Godogen
CLAUDE.md120 starsChanged 7 months agoMITView on GitHub
We develop agents and skills here. They are then used in another folder for Godot game development with Claude Code. Source code lives at the repo root: - skills/ — skill definitions (SKILL.md) and their tool scripts - game.md — CLAUDE.md template for game folders - publish.sh — create ready-to-develop game folder When writing skills: don't give obvious guidance. The agent is a highly capable LLM — handholding only pollutes the context. 程序路径：D:/Godot_v4.6.2-stable_win64.exe
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
When writing skills: don't give obvious guidance.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
We develop agents and skills here. They are then used in another folder for Godot game development with Claude Code.
Layout
Source code lives at the repo root:
skills/— skill definitions (SKILL.md) and their tool scriptsgame.md— CLAUDE.md template for game folderspublish.sh— create ready-to-develop game folder
Skills
- godogen — orchestrator + inline task execution + all pipeline stages (main thread, 1M context)
- godot-api — Godot class API lookup (context: fork, sonnet, Explore agent)
- visual-qa — visual quality assurance via Claude vision (context: fork)
When writing skills: don't give obvious guidance. The agent is a highly capable LLM — handholding only pollutes the context.
程序路径：D:/Godot_v4.6.2-stable_win64.exe
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.