autopus-ai/autopus-adk
Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/autopus-ai/autopus-adk 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 autopus-ai/autopus-adk/.omp/skills/agent-pipeline .claude/skills/agent-pipeline $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-canary .claude/skills/auto-canary $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-dev .claude/skills/auto-dev $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-doctor .claude/skills/auto-doctor $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-fix .claude/skills/auto-fix $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-go .claude/skills/auto-go $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-goal .claude/skills/auto-goal $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-idea .claude/skills/auto-idea $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-map .claude/skills/auto-map $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-plan .claude/skills/auto-plan $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-qa .claude/skills/auto-qa $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-review .claude/skills/auto-review $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-secure .claude/skills/auto-secure $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-setup .claude/skills/auto-setup $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-status .claude/skills/auto-status $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-sync .claude/skills/auto-sync $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-test .claude/skills/auto-test $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-update .claude/skills/auto-update $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-verify .claude/skills/auto-verify $ npx degit autopus-ai/autopus-adk/.omp/skills/auto-why .claude/skills/auto-why $ npx degit autopus-ai/autopus-adk/.omp/skills/auto .claude/skills/auto $ npx degit autopus-ai/autopus-adk/.omp/skills/ax-annotation .claude/skills/ax-annotation $ npx degit autopus-ai/autopus-adk/.omp/skills/browser-automation .claude/skills/browser-automation $ npx degit autopus-ai/autopus-adk/.omp/skills/codebase-design .claude/skills/codebase-design $ npx degit autopus-ai/autopus-adk/.omp/skills/debugging .claude/skills/debugging $ npx degit autopus-ai/autopus-adk/.omp/skills/frontend-verify .claude/skills/frontend-verify $ npx degit autopus-ai/autopus-adk/.omp/skills/idea .claude/skills/idea $ npx degit autopus-ai/autopus-adk/.omp/skills/planning .claude/skills/planning $ npx degit autopus-ai/autopus-adk/.omp/skills/prd .claude/skills/prd $ npx degit autopus-ai/autopus-adk/.omp/skills/review .claude/skills/review $ npx degit autopus-ai/autopus-adk/.omp/skills/security-audit .claude/skills/security-audit $ npx degit autopus-ai/autopus-adk/.omp/skills/spec-review .claude/skills/spec-review $ npx degit autopus-ai/autopus-adk/.omp/skills/tdd .claude/skills/tdd $ npx degit autopus-ai/autopus-adk/.omp/skills/testing-strategy .claude/skills/testing-strategy $ npx degit autopus-ai/autopus-adk/.omp/skills/using-autopus .claude/skills/using-autopus $ npx degit autopus-ai/autopus-adk/.omp/skills/verification .claude/skills/verification $ npx degit autopus-ai/autopus-adk/.omp/skills/worktree-isolation .claude/skills/worktree-isolation
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 (37)
agent-pipelineauto-canaryauto-devauto-doctorauto-fixauto-goauto-goalauto-ideaauto-mapauto-planauto-qaauto-reviewauto-secureauto-setupauto-statusauto-syncauto-testauto-updateauto-verifyauto-whyautoax-annotationbrowser-automationcodebase-designdebuggingfrontend-verifyideaplanningprdreviewsecurity-auditspec-reviewtddtesting-strategyusing-autopusverificationworktree-isolation
Similar rigs
Zack-Zz/ai-code
Complete ai Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
Pragmatist 1.9k tok ·
romiluz13/cc10x
The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.
Skill Collector 775 tok ·
tae0y/python-project-template
Project template for Claude Python Vibecoding workflow
Orchestrator 17.9k tok ·
rafagomes/ai-workflow
AI-assisted development workflow toolkit for Claude Code, Cursor, and Codex — skills, agents, and conventions for the full SDLC
Skill Collector 4.0k tok ·