{"slug": "show-hn-ctx-save-tokens-by-loading-only-the-relevant-tools", "title": "Show HN: Ctx, save tokens by loading only the relevant tools", "summary": "Developer Steve Solun released Ctx, an open-source tool that reduces token costs by selecting only relevant skills, agents, MCP servers, and harnesses before a session begins, rather than compressing data after loading. The tool uses a curated graph of 91k+ skills and other resources to recommend a focused bundle based on repo and task context, aiming to save tokens without manual comparison.", "body_md": "Hi HN!\n\nToken cost has started to become a high topic of concern to all of us. I tried a few (awesome) tools such as rtk, caveman, and the recent (hillarious but effective) ponytail. What they usually do, is in-line token reduction, e.g. try to compress requests / responses as much as possible.\n\nBut then it hit me (and I’m sure others had similar ideas) - just like we have routers that pick the right model, why not have something that will also narrow down the amount of available tools, skills and mcps based on repo/context?\n\nPeople usually accumulate skills, agents, MCP servers, harnesses, prompts, repo instructions, and local scripts. I’m not saying we are all hoarders, but we sort of are. When did you remove a skill recently? After a while, the model has way too many options to choose from.\n\nctx tries to fix that by selecting context before the session gets bloated.So no, it doesn’t cleanup your messy garage, but it gives you magic glasses that let you focus only on the tools you need.\n\nIt does it by watching the repo and task, walks a graph of available tooling, and recommends a small top-scored bundle of skills, agents, MCP servers, and harnesses.\n\nHow does it know? To make sure results are not hallucinated, and repeatable, I curated a list of 91k+ skills, 467 agents, 10.7k MCP servers, 207 harnesses, and built a graph to help ctx make decisions on what to recommend. While I used AI to generate it of course, I curated it and revised it to make sure the data is up to date.\n\nSo how this is different from rtk, caveman, ponytail, and similar token-saving tools?\n\nAs mentioned above those tools mostly reduce tokens after something is already being used.\n\nrtk compresses command output.\n\ncaveman-style tools make the assistant respond with fewer words.\n\nponytail, is, well, awesome, but again it focuses more on reducing code (YAGNI)\n\nctx is upstream. It tries to avoid loading irrelevant skills, agents, MCPs, and harnesses into context at all.\n\nSo it is not really a replacement. It should work side by side with them!\n\nUse ctx to choose the right tools. Use rtk to reduce terminal-output noise. Use terse-output tools if you want shorter responses.\n\nThe goal is simple: save tokens without forcing the user to manually test and compare thousands of possible skills, agents, MCP servers, and harnesses.\n\nRepo: [https://github.com/stevesolun/ctx](https://github.com/stevesolun/ctx)\n\nComments URL: [https://news.ycombinator.com/item?id=48559559](https://news.ycombinator.com/item?id=48559559)\n\nPoints: 2\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-ctx-save-tokens-by-loading-only-the-relevant-tools", "canonical_source": "https://github.com/stevesolun/ctx", "published_at": "2026-06-16 18:14:48+00:00", "updated_at": "2026-06-16 18:49:12.843199+00:00", "lang": "en", "topics": ["developer-tools", "ai-tools", "large-language-models"], "entities": ["Steve Solun", "Ctx", "rtk", "caveman", "ponytail", "MCP", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/show-hn-ctx-save-tokens-by-loading-only-the-relevant-tools", "markdown": "https://wpnews.pro/news/show-hn-ctx-save-tokens-by-loading-only-the-relevant-tools.md", "text": "https://wpnews.pro/news/show-hn-ctx-save-tokens-by-loading-only-the-relevant-tools.txt", "jsonld": "https://wpnews.pro/news/show-hn-ctx-save-tokens-by-loading-only-the-relevant-tools.jsonld"}}