roberdan-os
CLAUDE.md2 starsChanged 32 days agoMITView on GitHub
Thin pointer. The canonical instructions for this repository live in AGENTS.md — read that file. This was previously a symlink to AGENTS.md, which made agents load the same text twice in every session. Kept as a pointer to halve the per-call context.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- roberdan-twinSkill
- apple-designerSkill
- auto-checkpointSkill
- engineering-referenceSkill
- film-directorSkill
- focus-groupSkill
- jevSkill
- linear-uiSkill
- long-running-jobsSkill
- model-selection-policySkill
- instagram-reel-previewSkill
- premortemSkill
- problem-validationSkill
- reviewSkill
- shipSkill
- syncSkill
- verify-doneSkill
The file
Files
CLAUDE.md → AGENTS.md
Thin pointer. The canonical instructions for this repository live in
AGENTS.md — read that file.
This was previously a symlink to AGENTS.md, which made agents load the same
text twice in every session. Kept as a pointer to halve the per-call context.
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.