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.
Omnigent is an open-source orchestration layer for running and coordinating different AI coding agents through one system. It is for developers who want to combine agents, apply policies and sandboxing, and continue sessions across devices. The catalogue add-ons extend its agent workflows.
This repository also configures its own agents. See what omnigent tells them →
▶ Omnigent: The New Meta-Harness for EVERY Coding Agent - Claude Code, Codex, Pi, More Cole Medin · about omnigent-ai/omnigent · on YouTube → Skill Claude CodeCodex
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
Skill Claude CodeCodex
Have the Claude and GPT partners critique each other's answers across a configurable number of rounds (default 1) before converging on a synthesis. Use when the user wants the two perspectives stress-tested against each other, not just shown side by side.
Skill Claude CodeCodex
Procedure for answering a question with a thorough, cross-checked, cited web-research report using the Keenable search + fetch tools.
Skill Claude CodeCodex
Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.
Skill Claude CodeCodex
Run independent subtasks in parallel — one git worktree and one implementation sub-agent per task, each opening its own PR — then cross-review every PR. polly never merges; the human does.
Skill Claude CodeCodex
Delegate read-only investigation, debugging, audit, search, or code-understanding tasks to sub-agents; synthesize only from their structured reports.
Skill Claude CodeCodex
Document a module or public API surface (functions, classes, CLI commands, endpoints) from the code itself. Use when the user asks for API reference, to document a module, or to write usage docs for a public interface.
Skill Claude CodeCodex
Turn a range of commits or merged PRs into a changelog entry grouped by change type. Use when the user asks for release notes, a changelog, or "what changed" between two points.
Skill Claude CodeCodex
Turn a breaking change (an API rename, removed flag, changed default, or moved module) into concrete upgrade steps with before/after examples. Use when the user asks how to migrate, upgrade, or adapt to a breaking change.
Skill Claude CodeCodex
Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and produce a structured findings report. Use when the user asks for a security review, an audit, or to check code for vulnerabilities. Report only — never fix.
Skill Claude CodeCodex
Patterns and templates for generating valid Omnigent agent directories. Load when ready to create files.
Skill Claude CodeCodex
Detect Python agent frameworks from code imports and map them to Omnigent executor types. Load when the user has existing agent code to integrate.
Skill Claude CodeCodex
Deep reference on Omnigent config format, executor types, skill/tool structure, and conventions. Load when you need to look up how the platform works.
Skill Claude CodeCodex
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
Skill Claude CodeCodex
Drive an open PR through Polly/OCR, validation, and maintainer handoff.
Skill Claude CodeCodex
Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.
Skill Claude CodeCodex
Select the Resolve mode, recover its input, check the workspace, and discover existing fixes.
Skill Claude CodeCodex needs its repo
Commit the validated fix and follow local-only, workflow-owned, or direct PR publication.
Skill Claude CodeCodex
Audit a recovered repro patch, assertions, and behavioral baseline before authoring or reviewing.
Skill Claude CodeCodex
Review an existing fix PR using the audited repro and full diff, preserving branch and approval rules.
Skill Claude CodeCodex
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
Skill Claude CodeCodex
Verify the reported path, cause, and historical intent before choosing a fix.
Skill Claude CodeCodex
Run Polly and OCR on a PR until all findings settle.
Skill Claude CodeCodex
Handle trusted reviewers' change requests on Otto PRs.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: