npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

ai-dev-worklog

v0.5.0

Published

Local worklog CLI for AI-assisted development sessions.

Readme

AI Dev Worklog

CI

A local CLI that turns git evidence into a readable AI development worklog.

AI Dev Worklog scans the current git repository and writes a Markdown report, a JSON report, and a continuation prompt. It is useful when an AI-assisted coding session needs a local, reviewable record of what changed, what the task goal was, and how to continue.

The CLI is intentionally small and local-first: it reads git evidence, writes files under .ai-dev-worklog/, and keeps the output on your machine.

What It Does Now

ai-dev-worklog scan records:

  • optional declared intent from --intent
  • changed files from git status --porcelain
  • tracked file changes from git diff --name-status
  • diff summary from git diff --stat
  • raw command output for the scanned git commands
  • structured JSON fields for evidence, observed changes, validation status, risk signals, and next steps
  • a continuation prompt file for the next development session

Quick Start

Run once with npx:

npx ai-dev-worklog scan

Add a task goal for the next session:

npx ai-dev-worklog scan --intent "Prepare the repository for an open-source release"

Install globally:

npm install -g ai-dev-worklog
ai-dev-worklog scan --intent "Review local changes before opening a pull request"

Run from source:

git clone https://github.com/alexan780/ai-dev-worklog.git
cd ai-dev-worklog
npm ci
npm run build
node dist/index.js scan --intent "Verify the local CLI from source"

Local Output

Running ai-dev-worklog scan writes:

.ai-dev-worklog/
  latest.md
  latest.json
  continue-prompt.md

latest.md is the human-readable report. latest.json is the machine-readable scan result. It uses a structured worklog schema that separates declared intent, git evidence, observed changes, validation status, risk signals, and next steps. The formal JSON Schema is available at schema/worklog.schema.json. continue-prompt.md is a prompt-oriented summary for continuing the development session.

Example output is available in examples/basic-worklog.

Example summary:

## Summary

- Git status entries: 2
- Git diff name-status entries: 2
- Changed files: 2
- Working tree has changes: yes
- Validation: not_recorded
- Risk signals: 0
- Declared intent: Prepare the repository for an open-source release

What The CLI Scans

The local CLI reads these git commands:

git status --porcelain
git diff --stat
git diff --name-status

The scan uses local git evidence as the source of truth for observed code changes.

The CLI does not read chat windows, call AI APIs, upload code, or integrate with Codex App, Claude Code, Cursor, or MCP tools.

Privacy And Data Flow

AI Dev Worklog runs locally in the git repository where you call it.

  • It runs local git commands.
  • It writes local files under .ai-dev-worklog/.
  • It does not upload source code or generated worklogs.
  • It does not require an API key.

Why This Exists

When context breaks, tools switch, or a task becomes long, it can be hard to answer:

  • What files actually changed?
  • What git evidence is available?
  • What still needs checking?
  • How should the next session continue?

AI Dev Worklog turns AI-assisted coding sessions into local, reviewable development records.

Local Development

Install dependencies:

npm ci

Build the TypeScript CLI:

npm run build

Run tests:

npm test

Run a local scan:

node dist/index.js scan --intent "Validate local development output"

Generated build output goes to dist/. Generated worklog output goes to .ai-dev-worklog/.

GitHub Actions runs the same install, build, and test checks on pushes to main and on pull requests.

What It Records

The CLI records observed local git evidence.

Current output includes:

  • optional declared intent from the CLI
  • changed files from git status --porcelain
  • tracked file changes from git diff --name-status
  • diff summary from git diff --stat
  • raw command output for the scanned git commands
  • a JSON worklog schema with declared intent, evidence, observed changes, validation status, risk signals, and next steps
  • a continuation prompt file with changed files, command results, risk signals, remaining checks, and suggested next steps

Future versions may add command history and validation evidence.

What It Is

  • Local first
  • Evidence before summary
  • Human-readable Markdown
  • Machine-readable JSON
  • Minimal dependencies

Roadmap

Released

v0.1 - Local Core

  • Scan the current git repository
  • Record changed files from local git evidence
  • Generate latest.md and latest.json
  • Keep all data local

v0.2 - Worklog Schema

  • Define a stable JSON structure for AI coding worklogs
  • Separate declared intent from observed evidence
  • Add unified observed file changes
  • Add validation status and basic risk signals

v0.3 - Continuation Prompt

  • Generate a continuation prompt for the next development session
  • Keep git evidence as the source of truth for observed code changes

v0.4 - Open-source Readiness

  • Add GitHub Actions CI
  • Add a formal JSON Schema file for latest.json
  • Add a changelog and release history
  • Improve README demo flow and roadmap clarity

v0.5 - Declared Intent

  • Add --intent for recording the task goal in local worklog output
  • Include declared intent in Markdown and continuation prompt output
  • Prepare npm metadata and public installation paths

Future Work

  • Command history and validation evidence
  • Optional workflow guides for AI coding tools

Status

This project is in early development. The CLI scans a git repository and generates a local Markdown worklog, a structured JSON scan result, and a continuation prompt.

The next milestones focus on strengthening the local CLI contract before adding optional workflow integrations.