designgrappler/agent-os
Agent OS is a management layer for complex, multi-agent AI projects. Instead of letting agents get lost in endless conversational loops, it enforces a disciplined workflow: upfront planning, shared context, scoped work tracks, and strict qu
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/designgrappler/agent-os 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 designgrappler/agent-os/claude/skills/audit-security .claude/skills/audit-security $ npx degit designgrappler/agent-os/claude/skills/check-agent-os .claude/skills/check-agent-os $ npx degit designgrappler/agent-os/claude/skills/clean-context .claude/skills/clean-context $ npx degit designgrappler/agent-os/claude/skills/close-sprint .claude/skills/close-sprint $ npx degit designgrappler/agent-os/claude/skills/create-agent .claude/skills/create-agent $ npx degit designgrappler/agent-os/claude/skills/editorial-review .claude/skills/editorial-review $ npx degit designgrappler/agent-os/claude/skills/install-agent-scaffold .claude/skills/install-agent-scaffold $ npx degit designgrappler/agent-os/claude/skills/minify-context .claude/skills/minify-context $ npx degit designgrappler/agent-os/claude/skills/orchestrator .claude/skills/orchestrator $ npx degit designgrappler/agent-os/claude/skills/research .claude/skills/research $ npx degit designgrappler/agent-os/claude/skills/setup-connector .claude/skills/setup-connector $ npx degit designgrappler/agent-os/claude/skills/start-sprint .claude/skills/start-sprint $ npx degit designgrappler/agent-os/claude/skills/streamline-approvals .claude/skills/streamline-approvals $ npx degit designgrappler/agent-os/claude/skills/submit-agent-os-feedback .claude/skills/submit-agent-os-feedback $ npx degit designgrappler/agent-os/claude/skills/sync-vercel-env .claude/skills/sync-vercel-env $ npx degit designgrappler/agent-os/claude/skills/track-close .claude/skills/track-close $ npx degit designgrappler/agent-os/claude/skills/track-status .claude/skills/track-status $ npx degit designgrappler/agent-os/claude/skills/triage .claude/skills/triage $ npx degit designgrappler/agent-os/claude/skills/update-agent-os .claude/skills/update-agent-os
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 (19)
Similar rigs
Taloud/sp1ne
shared backbone for my Claude Code setup
Skill Collector 1.7k tok ·
open-gitagent/opengap
A framework-agnostic, git-native standard for defining AI agents
Skill Collector 2.0k tok ·
SynaLinks/synalinks
Keras based framework for neuro-symbolic LM systems
Minimalist 840 tok ·
yuxqiu/nix-config
Personal NixOS + Home Manager config, built with flake-parts
Minimalist 436 tok ·