Human-Agent-Society/CORAL
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
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 Human-Agent-Society/CORAL/.claude ./rig-coral # 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 Human-Agent-Society/CORAL/.claude/skills/coral-debug .claude/skills/coral-debug $ npx degit Human-Agent-Society/CORAL/.claude/skills/coral-extend .claude/skills/coral-extend $ npx degit Human-Agent-Society/CORAL/.claude/skills/coral-new-task .claude/skills/coral-new-task $ npx degit Human-Agent-Society/CORAL/.claude/skills/promoting-dev-to-main .claude/skills/promoting-dev-to-main $ npx degit Human-Agent-Society/CORAL/coral/template/skills/create-notes .claude/skills/create-notes $ npx degit Human-Agent-Society/CORAL/coral/template/skills/deep-research .claude/skills/deep-research $ npx degit Human-Agent-Society/CORAL/coral/template/skills/organize-files .claude/skills/organize-files $ npx degit Human-Agent-Society/CORAL/coral/template/skills/skill-creator .claude/skills/skill-creator $ npx degit Human-Agent-Society/CORAL/plugin/skills/coral-quickstart .claude/skills/coral-quickstart $ npx degit Human-Agent-Society/CORAL/plugin/skills/creating-a-coral-task .claude/skills/creating-a-coral-task $ npx degit Human-Agent-Society/CORAL/plugin/skills/running-coral-experiments .claude/skills/running-coral-experiments $ npx degit Human-Agent-Society/CORAL/plugin/skills/setting-up-coral .claude/skills/setting-up-coral
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 (12)
Similar rigs
PleasePrompto/ductor
Control Claude Code, Codex CLI and Gemini CLI from Telegram. Live streaming, persistent memory, cron jobs, webhooks, Docker sandboxing.
Minimalist 1.9k tok ·
nateberkopec/dotfiles
yup we're doin the thing
YOLO Cowboy 958 tok ·
AnkitClassicVision/Claude-Code-Deep-Research
I created a claude code deep researcher that seems to work better than the current deep research models
Pragmatist 8.3k tok ·
Abdullah-967/my-claudec0de-setup-2026
Transform Claude Code into a professional autonomous agent. This setup includes structured context handoffs, a features.json tracking system, and built-in workflows for synchronization and semantic commits.
Pragmatist 750 tok ·