Claude Code hook

Helpline

Demonstration codebase for building the AI Layer (CLAUDE.md hierarchy, hooks, skills, LSP, MCP, plugin) — companion repo for the 'How Claude Code works in large codebases' video.

115 stars 35 forksHooks Source

Install

Inside Claude Code
/plugin marketplace add /path/to/helpline/tooling

Found in the project README. Check it for setup steps after installing.

From source
git clone https://github.com/coleam00/helpline.git

From the README

Helpline

Helpline is a B2B helpdesk and customer-support platform — an internal monorepo
where five services (api, auth, billing, notifications, search) talk
over HTTP and share two internal packages (core, db). It's the kind of
mid-sized, multi-service codebase where an AI coding agent either pays for
itself or quietly makes a mess: shared packages that everything imports, money
rules that must never silently regress, a request gateway with its own
conventions, and tests scattered across services.

Quick start

What this repo actually is. Helpline is a *demonstration codebase*, built
for the YouTube video "The AI Layer: How to Make Claude Code Work in Large
Codebases." It is a deliberately realistic — but compact — complex codebase,
used to show *concretely* how to build an AI Layer — our name for the
harness of configuration and tooling that Anthropic's article describes in
*How Claude Code works in large codebases*.
(The article describes the harness and its components; "AI Layer" is our term
for it, not Anthropic's.)
That article is the *what* and the *why*, and it is excellent — but it stays
high-level. Helpline is the *how*: every component from the article, built and
validated on a real codebase. The rest of this repo is written as if Helpline
were a live product, because that is exactly how you should treat your own
codebase when you give it an AI Layer.

Run it:

See the AI Layer: read AI-LAYER.md — it maps every
component to the article and to where it lives in this repo. Then run the
validator, which proves every piece works end to end:

The AI Layer, concretely

Every codebase you ship with an AI agent has three parts: code, tests,
and — the new one — the AI Layer: the configuration, context, and reusable
workflows that make an agent productive in *your*…
Read the full README on GitHub

How hooks work

  • Hooks are shell commands Claude Code runs at fixed points: before or after a tool call, when you submit a prompt, when Claude stops, on notifications and at session start.
  • They are set in the hooks section of ~/.claude/settings.json (or .claude/settings.json for a project), or come bundled in a plugin.
  • A hook can block a tool call, add context, or run a formatter or test. Read the scripts before you install them: they run on your machine with your permissions.
Claude Code docs

Details

Type
Hooks
Language
Python
Last updated
20 May 2026

FAQ

What is Helpline?

Demonstration codebase for building the AI Layer (CLAUDE.md hierarchy, hooks, skills, LSP, MCP, plugin) — companion repo for the 'How Claude Code works in large codebases' video. It is a hook for Claude Code, from coleam00/helpline on GitHub.

How do I install Helpline?

Run /plugin marketplace add /path/to/helpline/tooling inside Claude Code, then follow the setup in the README.

Is Helpline popular?

coleam00/helpline has 115 GitHub stars and 35 forks. It was last updated on 20 May 2026.

More hooks

Browse the most popular Claude Code mods, all hooks, or the skills and MCP server directories.