⚡ ZeroToken Skill — 让 Agent 用最少的 token 做最准的事。提示词纪律规范：压缩无效上下文、无效解释、无效工具调用、无效输出，准确性不降。
A protocol for agent work that survives session boundaries — plan, implement, verify in sealed contexts, with proof bundles as the only currency between them.
sonmat (손맛) — Claude Code plugin that builds verification habits into AI-human collaboration
Discipline hooks for Claude Code. Stops the agent from claiming 'done' without proof, blocks accidental writes to ~/.claude config, and routes prompts to skills via local pgvector with zero Anthropic tokens.
Once for all. Stop agents from rediscovering already-solved solutions. Enforce CHECK, EXPLORE, and CODIFY on every task.
AI keeps skipping steps? Super-Spec enforces every step with evidence. Seven-gate engineering discipline for AI coding agents: anti-corner-cutting, verification-first, spec-driven. Stop vibe coding, start spec driving. Production-grade quality for solo developers.
A 200-line CLAUDE.md that fuses Andrej Karpathy's coding rules with field-tested agent-discipline patterns from real Claude Code builds.
Add a description, image, and links to the agent-discipline topic page so that developers can more easily learn about it.
To associate your repository with the agent-discipline topic, visit your repo's landing page and select "manage topics."