Agent skill

Omniflow Runtime Modifier

by omnimind-ai in omnimind-ai/OmniBot

Safely inspect, edit, validate, hot reload, and recover the OmniFlow Python runtime inside OpenOmniBot.

Custom licenceAuto-check passedMobile

Install Omniflow Runtime Modifier

skills CLI
$ npx skills add omnimind-ai/OmniBot --skill omniflow-runtime-modifier -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install omnimind-ai/OmniBot omniflow-runtime-modifier --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/omnimind-ai/OmniBot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/omni-vlm-lite/agent-skill/omniflow-runtime-modifier .claude/skills/omniflow-runtime-modifier && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
omniflow-runtime-modifier
GitHub stars
2k
Token cost
~440 tokens
SKILL.md length
187 words
Files
2
Skills in repo
8
Repo updated
First seen
Licence
Custom licence

At a glance

Safely inspect, edit, validate, hot reload, and recover the OmniFlow Python runtime inside OpenOmniBot.

  • Works in 6 steps: Call get_omniflow_python_override… → Call it again with the exact… → Change one owning file with the smallest… → …
  • Changing the VLM planner
  • SKILL.md covers Workflow and Ownership
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Omniflow Runtime Modifier is an agent skill from omnimind-ai/OmniBot. Safely inspect, edit, validate, hot reload, and recover the OmniFlow Python runtime inside OpenOmniBot. Use when changing the VLM planner, prompts, GUI execution policy, replay, retry, checker, Function, or RunLog behavior through the official OmniFlow developer override tools.

Its SKILL.md is about 440 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Mobile. It works with Python and Android. The repository describes itself as: Your on-phone / mobile AI Agent / Claw, capable of operating terminals and performing a wide range of tasks in the Android world || 你的手机 AI 代理,她可以操作终端,也可以完成 Android 世界的广泛任务.

When your agent uses it

  • Changing the VLM planner
  • GUI execution policy
  • RunLog behavior through the official OmniFlow developer override tools

Example prompts

  • “/omniflow-runtime-modifier”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Call get_omniflow_python_override without a path and record the runtime version and modified
  2. Call it again with the exact omniflow/**/*.py path to read current source and SHA-256.
  3. Change one owning file with the smallest coherent edit.
  4. Call apply_omniflow_python_override with the path and complete file content. It validates Python
  5. Exercise the affected operation. Use reload_omniflow_python_override only when a clean worker
  6. If the override is unhealthy, call clear_omniflow_python_override with confirm=true to restore

What it can do on your machine

Read from SKILL.md and the folder at commit 8c25545. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Omniflow Runtime Modifier loads about 440 tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 187 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~440

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 187 words (~440 tokens).

“Treat the packaged runtime as immutable. Make focused Python edits through the Android-managed developer override.”

— opening of SKILL.md by omnimind-ai, Custom licence
name
omniflow-runtime-modifier

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in plugins/omni-vlm-lite/agent-skill/omniflow-runtime-modifier of omnimind-ai/OmniBot.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 8c25545

Compare with similar skills

Omniflow Runtime Modifier next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Omniflow Runtime Modifier compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Omniflow Runtime Modifier this skillomnimind-ai/OmniBot2k—~440Automated safety check: PassCustom licence
Mobilerun Docs Referencedroidrun/mobilerun9.6k—~943Automated safety check: PassMIT
Phoneagentrounak/PhoneAgent798—~2.2kAutomated safety check: PassMIT
Burner Phone Android Controlsmallnest/goclaw598—~436Automated safety check: PassMIT
Ipaship Auditatharvnaik1/ipaship-audit108—~1.5kAutomated safety check: NotesMIT
Vicoa CLIvicoa-ai/vicoa496—~5.7kAutomated safety check: PassAGPL-3.0

Similar skills

  • Mobilerun Docs Reference

    droidrun/mobilerun

    Answers questions about Mobilerun, the LLM-agent framework for automating Android and iOS devices, by pointing the agent to the right page of its v5 documentation.

    9.6k GitHub stars~943 tokensUpdated 3 days ago
    MobileAuto-check passed
  • Phoneagent

    rounak/PhoneAgent

    Control a connected iPhone, iOS simulator, Android emulator, or Android device from macOS through PhoneAgent's JSON-RPC bridge.

    798 GitHub stars~2.2k tokensUpdated 1 mo ago
    MobileAuto-check passed
  • Controls an Android device over ADB in a loop of screenshot, vision analysis, tap and verification, so the agent acts on real on-screen coordinates.

    598 GitHub stars~436 tokensUpdated 6 mo ago
    MobileAuto-check passed
  • Ipaship Audit

    atharvnaik1/ipaship-audit

    A skill your agent uses when auditing iOS/Android app submissions for compliance with Apple App Store Review Guidelines or Google Play Developer Policies.

