More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    CodeMap Pro: Claude Code reads 65% less

    1

    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.

    $6

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    CodeMap Pro: Claude Code reads 65% less

    CodeMap Pro: Claude Code reads 65% less

    Example session with this skill installed

    Where does this project measure the token savings from the Claude Code logs?

    • Read your context and instructions
    • Compiled the codemap pro

    Summary

    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.

    Where it happens

    WhatFileLine
    Reads the session logs, counts map queries and the targeted reads after themscripts/measure.py793
    Recognises a map query (graphify query, explain, path) and checks that it answeredscripts/measure.py181
    Finds partial reads in the shell (sed -n, head, tail, grep with context)scripts/measure.py432
    Works out which project a query was about, from its graph.json pathscripts/measure.py201
    Counts each file whole once per session, at most 2,000 linesscripts/measure.py484
    Runs the measurement every 3 seconds while the dashboard is openscripts/dashboard.py35

    How it works

    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 the files that answer named: Read with offset or limit, or sed -n, head, tail and grep with context in the shell. Each file is compared with reading it whole once per session, at most 2,000 lines (the Read tool's limit), so a second excerpt of the same file does not count the whole file again. A file the session read whole anyway saves nothing, and a read that printed the whole file is not counted. 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.

    What this answer cost

    Measured with the built-in question test on this repository: a keyword search reading the 5 best matching files whole would have cost

    18,874 tokens. The map query plus targeted excerpts cost

    3,009 tokens, which is

    84% fewer.

    Next steps

    • Open the dashboard with dashboard.py to see the same numbers for your own sessions.
    • Run codemap.py --folder <project> --measure "<question>" to test any question yourself.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    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 65.6%: 70,473 tokens of whole files became 24,259 tokens of map queries and targeted excerpts, over 25 map queries and 9 targeted reads. That is a small sample, measured on 2026-11-10. Your number will differ by project, and the built-in dashboard measures it on your own sessions.

    What you get

    • The skill: Claude checks the map before it opens files, then reads only the lines that matter.
    • Auto-refresh hook: when a session starts in a project, the map refreshes in the background in a few seconds and Claude is told where it is.
    • Live token analytics dashboard: it reads your Claude Code logs every 3 seconds while it is open, so a new map query shows up within seconds. A live scanner shows the tool calls of every session, a feed lists the latest map queries and targeted reads, and the figures roll to their new values as they change. Real savings per day and per project, a token bridge from whole files to what Claude read, the API cost avoided at the list price of the model you use (or your own rate), question tests, map health and an interactive graph viewer.
    • One-command installer for macOS and Linux, with a clean uninstall.
    • Workspace mode: map a folder of many projects at once, plus one merged graph.

    Privacy and cost

    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.

    Requirements

    Claude Code, uv, macOS or Linux.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Does not index the internal content of images, videos, or PDFs. Project maps are stored in ~/.codemap/ or workspace subfolders, not the project root.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      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

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    Software
    uv (Python tool runner)graphify

    graphify is the PyPI package graphifyy; the installer adds it if missing.

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    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.

    Listed9 days ago
    Updated1 day ago

    What's inside

    Frequently Asked Questions

    Claude queries a graph of your project first and then reads only the lines the map points to, instead of opening whole files. In our own Claude Code work this cut file reading by 65.6% (a small sample: 25 map queries, 9 targeted reads). The built-in dashboard shows the number for your own sessions.

    Code structure is extracted by graphify, so the languages graphify parses get functions, classes, imports and calls in the map, and Markdown docs are mapped too. Every other file (images, video, PDF, office files) still appears in the map as a file in the folder tree.

    No. The map is built and queried on your own machine, with no LLM calls and no API keys. The only download is graphify itself, through uv, when it is not installed yet. The dashboard listens on 127.0.0.1 only.

    The SKILL.md for Claude Code, the map builder, the auto-refresh SessionStart hook, the local token analytics dashboard, and a one-command installer with uninstall. graphify is not bundled: the installer installs it from PyPI (graphifyy) with uv.

    It never writes into your project folders. Maps go to ~/.codemap or to <workspace>/graphify-out. If you install with --hook, one SessionStart hook is added to ~/.claude/settings.json, a backup is saved next to it, and --uninstall removes the hook again.

    Tokens are estimated as characters divided by 4, the same way on both sides. Real usage compares what Claude read after a map query with reading each file that answer named whole, once per session and file, at most 2,000 lines. A file Claude read whole anyway counts as zero. That baseline is an assumption, and negative results are shown too. Versions up to 1.0.5 counted the whole file again at every excerpt, which overstated the saving.

    New in Agents & Orchestration