oh-my-openagent

oh-my-openagent is a skill for Claude Code, Codex from znlgis/opengis-skills. It costs 114 tokens per session (3,152 once invoked), scanned C, original, MIT.

A plugin that configures OpenCode, an open-source AI coding client, to coordinate several AI models and background agents.

In plain words
What is it for?
Use it for multi-model coding workflows, automation and continuous integration, structured code search and editing, and managing token costs.
Why use it?
It helps divide development work among models suited to different tasks, such as reasoning, code search, or front-end work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit Use it for multi-model coding workflows, automation and continuous integration, structured code search and editing, and managing token costs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/znlgis/opengis-skills/oh-my-openagent
Install

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.

Any agent
npx skills add znlgis/opengis-skills --skill oh-my-openagent
Clone the repo
git clone --depth 1 https://github.com/znlgis/opengis-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for oh-my-openagent

README.md
[![agentmods](https://agentmods.dev/badge/skills/znlgis/opengis-skills/oh-my-openagent/github.svg)](https://agentmods.dev/skills/znlgis/opengis-skills/oh-my-openagent)
Your own site
<a href="https://agentmods.dev/skills/znlgis/opengis-skills/oh-my-openagent"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/oh-my-openagent/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.

agentmods 80×15 button for oh-my-openagent

Your own site · 80×15
<a href="https://agentmods.dev/skills/znlgis/opengis-skills/oh-my-openagent"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/oh-my-openagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,152 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.03152
Opus 5.5 $0.00046 $0.01261
Sonnet 5.5 $0.00023 $0.00630
Haiku 4.5 $0.00011 $0.00315

Measured 9d ago against content hash 3e7cb9ec2334, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

oh-my-openagent scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://get.omo.dev/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: "Use when installing or running OmO (oh-my-openagent) 5.1.48 — the standalone omo CLI built on senpi, migrating an older OpenCode-plugin install with omo setup, choosing thinking levels with /thinking, or sw
ai/oh-my-openagent/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

项目地址: https://github.com/code-yeongyu/oh-my-openagent

官网 / 文档: https://omo.dev | https://omo.dev/docs

npm 包: omo-ai(5.1.48,截至 2026-10)| CLI 命令:omo

许可证: SUL-1.0(Sustainable Use License,商用前阅读条款)

版本关键变化: OmO 5.0 起是独立应用("OmO Native"),跑在作者维护的 senpi(pi 的 fork)上,不再需要 OpenCode。4.x 及更早才是 OpenCode 插件(oh-my-opencode),旧装可用 omo setup 迁移。

概述

OmO 不是模型、也不是 IDE 插件,而是"一条 omo 命令把 token 变成交付物"的终端 Agent:调研、出稿、写后端前端、写代码都在同一套内置能力里。

  • 独立运行时:自带 senpi 引擎,不依赖 OpenCode 的插件注册
  • 多模型编排:不同角色分配不同模型并行跑(订阅型 provider 也支持)
  • 并行后台智能体:任务分给多个后台 agent 并行推进
  • 内置工具集:结构化检索/编辑、浏览器使用等以 skills 形式按需加载
  • 思考档位:/thinking <level>、/efforts <level> 控制推理强度,Shift+Tab 循环切换
  • 会话续接:/resume(或 /sessions)翻历史;shell 里 omo -c 续上一个会话、omo -r 打开选择器
  • 自诊断:omo doctor 看各任务类别能跑哪些 provider、旧安装留下了什么

安装

方式一:官方安装脚本(推荐)

curl -fsSL https://get.omo.dev/install.sh | bash
omo

Windows PowerShell:

irm https://get.omo.dev/install.ps1 | iex

脚本会把对应 OS/CPU 的原生 omo 二进制装到 ~/.local/bin,用发布校验和校验;镜像不可达时回退到 GitHub Releases。要换频道或锁版本,在 bash 后面追加:

curl -fsSL https://get.omo.dev/install.sh | bash -s -- beta
curl -fsSL https://get.omo.dev/install.sh | bash -s -- 5.1.1

方式二:包管理器(bun / npm)

bun add -g omo-ai          # 或 npm i -g omo-ai

npm 上名为 omo 的包是别人的,与本项目无关;认准 omo-ai。

方式三:从旧版(OpenCode 插件)迁移

bunx oh-my-openagent install --platform=native     # 没有 bun 用 npx

这条命令会:① 找到被 oh-my-openagent/oh-my-opencode/lazycodex 占用的全局 omo 并只删这一个文件;② 执行 bun add -g omo-ai(或 npm i -g omo-ai);③ 校验 omo --version 现在确实答的是 omo-ai;④ 询问是否立刻跑 omo setup(--no-tui 时只打印命令)。

验证:

omo --version        # 期望:omo 5.x.x (engine: senpi ...)
omo doctor           # provider/模型可用性 + 旧安装残留

要求:bun(推荐)或 npm,Node 24 或更新。


核心命令

命令 作用
omo 启动交互式会话
omo -c / omo -r 续上一个会话 / 打开历史选择器
omo setup 从 OpenCode 版或 LazyCodex 迁移 provider keys、自定义 provider、MCP、skills 与模型选择
omo doctor 诊断:哪些任务类别能跑、旧安装残留
omo doctor --models 看每个类别与 agent 用哪个模型、按什么顺序回退
omo update 包管理器安装方式下的自更新
omo --version 版本 + 引擎标识

Read the full file on GitHub · 197 lines

Changes

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.

  1. 9d ago Changed · +72 lines · +67 tokens per session scan A → C 3e7cb9ec2334
  2. 21d ago Changed · +1 lines fbb26bd40c46
  3. 22d ago Changed · +8 lines 5d052552879e
  4. 1mo ago Changed 84c88d33a743
  5. 2mo ago First seen · 116 lines · 47 tokens per session scan A 2074562ae2c0

Subscribe to this mod's changes

oh-my-openagent is a skill published in the GitHub repository znlgis/opengis-skills (76 stars, last pushed 10d ago), licensed MIT. It adds 114 tokens to every session and 3,152 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

oh-my-openagent compared with skills from other repositories

oh-my-openagent next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
oh-my-openagentznlgis/opengis-skillsSkill7610d agoMITC114Claude Code, Codex
drug-designsynthetic-sciences/openscienceSkill4.3k2d agoApache-2.0A44Claude Code, Codex
review1024XEngineer/bytemindSkill273mo agoMITA18Claude Code
bug-investigation1024XEngineer/bytemindSkill273mo agoMITA16Claude Code
github-pr1024XEngineer/bytemindSkill273mo agoMITA17Claude Code
repo-onboarding1024XEngineer/bytemindSkill273mo agoMITA21Claude Code
write-rfc1024XEngineer/bytemindSkill273mo agoMITA16Claude Code