dabydat/alpha-omega
AI agent harness. It turns any coding model into a self-managing team that delivers top-tier quality for a few tokens. It is a standard operating procedure (instructions + config + scripts) that any AI follows without breaking: opencode, Cl
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 dabydat/alpha-omega/.claude ./rig-alpha-omega # 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 dabydat/alpha-omega/skills/aitmpl-catalog .claude/skills/aitmpl-catalog $ npx degit dabydat/alpha-omega/skills/brainstorm .claude/skills/brainstorm $ npx degit dabydat/alpha-omega/skills/business-analysis .claude/skills/business-analysis $ npx degit dabydat/alpha-omega/skills/cli-dev-tools .claude/skills/cli-dev-tools $ npx degit dabydat/alpha-omega/skills/code-quality .claude/skills/code-quality $ npx degit dabydat/alpha-omega/skills/code-review .claude/skills/code-review $ npx degit dabydat/alpha-omega/skills/deploy .claude/skills/deploy $ npx degit dabydat/alpha-omega/skills/design-patterns .claude/skills/design-patterns $ npx degit dabydat/alpha-omega/skills/harness-standard .claude/skills/harness-standard $ npx degit dabydat/alpha-omega/skills/nestjs .claude/skills/nestjs $ npx degit dabydat/alpha-omega/skills/plan .claude/skills/plan $ npx degit dabydat/alpha-omega/skills/prompt-engineering .claude/skills/prompt-engineering $ npx degit dabydat/alpha-omega/skills/refactoring-techniques .claude/skills/refactoring-techniques $ npx degit dabydat/alpha-omega/skills/run-tests .claude/skills/run-tests $ npx degit dabydat/alpha-omega/skills/token-optimization .claude/skills/token-optimization
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 (15)
aitmpl-catalogbrainstormbusiness-analysiscli-dev-toolscode-qualitycode-reviewdeploydesign-patternsagent-harness-standardnestjsplanprompt-engineeringrefactoring-techniquesrun-teststoken-optimization
Cursor rules (1)
nsp-rev · always
Similar rigs
HumanDealer/vibeproof
Vibe-code anything. Ship like a senior. A drop-in rulebook + skills that turn any AI coding agent (Codex, Claude Code, Cursor) into a disciplined senior engineer — built for domain experts who build with AI.
Pragmatist 2.0k tok ·
selmakcby/claude-agents-skills
Multi-Agent Claude Code setup — 4 uzman ajan (planner · ui-agent · builder · reviewer) + skills + Next.js demo projesi. YouTube Bölüm 1 video materyalleri.
Orchestrator 1.5k tok ·
r3dpepper/claude-dotfiles
Claude code workflow harness files. Goes to ~/.claude in user-scoped location.
Fort Knox 1.5k tok ·
piomin/claude-ai-spring-boot
Claude Code template for Spring Boot and other staff (included in the tags)
Orchestrator 1.2k tok ·