mcaniot/Omega
Small, versioned agent setup for Claude Code and Codex that keeps the context window clean: shell output stored as evidence, guarded reads, on-demand skills. 87% fewer tokens on reproducible workloads.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit mcaniot/Omega/skills ./rig-omega/skills 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 mcaniot/Omega/skills/cpp-quality .claude/skills/cpp-quality $ npx degit mcaniot/Omega/skills/orca-cli .claude/skills/orca-cli $ npx degit mcaniot/Omega/skills/orchestration .claude/skills/orchestration $ npx degit mcaniot/Omega/skills/retro .claude/skills/retro $ npx degit mcaniot/Omega/skills/robotics-learning .claude/skills/robotics-learning $ npx degit mcaniot/Omega/skills/robotics-performance .claude/skills/robotics-performance $ npx degit mcaniot/Omega/skills/robotics-validation .claude/skills/robotics-validation $ npx degit mcaniot/Omega/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit mcaniot/Omega/skills/tool-output .claude/skills/tool-output
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (9)
Similar rigs
arbourd/dotfiles
Env as code
Pragmatist 3.2k tok · · Q3
mquesada02/agent-config
Personal Claude Code config: CLAUDE.md, skills, hooks and settings
Automator 8.8k tok · · Q20
stablyai/orca
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
Pragmatist 3.3k tok · · Q3
netresearch/retro-skill
LLM-driven session retrospection skill: detects friction in agent sessions and materializes learnings into correct destinations (user-memory, project-rules, skill PRs, checkpoints, harness artefacts)
Minimalist 1.5k tok · · Q0