A plugin for Claude Code
Where the business meets the codebase.
One dashboard on top of your team’s repos. Engineers start apps and Claude runs from the browser. Product, ops and support ask the code directly, read-only, without waiting on an engineer.
Two audiences, one room
Engineers get a home base for running things. Everyone else gets a way to ask how things work, and an answer from the code itself.
Fewer “quick question” interruptions for engineers. Faster, first-hand answers for everyone else.
What’s inside
Natterjack installs a dashboard into your workspace. Here’s what’s on it.
Runs
When Claude needs a decision, it asks on the page and you answer with buttons. Every run keeps its transcript, its subagents and a Changes tab with a diff of what it touched.
claude --resume when you want the keyboard back.Issues
The team’s board from Linear, Jira or GitHub Issues, with two buttons on every ticket. Other trackers can be added through adapters.
/implement skill.Apps & Workspaces
Start and stop each app, or a whole stack, for each git worktree, with logs. No more remembering commands and ports, or keeping six terminals open.
Machine
Natterjack knows what this computer needs for your stack and checks it live: Node, Go, PHP, Python, .NET, Java, Docker, databases and more. Missing something? Click Install.
A question box that starts a Claude run against the real code, read-only by default. While you type, a free local search shows the files Claude will start from. With Confluence connected, it searches and cites your pages too.
A run can watch its pull requests and wake up for a new review or comment, failing checks, a change in review decision, or a branch that’s behind or conflicting.
Team docs from your repos or Confluence, Notion and Drive. Link tiles anyone can add to. Environments, URLs and accounts with click-to-copy values.
Product, ops and support get a simpler dashboard. Build-and-run pages are hidden, and Implement isn’t available to readers.
People without git access download read-only copies of the code, published by CI, and can still Ask, Explore and read the docs.
Search across everything without spending tokens, skills as cards, plan usage limits, memory, and a file explorer.
How setup works
Run one command in the folder that holds your repos. Claude works out your setup, asks about the gaps, and hands you a dashboard that already knows your stack.
Claude scans your repos: stacks, ports, run commands, databases, CI, deploy targets, ticket keys in your branches, and your design system.
It asks only what it couldn’t work out, in a round or two of questions: which repos, which tracker, which apps run together.
It writes the config and brands the dashboard with your team’s own colors and logo, and checks the contrast.
The dashboard starts on localhost. Teammates pull, start it, and the Machine and Repos pages walk them through the rest.
The dashboard is copied into your workspace and you own that copy. Change anything. When a new version comes out, /agentic-os:upgrade merges it around your changes.
Run it your way
Engineers run Natterjack on their own machines. People without a dev machine can use a hosted copy behind your company’s single sign-on. The same workspace serves both.
For engineers
localhost:3333.For product, ops and support
Trust and safety
The dashboard runs Claude and your apps as you, so it only listens to you.
The dashboard binds to 127.0.0.1 only, with checks against DNS rebinding and other origins, and a per-install token on every POST.
Ask runs in plan mode unless you switch it off. People on the reader profile never get Implement.
Tracker keys never reach the browser. Install buttons and app commands come only from config files, never from the page.
Hosted mode isn’t a shared multi-user server. Each person gets their own container, disk and Claude sign-in.
Where it’s heading
Natterjack runs on Claude Code today. Much of the dashboard, like Apps, Machine, Docs, Links and the issue board, is plain tooling that doesn’t need a model at all. We want the agent behind Runs and Ask to be your choice too.
What Natterjack runs on today. Sign in with a Claude subscription, or use an Anthropic API key, Amazon Bedrock or Google Vertex AI.
Codex as the agent behind Runs and Ask, for teams that have standardized on OpenAI.
Open-weight models running locally, through tools like Ollama or LM Studio. Nothing leaves the laptop.
Models you serve inside your own network or cloud account, so prompts and code stay where your security team wants them.
“Exploring” means exactly that: ideas we’re weighing, not dates. Tell us what your team would use.
Get started
Install the plugin in Claude Code, then run create in the folder that holds your team’s repos.
The dashboard’s Machine page helps with everything else your stack needs.
/plugin marketplace add lhoezee/skills
/plugin install agentic-os@lhoezee-skills/agentic-os:createThe plugin is called agentic-os in Claude Code. Afterwards, /agentic-os:doctor checks everything and /agentic-os:upgrade pulls in new versions.