Cyberwise Modbase logo

Cyberwise Modbase

Organization
zenobi-us
cyberwise-modbase

Build and maintain a per-user knowledge base covering every mod actually deployed on this install - the inventory that comes from the deployment manifest rather than a manager's list, how to derive a Nexus id without guessing one, and the order to document them in. Use when asked what a mod does, when auditing a large load order, or when starting a documentation pass.

Overview

Publisherzenobi-us
Repositorydotfiles
Skill namecyberwise-modbase
Stars
67
Forks
6
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zenobi-us on GitHub. Read the source before you install it.

Installation

Install the Cyberwise Modbase AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zenobi-us/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/files/devtools/agent/bundles/developer/skills/game-dev/cyberwise-modbase .claude/skills/cyberwise-modbase
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cyberwise Modbase in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cyberwise Modbase on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cyberwise Modbase is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cyberwise: the mod base

Verified: Cyberpunk 2077 patch 2.31 - August 2026

Load cyberwise for the method rules and cyberwise-wiki for the article format. Everything this skill produces goes in the user bundle and never ships - see the boundary in cyberwise-wiki.

Start from what is deployed, never from a list

powershell
tools\Get-ModInventory.ps1 -GameRoot '<path>' -OutFile inventory.json

This reads <GameRoot>\vortex.deployment.json, which stamps every deployed file with the staging mod that put it there. That matters for two reasons:

  • Staged is not deployed. A manager's list holds disabled mods on purpose, and naming one in a report discredits every other name in it.
  • Nothing on disk says who owns a file. archive\pc\mod is a flat pile of archives. The manifest is the only mapping back to an owner, and without it "which mod put this here" is unanswerable.

On the reference install this yields 812 deployed mods from 8,699 files.

Nexus ids are DERIVED, and a derived id can be wrong

Vortex names staging folders after the download, in one of two shapes:

Immersive Bullet Holes-15309-2k-1718581479        Name-<id>-<version>-<unix stamp>
0-Engine Pure CET 27967 0.18.6 2026-06-29T14-25Z  Name <id> <version> <ISO date>

The inventory reports the id with the pattern that produced it, so a reader can judge the claim. 801 of 812 resolve; the other 11 have no id at all, because a mod installed from a local zip or built by hand never had one.

Verify a sample against the API before building anything on top of the ids. An id derived wrong does not fail - it silently points every later lookup at a different author's mod page, and the article that results is confidently about the wrong software. The API key lives in Proton Pass and the agent session expires; when it does, this whole avenue is blocked and the local sources below are the fallback, not a lesser option.

The local sources outrank the mod page

A description is what the author says it does. These are what it does:

questionread
what settings exist, and their defaultsr6\scripts\<mod>\Config.reds, @runtimeProperty("ModSettings.*")
what the user actually setred4ext\plugins\mod_settings\user.ini
what records it adds or changesr6\tweaks\**\*.yaml
what it hooks@wrapMethod / @replaceMethod / @addField in its .reds
what it registersregisterHotkey / registerForEvent in its CET init.lua
what files it contestscyberwise-conflicts

A settings table built from Config.reds defaults plus user.ini overrides is checkable and dated. One built from a mod page is a paraphrase of marketing.

Order to document in

Depth is not free, so spend it where it is repaid:

  1. Frameworks - anything other mods depend on. Wrong here poisons everything.
  2. Settings-bearing mods - a Config.reds or a Mod Settings category means there are decisions to record, and decisions are what a user comes back for.
  3. Mods already implicated in a finding - the investigation is already done.
  4. Mods that hook shared systems - loot, inventory, vendors, status effects, save/load. These are where interactions come from.
  5. Everything else - name, layer, files, id. A stub that says where a mod lives is worth having; a stub that guesses what it does is not.

Track coverage in the bundle's own log.md and an index.md per directory. Never let the index claim an article that is a stub - a listing that overstates coverage is how a documentation pass quietly stops being trusted.

Tools

toolwhat it does
tools/Get-ModInventory.ps1every deployed mod, its layers, its files, and its derived Nexus id with the pattern that produced it
tools/New-ModStubs.ps1one OKF article per deployed mod in the USER bundle, recording only what is true from disk

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cyberwise Modbase AI skill do?

Build and maintain a per-user knowledge base covering every mod actually deployed on this install - the inventory that comes from the deployment manifest rather than a manager's list, how to derive a Nexus id without guessing one, and the order to document them in. Use when asked what a mod does, when auditing a large load order, or when starting a documentation pass.

Why use Cyberwise Modbase on TypingMind?

Because you install it once and use it with any model. Cyberwise Modbase is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cyberwise Modbase in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zenobi-us/dotfiles/tree/master/files/devtools/agent/bundles/developer/skills/game-dev/cyberwise-modbase. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cyberwise Modbase?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cyberwise Modbase?

As many as you like. As long as a model supports skills, you can use Cyberwise Modbase with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cyberwise Modbase AI skill free?

Yes. It is published on GitHub by zenobi-us under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