GitHub Repository

Skill, agent, MCP, and harness recommendations for Claude Code/custom LLMs: 102,928-node LLM-wiki graph, 91,464 skills, 467 agents, 10,790 MCPs, 207 harnesses, and capped execution recommendations.

499 starsPython

Ctx, save tokens by loading only the relevant tools

Name: Ctx, save tokens by loading only the relevant tools
Availability: InStock
Author: stevesolun

by stevesolun·Jun 16, 2026·8 points·2 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainNiche Gem

Pre-session tool selection via 102K-node graph beats inline token compression.

Strengths

•102K-node graph with 2.9M edges shows serious curation effort, not just API chaining
•Pre-session selection approach differs from inline compression tools like rtk or caveman
•Automatic skill rot detection flags stale tools you haven't used in months

Weaknesses

•AI tool router category is getting crowded with LangChain and MCP orchestration tools
•Graph maintenance at this scale creates ongoing curation burden for the maintainer

Post Description

Hi HN!

Token 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.

But 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?

People 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.

ctx 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.

It 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.

How 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.

So how this is different from rtk, caveman, ponytail, and similar token-saving tools?

As mentioned above those tools mostly reduce tokens after something is already being used.

rtk compresses command output.

caveman-style tools make the assistant respond with fewer words.

ponytail, is, well, awesome, but again it focuses more on reducing code (YAGNI)

ctx is upstream. It tries to avoid loading irrelevant skills, agents, MCPs, and harnesses into context at all.

So it is not really a replacement. It should work side by side with them!

Use ctx to choose the right tools. Use rtk to reduce terminal-output noise. Use terse-output tools if you want shorter responses.

The goal is simple: save tokens without forcing the user to manually test and compare thousands of possible skills, agents, MCP servers, and harnesses.

Repo: https://github.com/stevesolun/ctx