juunge
European Arrogance
Anthropic Discloses That AI Models Testing Hacked Three Companies
OpenAI's rogue agent compromised a customer at a second tech firm
The Meta Repo
Capitalism Gone Wrong
We Don't Have to Be This Bad at Improving Society
An Early Example of Super Bad AI Governance
Everyone got excited they can suddenly code, and missed the point
Share AI Agent Skills Across Your Team
Re:Ralph.md: A Markdown format for autonomous coding-agent loops
on Thursday March 26, 2026 @05:31PM (#47536053)
RALPH.md is a skill-like format for reusable agent loops. It defines the outer loop around an agent run: the agent command, the commands to run between iterations, the arguments for steering, and the prompt body. That makes it possible to package and share loops that run repeatedly until stopped. I’ve been writing down example patterns and use cases in the cookbook as I learn what works well: https://ralphify.co/docs/cookbook/
Ralph.md: A Markdown format for autonomous coding-agent loops
Re:LNAI – Define AI coding tool configs once, sync to Claude, Cursor, ...
on Tuesday February 03, 2026 @11:45AM (#46873394)
That would be great! And thanks for your take on this problem, I love to see others take on solving it
Re:LNAI – Define AI coding tool configs once, sync to Claude, Cursor, ...
on Tuesday February 03, 2026 @10:25AM (#46872138)
I really like the idea of an agent package manager! I built something similar aiming to be like uv but for AI agents https://github.com/kasperjunge/agent-resources
Skills Are Replacing Commands, Rules, and Subagents
Show HN: NPM/uv for Claude Code – install skills from GitHub with one command
https://github.com/kasperjunge/agent-resources/blob/main/README.md
Got tired of manually copying files to .claude/ and managing skills across projects. So I built agr (agent-resources) — basically open source npm/uv but for Claude Code.The gist:uvx agr add anthropics/skills/skill-creator(Or pip install agr if you want it permanently)Link: https://github.com/kasperjunge/agent-resourcesFormat is <username>/<repo>/<resource-name> - works for...
Show HN: Skill-Add – Share and Install Claude Code Skills from GitHub
https://github.com/kasperjunge/skill-add
I built a small CLI to make it easy to share and reuse Claude Code skills.skill-add solves this: create an agent-skills repo on GitHub with your skills, and anyone can install them with:skill-add yourname/skill-nameIt downloads the skill from github.com/yourname/agent-skills and copies it to .claude/skills/ in your current project.That's it. No registry, no auth, just GitHub repos.Built with...
MCP (Or Similar Standards) Could Change the Way We Use Software with AI
The Next Big Platform Is Language
How xAI made the world largest GPU cluster operational in 122 days
Re:Show HN: Transform Your Codebase into a Single Markdown Doc for Fee...
on Saturday February 15, 2025 @02:30AM (#43056618)
I’ve made a CLI tool that does something similar, called Copcon:
https://github.com/kasperjunge/copcon
Point it at a code project directory to get a file tree and content, optionally with a git diff, copied to the clipboard - ready for copy pasting into ChatGPT.
It is very true that this only works for small projects, as you will bloat the LLM’s context with large codebases.
My solution to this is two files you can use to steer the tool’s behavior:
- .copconignore: For ignoring specific files and directories.
- .copcontarget: For targeting specific files and directories (applied before .copconignore).
These two files provide great control over what to include and exclude in the copied context.