Session Visualization with Obsidian

A developer created a script that logs coding agent events into Obsidian vault files, enabling visualization of the model's reasoning path through a graph. The script, shared as a gist, uses pre/post hooks in Claude's settings.json to capture prompts, tool calls, and results, allowing users to see the step-by-step process behind the final output.

on Session Visualization with Obsidian When working with coding agents such as Claude, Codex etc. we provide the prompts and context until we get to the final result. However a lot happens behind the scenes. The model constantly makes calls to tools, MCP servers, commands etc until it arrives at the output. By knowing what path it took, we can begin to understand its reasoning better. One way I have found useful is to use pre/post hooks to log these messages into files and then use Obsidian https://obsidian.md to visualize them. Obsidian is a note taking app which stores notes as files on your local disk. You can link notes together and then visualize them as a graph. In order to demonstrate this, I used claude to create a sample todo app. I had claude generate a script https://gist.github.com/jimmyislive/883238a86c4f8ffe5603c7e3e8d1e903 which would log events for me into a folder of my choice In Obsidian lingo, this folder is called a “ vault https://obsidian.md/help/vault ” . Before you start prompting Claude, you will have to update its settings.json file to call this script in the pre/post hooks: | 1 2 3 4 5 | "hooks": { "UserPromptSubmit": { "hooks": { "type": "command", "command": "python3 ~/.claude/obsidian-tracker/log event.py prompt" } } , "PreToolUse": { "matcher": "mcp . ", "hooks": { "type": "command", "command": "python3 ~/.claude/obsidian-tracker/log event.py tool call" } } , "PostToolUse": { "matcher": "mcp . ", "hooks": { "type": "command", "command": "python3 ~/.claude/obsidian-tracker/log event.py result" } } } | Once this is ready, just prompt claude as you would. It will log all the events into the folder configured in your script. The events are logged into numbered files representing the thought process of the model. You can now see the visual representation of all the steps as to how the model arrived at the final result. You can also go sequentially through the files to understand them and see how the graph builds up. And here is the final todo app: There may be other uses of keeping your session history around, but at least now you have them in an easy visualizable format