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 build-omnigentgit 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/build-omnigent)<a href="https://agentmods.dev/skills/omnigent-ai/omnigent/build-omnigent"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/build-omnigent.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.02279 |
| Opus 5 | $0.00012 | $0.01140 |
| Sonnet 5 | $0.00005 | $0.00456 |
| Haiku 4.5 | $0.00002 | $0.00228 |
Grade A, and why
build-omnigent 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 8d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Generation
Use these patterns to generate a valid agent directory. Always generate the minimal set of files needed — don't over-engineer.
Every template below has been validated with the same parser/validator
that omnigent server uses. If your environment exposes the
validate_agent tool (the dedicated agent-authoring environment does),
run it after generating files to confirm the spec loads. Load the
omnigent-knowledge skill if you need the deeper field reference
(executor types, os_env, guardrails, sandboxing).
Step 1: Choose a directory name
Use the agent name in kebab-case: my-research-agent/
Step 2: Generate config.yaml
Always include:
spec_version: 1name(lowercase, hyphens OK)description(one sentence)instructions— path to a file (defaultAGENTS.md) or inline text. (prompt:is an accepted alias;instructions:wins if both are set.)executor— how the agent runs. See Step 2a.
Include if needed:
tools.builtins— built-in tools. The current set isdownload_file,export_agent,list_files,search_conversations,upload_file,web_fetch,web_search. If thelist_builtin_toolstool is available, call it for the authoritative live set rather than trusting this list.tools.agents— sub-agents, by thenameeach declares underagents/(a sub-agent's directory name may differ from its name).os_env— filesystem/shell access for harness agents (see the shell-capable template).interaction.modalities— if the agent handles images or files.guardrails— runtime policy gates (seeomnigent-knowledge).
Step 2a: Choose an executor
executor.type must be one of claude_sdk, agents_sdk, or
omnigent. There is no llm executor — do not use it.
| Need | executor |
|---|---|
| A fresh, simple LLM agent (default) | claude_sdk (Anthropic) or agents_sdk (OpenAI), in-process |
| Existing Claude SDK / OpenAI Agents SDK code | claude_sdk / agents_sdk |
| A CLI/coding harness, shell + file tools, sub-agents | omnigent + a config.harness |
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.
- 8d ago First seen · 288 lines · 24 tokens per session scan A 531ef88a0043
build-omnigent is a skill published in the GitHub repository omnigent-ai/omnigent (9,752 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 2,279 once invoked, about $0.0001 per session on Opus 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
Codomyrmex
Full-spectrum coding workspace skill providing 627 production MCP @mcptool lines across 130 top-level modules. USE WHEN user says 'verify codomyrmex', 'codomyrmexVerify', 'audit codomyrmex', 'trust codomyrmex', 'codomyrmexTrust', 'trust tools', 'enable destructive tools', 'check pai status', 'codomyrmex tools'…
hugging-face-tool-builder
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
ai-engineer
Builds production AI/ML systems — model training, fine-tuning, MLOps pipelines, model serving, evaluation frameworks, RAG optimization, and agent orchestration at scale. Use when the user asks to build, train, or deploy ML models, set up MLOps pipelines, optimize RAG systems, create inference endpoints, or design…
data-scientist
!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults".
agent-hub-init
Scaffold the agent-hub project profile (.claude/agent-hub/profile.yml + CLAUDE.md) for the current project so the super-team can specialize to it. Use when a project has no profile yet, or when the user says "onboard", "set up the team here", or "create the profile".
decision-log
Record and read architectural decisions (ADRs) for a project so the team's choices persist across sessions. Use when the user says "decide", "record this decision", "why did we choose X", or when a significant technical choice is made.