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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add omnigent-ai/omnigent --skill detect-frameworkgit clone --depth 1 https://github.com/omnigent-ai/omnigentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/omnigent-ai/omnigent/detect-framework)<a href="https://agentmods.dev/skills/omnigent-ai/omnigent/detect-framework"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/detect-framework/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/omnigent-ai/omnigent/detect-framework"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/detect-framework.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00575 |
| Opus 5.5 | $0.00012 | $0.00230 |
| Sonnet 5.5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
detect-framework scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framework Detection
When the user has existing Python code they want to integrate into Omnigent, detect the framework from import statements and recommend the appropriate executor type.
Detection Procedure
-
Ask the user for the path to their agent code (or look for Python files in the current directory if filesystem access is enabled).
-
Scan Python files for import patterns. Check in this priority order:
| Import pattern | Framework | Executor type |
|---|---|---|
import anthropic or from anthropic + agent patterns (e.g. Agent, tool, system prompt setup) |
Claude SDK | claude_sdk |
import openai or from openai + agents patterns (e.g. Agent, Runner, function_tool) |
OpenAI Agents SDK | agents_sdk |
from langgraph or import langgraph |
LangGraph | Not natively supported yet |
from deepagents or import deepagents |
DeepAgents | Not natively supported yet |
from langchain or import langchain |
LangChain | Not natively supported yet |
from crewai or import crewai |
CrewAI | Not natively supported yet |
from autogen or import autogen |
AutoGen | Not natively supported yet |
| None of the above | Unknown | Not natively supported yet |
- Report what you found and recommend the executor type.
What to generate for each executor type
llm (default — no existing code)
Generate a standard agent directory:
executor:
type: llm # or omit entirely (llm is the default)
claude_sdk
The user's Claude SDK code runs directly. Generate config that points to their entry module:
executor:
type: claude_sdk
agents_sdk
The user's OpenAI Agents SDK code runs directly:
executor:
type: agents_sdk
Asking about unsupported frameworks
If the user's framework is not natively supported, let them know:
- Explain that Omnigent does not currently have a supported executor for that framework.
- Offer to show them a pre-filled GitHub issue URL requesting first-class support for their framework.
- If they want to start fresh instead, recommend generating a standard
llmagent. - The issue URL format:
https://github.com/dbczumar/omnigent/issues/new?title=...&body=...
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 67 lines · 31 tokens per session scan A 97d078eeed0d
detect-framework is a skill published in the GitHub repository omnigent-ai/omnigent (10,863 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 575 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
python-expert
Conventions for clean, idiomatic Python. Load whenever you read, edit, or write Python source files.
create_jinx
Write a new .jinx file from inputs (name, description, inputs spec as JSON list of strings, python body). Agents use this mid-task to crystallize a repeated block of code into a reusable jinx. The jinx is written to the team's jinxes/lib dir by default and registered with the running team so it is immediately callable…
langgraph
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph…
python-backend
Production Python async patterns including asyncio TaskGroup, FastAPI dependency injection and middleware, SQLAlchemy 2.0 async sessions, and database connection pool tuning. Python 3.11+ runtime concerns such as ExceptionGroup, cancellation semantics, and session rollback. Use when building async services, wiring…
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
python-development
You MUST activate this skill when working on Python projects.