HN Showcase
Back to browse
GitHub Repository

A Claude Code plugin that automatically generates a standup ready update of what you built in the last 24 hours

5 starsPython

Generate Automatic Standup Updates from Claude Code

by alexanderbz·Mar 16, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemNiche Gem

Turns Claude Code traces into standups, replacing manual Toggl time tracking.

Strengths
  • •Deterministic Python parsing avoids LLM hallucination during data extraction phase.
  • •Categorizes work into Bugs, Features, and Other without manual tagging.
  • •Runs locally using session traces, requiring zero extra workflow changes.
Weaknesses
  • •Only works for Claude Code users, excluding Copilot or Cursor users.
  • •Relies on consistent user messaging intent within sessions for accuracy.
Target Audience

Developers using Claude Code for daily tasks

Similar To

Toggl Track · Standuply · Clockify

Post Description

Hi! I built Status Update as an experiment to see if Claude Code's session traces contained enough signal to write your standup for you, without any manual input. Turns out they do a pretty good job.

Quick path to a result: - Inside any Claude Code project, run: `/plugin marketplace add AlexanderBZ/claude-status-update` - Then: `/plugin install status-update` - Then: `/status-update:generate`

You'll get a short exec summary followed by your work categorized into Bugs, Features, and Other, scoped to the last 24 hours of that project.

The Stack: - A Python CLI reads `~/.claude/projects/[current-project]/*.jsonl` and extracts user messages and AskUserQuestion responses as intent signals. No LLM involved in this step, it's fully deterministic. - Claude reads the grouped signals, collapses each session into a work item, classifies it, and writes the exec summary. - Everything runs locally. The scratch file written during processing is deleted after Claude reads it.

This isn't a replacement for writing good commit messages or keeping a work log. It's a last-mile tool for the gap between "I know what I did" and "I need to say it out loud in 60 seconds." It works best when you use plan mode or write messages describing intent. Silent sessions won't produce much.

Currently in early release. Any feedback on or tips on how to approve it are greatly appreciated!

Source (MIT): https://github.com/AlexanderBZ/claude-status-update

Similar Projects

Developer Tools●●Solid

Agent Lens – Code assistant observability in VSCode

Parses local JSONL session files from Copilot, Claude Code, and Codex and surfaces an interactive DAG, per-agent/token metrics, and session replay directly in the activity bar — immediately useful for spotting which agents and skills actually do the work. The Claude cache-token breakdown and timeline replay are clever, concrete features that show the author dug into provider internals; adoption looks small today, but the concept and implementation give real observability where previously there was opacity.

Niche GemWizardry
pjettter
204mo ago