universal-modder-unrestricted
AGENTS.md23 starsChanged 47 days agoMITView on GitHub
A game-modding toolkit and a shared knowledge base for AI coding agents: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and anything else that reads AGENTS.md. When someone opens an agent in this repo, they almost always want to mod a game, or to learn how a game was modded.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository37 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- asset-pipelineSkill
- fal-assetsSkill
- game-automationSkill
- game-reconSkill
- game-research-websearchSkill
- mashup-modsSkill
- mod-any-gameSkill
- port-a-modSkill
- publish-modSkill
- reverse-engineeringSkill
- share-field-notesSkill
- showcase-videoSkill
- asset-pipelineSkill
- fal-assetsSkill
- game-automationSkill
- game-reconSkill
- game-research-websearchSkill
- mashup-modsSkill
- mod-any-gameSkill
- port-a-modSkill
- publish-modSkill
- reverse-engineeringSkill
- share-field-notesSkill
- showcase-videoSkill
- asset-pipelineSkill
- fal-assetsSkill
- game-automationSkill
- game-reconSkill
- game-research-websearchSkill
- mashup-modsSkill
- mod-any-gameSkill
- port-a-modSkill
- publish-modSkill
- reverse-engineeringSkill
- share-field-notesSkill
- showcase-videoSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
At the end, share what you learned: write a field note (bin/um kb new ...) and, once your human agrees, open a PR (bin/um kb pr <note> …
- Very specific: line 17
Put it on PATH: export PATH="$PWD/bin:$PATH" (from Windows cmd or PowerShell, add bin to PATH and bin\um.cmd runs it), or install it …
- Very specific: line 20
Every group has --help:
- Very specific: line 42
No MCP? um fal does the same over REST.
- Distinctive: line 56
What you ship: don't commit or publish game files, extracted assets, decompiled source, leaked builds or keys.
- Distinctive: line 72
Wording: keep skills and docs agent-neutral ("the agent", not a product name) except in sections about one specific agent.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
universal-modder
A game-modding toolkit and a shared knowledge base for AI coding agents: Claude Code, Codex, Cursor, Gemini
CLI, GitHub Copilot, OpenCode and anything else that reads AGENTS.md. When someone opens an agent in this
repo, they almost always want to mod a game, or to learn how a game was modded.
Start here
- Read
skills/mod-any-game/SKILL.mdand follow its loop: intake → recon → route → lab (backups) → source of truth → vertical slice → assets → verify in the real game → showcase → publish. - Search the knowledge base first:
bin/um kb search "<game or engine>". Other agents may already have written down the exact versions, routes and gotchas (knowledge/INDEX.md). - At the end, share what you learned: write a field note (
bin/um kb new ...) and, once your human agrees, open a PR (bin/um kb pr <note> --yes). Seeknowledge/README.mdandCONTRIBUTING.md.
Tools
bin/umis the Python CLI, and it sets itself up withuv.- Put it on PATH:
export PATH="$PWD/bin:$PATH"(from Windows cmd or PowerShell, addbinto PATH andbin\um.cmdruns it), or install it anywhere withuv tool install git+https://github.com/rehan-remade/universal-modder. - Every group has
--help:scan: installed games, engine, anti-cheat, loaders, saves, routesfal: sprites, textures, PBR, 3D, rigs, SFX, music, voice, video via fal's REST APIcomfy: images from a local ComfyUI server, with no API keysprite/render3d: art → engine-ready frames (render3dneeds Blender on PATH orBLENDER=...)win: launch, screenshot, input, record on Windows (also from WSL)video: contact sheets and EDL showcase editsbackup: snapshot and restore savespublish: pre-release lintkb: the knowledge base
- Put it on PATH:
- REA (https://github.com/morluto/rea, rea.tools) — the reverse-engineering MCP.
npx rea-agents setupregisters it with your agent and installs its workflow instructions. One server covers native binaries (through a Ghidra, IDA or Hopper install you already have), .NET assemblies and CIL, Android APKs, JavaScript/Electron, WASM, Go and Rust binaries, firmware and SQLite — plus the runtime sessions it owns: Rizin and GDB debuggers, Frida injection, live memory reads. Results come back with their evidence and their unknowns. Needs Node 22+;skills/reverse-engineeringis the workflow. - fal MCP server:
https://mcp.fal.ai/mcpwith headerAuthorization: Bearer $FAL_KEY.- It's pre-configured per agent:
.mcp.json(Claude Code),.codex/config.toml(Codex),.cursor/mcp.json(Cursor),.vscode/mcp.json(VS Code / Copilot),gemini-extension.json(Gemini CLI),opencode.json(OpenCode). - It needs
FAL_KEYin the agent's environment; without it the server doesn't connect. fal's OAuth endpoint,https://mcp.fal.ai/mcp-relay, takes a browser sign-in instead (seeskills/fal-assets). - No MCP?
um faldoes the same over REST. It also finds the key thatum fal key setstored (the desktop keyring on Linux,~/.secrets/fal-keyelsewhere).
- It's pre-configured per agent:
- Skills (
skills/*/SKILL.md, Agent Skills format) are copied where agents look for them in a clone:.agents/skills(Codex, Gemini CLI, Copilot, Cursor, OpenCode) and.claude/skills(Claude Code). Editskills/, then copy it over; a test fails while the copies differ. - Engine playbooks:
skills/mod-any-game/references/engines/. - Worked examples:
examples/terraria-tmodloader,examples/aoe2-de-civ,examples/minecraft-gta5-passthrough,examples/outer-wilds-portal-gun,examples/mindustry-homing,examples/cities-skylines-city-dashboard.
Rules (full reasoning in skills/mod-any-game/SKILL.md)
- What you can mod: any game the user owns, from their own install or their own dumps of discs and cartridges.
- Saves:
um backupsaves before modded launches. - What you ship: don't commit or publish game files, extracted assets, decompiled source, leaked builds or keys. Keep decompiles outside the repo.
- Processes: kill by exact PID (
um win kill), never by name pattern. - Ask first before:
- driving the user's mouse and keyboard;
- installing loaders into game folders or changing the registry;
- publishing anything, PRs included.
- Keep a journal: a
MODLOG.mdin the mod's working folder. It becomes your field note at the end.
Working on the toolkit itself
- Python: 3.10+, deps Pillow, numpy and PyYAML (
uvhandles them viabin/um). Code lives inum/, one module per CLI group, each withregister(sub)and a docstring that doubles as--help. - Windows tools:
um/ps1/*.ps1embed C# 5 (Windows PowerShell 5.1's compiler): no string interpolation, noout var, no expression-bodied members. - Tests:
uv run --with pytest pytest -q tests. CI also runsum kb check --indexandum publish check .. - Wording: keep skills and docs agent-neutral ("the agent", not a product name) except in sections about one specific agent.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

