setup.
Pragmatist 136 tok ·