    108 GitHub stars~1.5k tokensUpdated 4 mo ago
    MobileAuto-check: notes
  • Vicoa CLI

    vicoa-ai/vicoa

    Operate Vicoa from the terminal with the vicoa CLI — list and inspect agent sessions (and their transcripts) across machines, start/resume/stop sessions, manage the task backlog with projects and…

    496 GitHub stars~5.7k tokensUpdated today
    MobileAuto-check passed
  • Meowhub Device

    zhaojiaqi/MeowHub

    Control your Android phone via MeowHub — screenshot, tap, swipe, type, open apps, execute shell commands, make/accept/end calls, and control audio channels.

    111 GitHub stars~3.5k tokensUpdated 4 mo ago
    MobileAuto-check passed

More from omnimind-ai/OmniBot

All 8 skills in this repo
  • Find Install Skills

    omnimind-ai/OmniBot

    Find and install relevant Omnibot skills. An agent skill from omnimind-ai/OmniBot.

    2k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Install Codex Pet

    omnimind-ai/OmniBot

    Install shared Codex pet packages into Omnibot with the official codex-pets npm CLI.

    2k GitHub stars~508 tokensUpdated today
    Auto-check passed
  • Self Improving Agent

    omnimind-ai/OmniBot

    Built-in self-improvement loop for Omnibot agents. An agent skill from omnimind-ai/OmniBot.

    2k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Vibe Project Builder

    omnimind-ai/OmniBot

    Build a standalone phone-first HTML App with an SVG icon, Xiaowan skill, Agent-callable tools, reusable connectors, real data paths, and optional SQLite, then validate, publish, and add it to the…

    2k GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Install Acp Agent

    omnimind-ai/OmniBot

    在当前 Android 设备安装、升级或修复 DSH、Codex、Claude Code、Kimi、OpenCode 等 ACP 助手;用户提供安装命令、要求自主安装或反馈安装未完成时使用。

    2k GitHub stars~477 tokensUpdated today
    Auto-check passed
  • Omnilink Agent

    omnimind-ai/OmniBot

    Use the built-in OmniLink collaboration primitives to inspect trusted devices, compose cross-device event workflows, send messages to another Xiaowan, and continue after reconnect.

    2k GitHub stars~593 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Omniflow Runtime Modifier

What does Omniflow Runtime Modifier do?

Safely inspect, edit, validate, hot reload, and recover the OmniFlow Python runtime inside OpenOmniBot. Omniflow Runtime Modifier is an agent skill from omnimind-ai/OmniBot. Safely inspect, edit, validate, hot reload, and recover the OmniFlow Python runtime inside OpenOmniBot.

When should I use Omniflow Runtime Modifier?

Omniflow Runtime Modifier fits situations like: changing the VLM planner; GUI execution policy; runLog behavior through the official OmniFlow developer override tools.

How do I install Omniflow Runtime Modifier in Claude Code?

Run `npx skills add omnimind-ai/OmniBot --skill omniflow-runtime-modifier -a claude-code`. Or copy the skill folder (plugins/omni-vlm-lite/agent-skill/omniflow-runtime-modifier in omnimind-ai/OmniBot) into .claude/skills/omniflow-runtime-modifier in your project. Claude Code loads it when a task matches its description.

How do I install Omniflow Runtime Modifier in Codex?

Run `npx skills add omnimind-ai/OmniBot --skill omniflow-runtime-modifier -a codex`. Or copy the skill folder (plugins/omni-vlm-lite/agent-skill/omniflow-runtime-modifier in omnimind-ai/OmniBot) into .agents/skills/omniflow-runtime-modifier in your project. Codex loads it when a task matches its description.

Can I use Omniflow Runtime Modifier in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add omnimind-ai/OmniBot --skill omniflow-runtime-modifier -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/omniflow-runtime-modifier, .gemini/skills/omniflow-runtime-modifier, .github/skills/omniflow-runtime-modifier and .opencode/skills/omniflow-runtime-modifier in your project.

What does Omniflow Runtime Modifier need to run?

SKILL.md names no scripts, command-line tools or credentials: Omniflow Runtime Modifier is instructions for the agent only. Our summary lists: Python 3.

Does Omniflow Runtime Modifier access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Omniflow Runtime Modifier safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Omniflow Runtime Modifier use?

Omniflow Runtime Modifier has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Omniflow Runtime Modifier use?

About 440 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Omniflow Runtime Modifier?

Skills that share tags, products or a category with Omniflow Runtime Modifier: Mobilerun Docs Reference (droidrun/mobilerun, 9.6k stars), Phoneagent (rounak/PhoneAgent, 798 stars), Burner Phone Android Control (smallnest/goclaw, 598 stars) and Ipaship Audit (atharvnaik1/ipaship-audit, 108 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Omniflow Runtime Modifier?

omnimind-ai (a GitHub organization) maintains it in omnimind-ai/OmniBot, which has 2,029 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 8, 2026.

Source: omnimind-ai/OmniBot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.