DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to script reports over your agent sessions with JSON with Wallfacer

Export session lists per project as JSON for your own scripts and dashboards.

Short answer: Install Wallfacer and organize sessions into projects; then run wallfacer list --project api --json; Pipe the output into your script. All steps.

Who it is forA developer who wants a weekly summary of where their agent time went.

The problemSession data is spread across four agents' private folders.

The outcomeMachine-readable session lists filtered by project.

What you need first

  • Homebrew or Go
  • At least one of Claude Code, Cursor CLI, Kiro CLI or Codex

Steps

  1. Install Wallfacer and organize sessions into projects
  2. Run wallfacer list --project api --json
  3. Pipe the output into your script
  4. Delete stale sessions with rm, which moves them to trash

Prompt for your agent

Run `wallfacer list --project <project> --json`, count sessions per agent, and report the oldest one. Confirm the counts match what the full-screen browser shows.

Caveat. Deleting with rm only moves sessions to trash, so they are recoverable until emptied.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for pradipta/wallfacer and "Script reports over your agent sessions with JSON"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer