Magyar fejlesztésű CodeMap Pro: 87,4 százalékkal kevesebbet olvas a Claude Code

Works with the AI Agents you already use A code map for Claude Code. Claude queries a graph of your project first, then reads only the lines it needs instead of whole files. Auto-refresh hook and a live, local token analytics dashboard included. Converts to your local currency at checkout Example session with this skill installed Where does this project measure the token savings from the Claude Code logs? The savings are measured in live_measure() in scripts/measure.py. I found it with one map query and read only the lines around it, instead of opening the whole files. live_measure() walks every *.jsonl session log in ~/.claude/projects. A map query counts when graphify actually answered. For the next 12 tool calls it looks for partial reads of files in the project the map answered about: Read with offset or limit, or sed -n, head, tail and grep with context in the shell. A read that printed the whole file anyway is not counted. It compares the tokens actually read with the size of the whole file. Results are kept in total, per day and per project, and every tool call counts once by its id. Each log is read line by line, a log that did not change since the last run is not read again, and a log that keeps growing is followed from where the last read ended. Measured with the built-in question test on this repository: a keyword search reading the 5 best matching files in full would have cost 26,681 tokens. The map query plus targeted excerpts cost Connects securely to your tools. The creator never sees your data. Claude Code spends most of its context reading files. Ask where something happens in a big project and it greps, opens five whole files, and reads thousands of lines it never needed. CodeMap Pro gives Claude a map instead. It builds a graph of your project (functions, classes, imports, calls, docs, media and the folder tree) with graphify, and teaches Claude to query the map first and then open only the few lines it points to. In our own Claude Code work it cut file reading by 87.4%: 299,055 tokens of whole files became 37,578 tokens of map queries and targeted excerpts. Your number will differ by project, and the built-in dashboard measures it on your own sessions. No LLM calls, no API keys, no cost per run, no file-count limit. Your code never leaves your machine, and nothing is written into your project folders. The only download is graphify itself (uv tool install graphifyy), and only if it is missing. Does not index the internal content of images, videos, or PDFs. Project maps are stored in ~/.codemap/ or workspace subfolders, not the project root. Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup Your agent shows a sign-in link. Sign in and click Allow. Your agent loads this skill and uses it on your task. It always asks before any payment. Be one of the first to try it. Every listed skill goes through the trust checks below. Checked by our 8-point scan before listing Doesn't do what its page promises? You get your money back. graphify is the PyPI package graphifyy; the installer adds it if missing. Terminal: runs the map builder and graphify queries. Read files: reads the project to build the map and Claude Code's session logs in ~/.claude/projects for the savings dashboard. Write files: maps go to ~/.codemap or <workspace>/graphify-out, and the optional installer adds one SessionStart hook to ~/.claude/settings.json (a backup is saved). Network: only the installer, to run 'uv tool install graphifyy' when graphify is missing; the dashboard listens on 127.0.0.1 only. Environment variables: optional CODEMAP_WORKSPACE and CODEMAP_HOME settings.