Fili999/ai-hub
One hub for your AI coding agents, skills and workflows: write them once, install them into Claude Code, Codex, Antigravity CLI and local models. Free, open source, runs on your computer.
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code
$ npx degit Fili999/ai-hub/agents ./rig-ai-hub/agents 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/implementer.md https://raw.githubusercontent.com/Fili999/ai-hub/main/agents/own/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/Fili999/ai-hub/main/agents/own/planner.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/Fili999/ai-hub/main/agents/own/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/Fili999/ai-hub/main/agents/own/reviewer.md
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 *)"
]
}
} Subagents (4)
| implementer | Makes a focused change to code, documents or configuration following an agreed plan, with tests and a short report. Use it after the plan and acceptance criteria are clear, for work that should stay o |
| planner | Turns a vague or large request into a short plan with acceptance criteria, before any work starts. Use it at the start of any non-trivial job to clarify the goal, size and risk, and to decide whether |
| researcher | Finds and checks information from reliable, dated sources and separates verified facts from assumptions. Use it for market or technical research, documentation lookups, comparing options, or any decis |
| reviewer | Checks a result against its acceptance criteria with real evidence and gives a clear pass, fail or blocked, then an honest per-point critique. Use it before calling anything done, merging or publishin |
Similar rigs
Saba-Var/claude-ward
A read-only tripwire that watches Claude Code's local config and reports suspicious changes.
Pragmatist 1.8k tok · · Q21
yopazerbot/brieltje
Smetlede and Briel (Lede, Belgium) in 3D: a walkable village in the browser, alone or with up to 16 friends. Explore, Paintball, Action, and endless waves of Zombies. Three.js and Blender, made with Claude Code and OpenAI Codex..
Pragmatist 4.7k tok · · Q8
juyoungml/nemo-k-cards
Research Korean events, create English Instagram carousels, and publish with human approval. Claude Code + NVIDIA OpenShell.
Orchestrator 4.9k tok · · Q8
danielsaed/sdd-base
Spec-driven development workflow for Claude Code: an orchestrator plus permissioned planner, implementer and reviewer agents — one feature per spec, branch and PR.
Fort Knox 9.7k tok · · Q53