DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to add Claude Code hooks for session and tool activity with Agenttrail

Connect Claude Code through reviewed hooks so Agenttrail shows session trails and tool activity.

Who it is forA developer who runs Claude Code in a repo and wants session and tool activity visible in Agenttrail beyond plain file changes.

The problemPlain file observation does not show which Claude Code session did what or which tools it used.

The outcomeSession and tool activity from Claude Code appears in the Map and Kitchen views, and the hook setup can be reversed.

What you need first

  • Node.js 20 or newer
  • A browser with WebGL
  • A local project folder (a git repo and PLAN.md are optional)

Steps

  1. Run npx agenttrail init in the repo and accept the local Claude Code hooks offer after reviewing it.
  2. Or, for Kitchen, run npx agenttrail-kitchen . and choose **Connect agents**, then pick the provider you use.
  3. Review the hook changes listed in the setup before confirming.
  4. Restart the agent conversation if it does not load newly installed hooks.
  5. Run a short task in Claude Code and confirm session activity appears in the view.

Prompt for your agent

In the repo <repo-path>, set up Agenttrail Claude Code hooks using the reviewed setup flow, then restart the Claude Code conversation. Report which provider settings files were changed. Verify that a short test task in Claude Code produces visible session activity in the Map or Kitchen view.

Caveat. Map's Claude hook view can show shortened command text and tool details, so review what is visible before sharing any recording.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page