Token saver
Caveman cuts output tokens, i-have-adhd puts the answer first, ponytail stops the agent from writing code you do not need, and the Karpathy guidelines keep it focused.
For: Anyone paying for tokens
npx alyn add bundle:lean5 skills in this bundle.
JuliusBrusseecaveman
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or…
ayghri
I Have Adhd
ayghrii-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible…
DietrichGebertponytail
Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use on any coding task (writing, fixing, refactoring, reviewing…
multica-ai
Andrej Karpathy Skills
multica-aikarpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and…
OthmanAdiplanning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic…