atemaguer/supertag
Persistent, proactive, multiplayer AI actors for engineering work. Define outcomes, not tasks.
field: Developer tools workflow: DocsTesting & TDDPlanning & specsCI/CD & deployData / ETL runs codex in CI
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 atemaguer/supertag/.claude ./rig-supertag # 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 atemaguer/supertag/.claude/skills/add-a-migration .claude/skills/add-a-migration $ npx degit atemaguer/supertag/.claude/skills/docs-conventions .claude/skills/docs-conventions $ npx degit atemaguer/supertag/.claude/skills/public-api-export .claude/skills/public-api-export $ npx degit atemaguer/supertag/.claude/skills/repo-orientation .claude/skills/repo-orientation $ npx degit atemaguer/supertag/.claude/skills/verify-changes .claude/skills/verify-changes $ npx degit atemaguer/supertag/skills/build-a-harness-adapter .claude/skills/build-a-harness-adapter $ npx degit atemaguer/supertag/skills/configure-tags .claude/skills/configure-tags $ npx degit atemaguer/supertag/skills/connect-a-surface .claude/skills/connect-a-surface $ npx degit atemaguer/supertag/skills/deploy-supertag .claude/skills/deploy-supertag $ npx degit atemaguer/supertag/skills/install-and-first-reply .claude/skills/install-and-first-reply $ npx degit atemaguer/supertag/skills/operate-supertag .claude/skills/operate-supertag $ npx degit atemaguer/supertag/skills/run-a-worker .claude/skills/run-a-worker $ npx degit atemaguer/supertag/skills/troubleshoot .claude/skills/troubleshoot
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (13)
Similar rigs
h0x91b/dev-3.0
Mission control for the One Person Studio — run a fleet of AI coding agents in parallel without losing your mind. Kanban + git worktrees + tmux for Claude Code, Codex, Gemini CLI, OpenCode and any shell agent. Not an IDE.
Pragmatist 12.8k tok · · Q21
deymosh/codedeck-plus
Drive coding agents (OpenCode, Claude Code, DeepSeek Harness) on your own machine from Android, over end-to-end encrypted Nostr. No accounts, no server; Tor, NIP-42 relays and a LAN direct link.
Pragmatist 6.3k tok · · Q5
vidbina/dotfiles
Just dotfiles. Managing most of my systems with Nix ❄️ and now with home-manager too. Parts of the configuration are literate 📜, others are just a hot mess of spaghetti 🍝. Here be dragons. 🐲
Pragmatist 6.2k tok · · Q3
marshal-org/runlease
Cheap spot VMs for coding agents, in your own cloud. Every machine deletes itself when its lease ends.
Pragmatist 6.8k tok · · Q8