DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: Yoink functionality from dependencies and avoid supply chain attacks
yoink is a Claude Code plugin that removes complex dependencies from your codebase by reimplementing only the functions you actually use.<p>yoink runs as a three-step, agent skills-based workflow:<p>1. /setup clones the target repo and scaffolds a replacement package.<p>2. /curate-tests generates tests verified against the original's expectations.<p>3. /decompose determines dependencies to keep or decompose based on principles such as "keeping foundational primitives regardless of how narrow they are used".<p>We built yoink in response to the five major supply chain attacks that happened in two weeks, including LiteLLM and axios. We install most of these packages without thinking twice.<p>Andrej Karpathy recently called for re-evaluating the belief that "dependencies are good". OpenAI echoed this in their harness engineering article: agents reason better from reimplemented functionality they have full visibility into, over opaque third-party libraries.<p>yoink makes this capability accessible to anyone.<p>Refer to the GitHub repo to install the plugin to Claude Code: <a href="https://github.com/theogbrand/yoink" rel="nofollow">https://github.com/theogbrand/yoink</a><p>Love to hear what you think!
Yoink addresses a timely and critical pain point in software security and AI agent transparency, capitalizing on a shift toward 'minimal dependency' architectures. However, the project currently exists only as a niche plugin with significant risks regarding long-term code maintainability and a lack of clear defensibility against native IDE integrations.