omnigent-ai/omnigent
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
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 omnigent-ai/omnigent/.claude ./rig-omnigent # 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 omnigent-ai/omnigent/.claude/skills/antigravity-native-e2e-dev .claude/skills/antigravity-native-e2e-dev $ npx degit omnigent-ai/omnigent/.claude/skills/antigravity-sdk-e2e-dev .claude/skills/antigravity-sdk-e2e-dev $ npx degit omnigent-ai/omnigent/.claude/skills/cli-setup-verify .claude/skills/cli-setup-verify $ npx degit omnigent-ai/omnigent/.claude/skills/copilot-sdk-e2e-dev .claude/skills/copilot-sdk-e2e-dev $ npx degit omnigent-ai/omnigent/.claude/skills/cursor-sdk-e2e-dev .claude/skills/cursor-sdk-e2e-dev $ npx degit omnigent-ai/omnigent/.claude/skills/harness-integration-guide .claude/skills/harness-integration-guide $ npx degit omnigent-ai/omnigent/.claude/skills/pi-native-e2e-dev .claude/skills/pi-native-e2e-dev $ npx degit omnigent-ai/omnigent/.claude/skills/polly-e2e-dev .claude/skills/polly-e2e-dev $ npx degit omnigent-ai/omnigent/.claude/skills/run-load-test .claude/skills/run-load-test $ npx degit omnigent-ai/omnigent/dev/resolve-agent/skills/resolve-author-fix .claude/skills/resolve-author-fix $ npx degit omnigent-ai/omnigent/dev/resolve-agent/skills/resolve-drive-pr .claude/skills/resolve-drive-pr $ npx degit omnigent-ai/omnigent/dev/resolve-agent/skills/resolve-handoff .claude/skills/resolve-handoff $ npx degit omnigent-ai/omnigent/dev/resolve-agent/skills/resolve-impact-assessment .claude/skills/resolve-impact-assessment $ npx degit omnigent-ai/omnigent/dev/resolve-agent/skills/resolve-inputs .claude/skills/resolve-inputs $ npx degit omnigent-ai/omnigent/dev/resolve-agent/skills/resolve-investigate .claude/skills/resolve-investigate $ npx degit omnigent-ai/omnigent/dev/resolve-agent/skills/resolve-publish .claude/skills/resolve-publish $ npx degit omnigent-ai/omnigent/dev/resolve-agent/skills/resolve-repro-audit .claude/skills/resolve-repro-audit $ npx degit omnigent-ai/omnigent/dev/resolve-agent/skills/resolve-review-pr .claude/skills/resolve-review-pr $ npx degit omnigent-ai/omnigent/examples/debby/skills/debate .claude/skills/debate $ npx degit omnigent-ai/omnigent/examples/deep-research/skills/deep-research .claude/skills/deep-research $ npx degit omnigent-ai/omnigent/examples/polly/skills/cross-review .claude/skills/cross-review $ npx degit omnigent-ai/omnigent/examples/polly/skills/fanout .claude/skills/fanout $ npx degit omnigent-ai/omnigent/examples/polly/skills/investigate .claude/skills/investigate $ npx degit omnigent-ai/omnigent/examples/scribe/skills/api-docs .claude/skills/api-docs $ npx degit omnigent-ai/omnigent/examples/scribe/skills/migration-guide .claude/skills/migration-guide $ npx degit omnigent-ai/omnigent/examples/sentinel/skills/security-audit .claude/skills/security-audit $ npx degit omnigent-ai/omnigent/feature-map/skills/verify-omnigent .claude/skills/verify-omnigent $ npx degit omnigent-<redacted>-omnigent .claude/skills/build-omnigent $ npx degit omnigent-<redacted>-framework .claude/skills/detect-framework $ npx degit omnigent-<redacted>-knowledge .claude/skills/omnigent-knowledge
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 (30)
antigravity-native-e2e-devantigravity-sdk-e2e-devcli-setup-verifycopilot-sdk-e2e-devcursor-sdk-e2e-devharness-integration-guidepi-native-e2e-devpolly-e2e-devrun-load-testresolve-author-fixresolve-drive-prresolve-handoffresolve-impact-assessmentresolve-inputsresolve-investigateresolve-publishresolve-repro-auditresolve-review-prdebatedeep-researchcross-reviewfanoutinvestigateapi-docsmigration-guidesecurity-auditverify-omnigentbuild-omnigentdetect-frameworkomnigent-knowledge
Similar rigs
staruhub/ClaudeSkills
13 curated Agent Skills for research, product decisions, decks, publishing, audits, and more — portable across skills-compatible agents.
Skill Collector 2.0k 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 ·
TheDecipherist/claude-code-mastery
The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands
Pragmatist 823 tok ·
jLAM-ERR/corp-llm-gateway
Corporate LLM gateway. Sanitizes traffic between developer Claude Code instances and Anthropic/OpenAI before it leaves the corp boundary.
Pragmatist 6.6k tok ·