angadhn/botference
One room, three minds: a multi-LLM planning council for your terminal — you, Claude Code, and Codex debate and ship an implementation plan.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit angadhn/botference/.claude ./rig-botference # 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 angadhn/botference/.agents/skills/grill-me .claude/skills/grill-me $ npx degit angadhn/botference/.agents/skills/paper-review .claude/skills/paper-review $ npx degit angadhn/botference/.agents/skills/plain-speech .claude/skills/plain-speech $ npx degit angadhn/botference/.agents/skills/review-doc .claude/skills/review-doc $ npx degit angadhn/botference/.agents/skills/see-ui .claude/skills/see-ui $ npx degit angadhn/botference/.agents/skills/tufte-viz .claude/skills/tufte-viz
$ curl -fsSL --create-dirs -o .claude/agents/agent-base.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/agent-base.md $ curl -fsSL --create-dirs -o .claude/agents/agent-template.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/agent-template.md $ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/coder.md $ curl -fsSL --create-dirs -o .claude/agents/coherence-reviewer.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/coherence-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/critic.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/critic.md $ curl -fsSL --create-dirs -o .claude/agents/deep-reader.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/deep-reader.md $ curl -fsSL --create-dirs -o .claude/agents/editor.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/editor.md $ curl -fsSL --create-dirs -o .claude/agents/figure-stylist.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/figure-stylist.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/paper-writer.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/paper-writer.md $ curl -fsSL --create-dirs -o .claude/agents/plan.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/plan.md $ curl -fsSL --create-dirs -o .claude/agents/provocateur.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/provocateur.md $ curl -fsSL --create-dirs -o .claude/agents/refactorer.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/refactorer.md $ curl -fsSL --create-dirs -o .claude/agents/research-coder.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/research-coder.md $ curl -fsSL --create-dirs -o .claude/agents/role-analyst.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/role-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/scout.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/security-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/synthesizer.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/synthesizer.md $ curl -fsSL --create-dirs -o .claude/agents/triage.md https://raw.githubusercontent.com/angadhn/botference/main/.claude/agents/triage.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 *)"
]
}
} Skills (6)
Subagents (19)
Similar rigs
j0yen/dotfiles
The claude-self cluster: machine-personal CLAUDE_SELF.md, its SessionStart hook, and the claude-self CLI.
YOLO Cowboy 4.5k tok ·
CloudAI-X/claude-workflow-v2
Universal Claude Code workflow plugin with agents, skills, hooks, and commands
Orchestrator 23.3k tok ·
lucabrag/clo-author-template
Claude Code workflow template for academic research papers. 18 agents, 10 skills, simulated peer review, R&R cycle, 30+ journal profiles.
Orchestrator 3.8k tok ·
mim1963/mim-CC-dev-bootstrap
Claude Code multi-agent dev environment pieces
Orchestrator 5.8k tok ·